* [Agent Canvas v1.16.0](https://github.com/OpenHands/OpenHands) – Self-hosted developer control center that runs coding agents across local, remote, or cloud backends and automates everyday engineering workflows.

* [Langfuse v4.22.0](https://github.com/langfuse/langfuse) – LLM engineering platform for collaboratively developing, monitoring, evaluating, and debugging AI applications.

* [Langfuse v4.21.0](https://github.com/langfuse/langfuse) – LLM engineering platform for collaboratively developing, monitoring, evaluating, and debugging AI applications.

* [Ollama v0.33.0](https://github.com/ollama/ollama) – Tool for running and managing large language models.

* [Langfuse v4.19.0](https://github.com/langfuse/langfuse) – LLM engineering platform for collaboratively developing, monitoring, evaluating, and debugging AI applications.

* [Dify 1.17.0](https://github.com/langgenius/dify) – Platform for developing large language model applications with AI workflows, model management, and observability.

* [Langfuse v4.18.0](https://github.com/langfuse/langfuse) – LLM engineering platform for collaboratively developing, monitoring, evaluating, and debugging AI applications.

* [Langfuse v4.17.0](https://github.com/langfuse/langfuse) – LLM engineering platform for collaboratively developing, monitoring, evaluating, and debugging AI applications.

* [CopilotKit v1.69.0](https://github.com/CopilotKit/CopilotKit) – Tool for building integrated AI assistants and agents that operate within user applications.

* [Agent Canvas v1.15.0](https://github.com/OpenHands/OpenHands) – Self-hosted developer control center that runs coding agents across local, remote, or cloud backends and automates everyday engineering workflows.

* [Langfuse v4.16.0](https://github.com/langfuse/langfuse) – LLM engineering platform for collaboratively developing, monitoring, evaluating, and debugging AI applications.

* [Frontman v4.0.0](https://github.com/frontman-ai/frontman) – Browser-based tool that edits a project's frontend source code from live UI interactions and natural-language instructions.

* [LangChain langchain-anthropic=...](https://github.com/langchain-ai/langchain) – Framework for building agents and LLM-powered applications with modular components and integrations.

* [Token Optimizer MCP v6.0.0](https://github.com/ooples/token-optimizer-mcp) – Model Context Protocol server that optimizes Claude Code context usage using caching, Brotli compression, and smart tool replacements for large text and file operations.

* [opencodex v2.34.0](https://github.com/lidge-jun/opencodex) – Lightweight local proxy that translates Codex Responses API into multiple LLM providers with full support for streaming, tools, reasoning tokens, and images.

* [FinanceMCP (Synapse) - MCP v4.11.0](https://github.com/guangxiangdebizi/FinanceMCP) – MCP integrating Tushare and Binance APIs to provide real-time multi-asset financial data and news for language models.

* [opencodex v2.33.0](https://github.com/lidge-jun/opencodex) – Lightweight local proxy that translates Codex Responses API into multiple LLM providers with full support for streaming, tools, reasoning tokens, and images.

* [TencentDB Agent Memory v2.0.1](https://github.com/TencentCloud/TencentDB-Agent-Memory) – TencentDB Agent Memory provides symbolic short-term and layered long-term memory for AI agents to retain context and reduce token usage without external APIs.

* [Aiden v4.21.0](https://github.com/taracodlabs/aiden) – Local-first AI operating system for Windows, Linux, WSL, and macOS with 1,400+ skills, 80+ tools, and provider routing.

* [avoid-ai-writing v3.26.0](https://github.com/conorbronsdon/avoid-ai-writing) – Audit and rewrite content to remove AI writing patterns, with detect-only or edit-in-place modes and configurable voice profiles for agent skills.

* [opencodex v2.32.0](https://github.com/lidge-jun/opencodex) – Lightweight local proxy that translates Codex Responses API into multiple LLM providers with full support for streaming, tools, reasoning tokens, and images.

* [LLM Gateway v1.14.0](https://github.com/theopenco/llmgateway) – API gateway that routes and manages requests across multiple LLM providers with an OpenAI-compatible API, usage analytics, and cost tracking.

* [opencodex v2.31.0](https://github.com/lidge-jun/opencodex) – Lightweight local proxy that translates Codex Responses API into multiple LLM providers with full support for streaming, tools, reasoning tokens, and images.

* [Aiden v4.20.0](https://github.com/taracodlabs/aiden) – Local-first AI operating system for Windows, Linux, WSL, and macOS with 1,400+ skills, 80+ tools, and provider routing.

* [FastGPT v4.16.1](https://github.com/labring/FastGPT) – Knowledge-based platform leveraging LLMs for data processing, retrieval, and AI workflow orchestration.

* [CopilotKit v1.69.3](https://github.com/CopilotKit/CopilotKit) – Tool for building integrated AI assistants and agents that operate within user applications.

* [Ax 24.0.10](https://github.com/ax-llm/ax) – End-to-end streaming framework for building multi-modal agents with typed signatures.

* [Ax 24.0.9](https://github.com/ax-llm/ax) – End-to-end streaming framework for building multi-modal agents with typed signatures.

* [Reasonix studio-v2.9.0](https://github.com/esengine/DeepSeek-Reasonix) – DeepSeek-native AI coding agent for your terminal, engineered around prefix-cache stability to keep token costs low across long sessions.

* [SQLBot v1.10.1](https://github.com/dataease/SQLBot) – RAG-based conversational data analysis and Text-to-SQL generation using large language models.

* [Ollama v0.33.1](https://github.com/ollama/ollama) – Tool for running and managing large language models.

* [Promptfoo 0.122.1](https://github.com/promptfoo/promptfoo) – Developer-friendly local tool for testing, evaluating, and securing large language model applications.

* [Kortix v0.13.6](https://github.com/kortix-ai/suna) – Autonomous company OS where Linux-sandboxed AI agents run code, manage files, and automate operations 24/7.

* [Bifrost plugins/telemetry/v1...](https://github.com/maximhq/bifrost) – High-performance AI gateway offering multi-provider access with automatic failover, load balancing, and zero-downtime deployments.

* [Headroom v0.9.0](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [Abu v0.42.0](https://github.com/PM-Shawn/Abu-Cowork) – Privacy-first desktop AI coworking app with multi-model support, agent skills, IM integration, MCP/Playwright, scheduling, and built-in security controls.

* [Reasonix studio-v2.8.0](https://github.com/esengine/DeepSeek-Reasonix) – DeepSeek-native AI coding agent for your terminal, engineered around prefix-cache stability to keep token costs low across long sessions.

* [NoteGen note-gen-v0.36.0](https://github.com/codexu/note-gen) – Cross-platform Markdown note-taking application using AI to organize fragmented knowledge into readable notes.

* [Bifrost core/v1.8.0](https://github.com/maximhq/bifrost) – High-performance AI gateway offering multi-provider access with automatic failover, load balancing, and zero-downtime deployments.

* [Mastra @mastra/core@1.62.0](https://github.com/mastra-ai/mastra) – Opinionated TypeScript framework for building AI applications and features quickly.

* [freebuff-proxy v1.2.0](https://github.com/trefeon/freebuff-proxy) – High-performance OpenAI-compatible gateway and protocol bridge that manages sessions, pools tokens, and forwards chat completions with SSE streaming and TLS stealth.

* [Prompt Optimizer v2.11.9](https://github.com/linshenkx/prompt-optimizer) – Tool for enhancing prompt quality to improve AI interaction results.

* [CopilotKit v1.69.2](https://github.com/CopilotKit/CopilotKit) – Tool for building integrated AI assistants and agents that operate within user applications.

* [CopilotKit v1.69.1](https://github.com/CopilotKit/CopilotKit) – Tool for building integrated AI assistants and agents that operate within user applications.

* [Gerbil v1.28.0](https://github.com/lone-cloud/gerbil) – Desktop app for running Large Language Models locally with cross-platform support and integrated image generation.

* [Sokuji v0.39.0](https://github.com/kizuna-ai-lab/sokuji) – Desktop application providing live speech translation and audio routing using multiple AI-powered APIs.

* [yzma v1.25.0](https://github.com/hybridgroup/yzma) – Go-based library for hardware-accelerated local inference with llama.cpp integration.

* [Ax 24.0.8](https://github.com/ax-llm/ax) – End-to-end streaming framework for building multi-modal agents with typed signatures.

* [Read Frog v1.46.5](https://github.com/mengxi-ream/read-frog) – AI-powered browser extension for immersive language learning with translation and article analysis.

* [easy-stock v0.9.0](https://github.com/jundizhou/easy-stock) – Local-first A 股行情分析与AI智能投研代理，支持日常共识与短线研判。

* [easy-stock v0.8.0](https://github.com/jundizhou/easy-stock) – Local-first A 股行情分析与AI智能投研代理，支持日常共识与短线研判。

* [Ax 24.0.7](https://github.com/ax-llm/ax) – End-to-end streaming framework for building multi-modal agents with typed signatures.

* [opencodex v2.32.1](https://github.com/lidge-jun/opencodex) – Lightweight local proxy that translates Codex Responses API into multiple LLM providers with full support for streaming, tools, reasoning tokens, and images.

* [Reasonix v1.31.4](https://github.com/esengine/DeepSeek-Reasonix) – DeepSeek-native AI coding agent for your terminal, engineered around prefix-cache stability to keep token costs low across long sessions.

* [Vellium v1.1.0](https://github.com/tg-prplx/vellium) – Desktop chat app using Electron, local Express API, and SQLite for roleplay and creative-writing LLM workflows.

* [Memmy v1.1.0](https://github.com/MemTensor/memmy-agent) – Memory hub and local agent runtime that provides shared long-term personal context across multiple AI agents.

* [Reasonix studio-v2.6.0](https://github.com/esengine/DeepSeek-Reasonix) – DeepSeek-native AI coding agent for your terminal, engineered around prefix-cache stability to keep token costs low across long sessions.

* [llm.rb v15.1.0](https://github.com/r-uby-dev/llm) – Advanced Ruby AI runtime for building capable applications with multiple LLM providers, streaming, tool calls, and RAG support.

* [Cherry Studio v2.0.9](https://github.com/CherryHQ/cherry-studio) – Desktop client supporting multiple LLM providers, available on Windows, Mac, and Linux.

* [Kortix v0.13.5](https://github.com/kortix-ai/suna) – Autonomous company OS where Linux-sandboxed AI agents run code, manage files, and automate operations 24/7.

* [yibiao-simple v2.25.19](https://github.com/FB208/OpenBidKit_Yibiao) – Out-of-the-box AI bid writing and checking tool with knowledge base and duplicate detection.

* [yibiao-simple v2.25.18](https://github.com/FB208/OpenBidKit_Yibiao) – Out-of-the-box AI bid writing and checking tool with knowledge base and duplicate detection.

* [yibiao-simple v2.25.17](https://github.com/FB208/OpenBidKit_Yibiao) – Out-of-the-box AI bid writing and checking tool with knowledge base and duplicate detection.

* [yibiao-simple v2.25.16](https://github.com/FB208/OpenBidKit_Yibiao) – Out-of-the-box AI bid writing and checking tool with knowledge base and duplicate detection.

* [Ax 24.0.6](https://github.com/ax-llm/ax) – End-to-end streaming framework for building multi-modal agents with typed signatures.

* [Reasonix studio-v2.5.0](https://github.com/esengine/DeepSeek-Reasonix) – DeepSeek-native AI coding agent for your terminal, engineered around prefix-cache stability to keep token costs low across long sessions.

* [MDFlux v0.3.0](https://github.com/ibrahimqureshae/mdflux) – MDFlux is a local-first desktop tool that converts many document types and scanned PDFs into clean, AI-ready Markdown with OCR and optional cleanup.

* [Sokuji v0.38.0](https://github.com/kizuna-ai-lab/sokuji) – Desktop application providing live speech translation and audio routing using multiple AI-powered APIs.

* [CortexDB v2.74.0](https://github.com/liliang-cn/cortexdb) – Pure-Go, single-file embedded AI memory and knowledge graph library that provides hybrid vector and lexical retrieval, RDF/SPARQL graph features, and MCP tools via SQLite.

* [CortexDB v2.73.0](https://github.com/liliang-cn/cortexdb) – Pure-Go, single-file embedded AI memory and knowledge graph library that provides hybrid vector and lexical retrieval, RDF/SPARQL graph features, and MCP tools via SQLite.

* [llama\_cpp.rb v0.28.0](https://github.com/yoshoku/llama_cpp.rb) – Ruby bindings for llama.cpp, enabling easy integration of the library in Ruby applications.

* [AI SDK @ai-sdk/deepgram@3.1...](https://github.com/vercel/ai) – TypeScript toolkit for building AI-powered applications with popular frameworks.

* [Ax 24.0.5](https://github.com/ax-llm/ax) – End-to-end streaming framework for building multi-modal agents with typed signatures.

* [Kortix v0.13.4](https://github.com/kortix-ai/suna) – Autonomous company OS where Linux-sandboxed AI agents run code, manage files, and automate operations 24/7.

* [obsidian-mcp-server v3.5.0](https://github.com/cyanheads/obsidian-mcp-server) – MCP server for Obsidian vaults that reads, writes, searches, and surgically edits notes, tags, and frontmatter via the Local REST API plugin.

* [obsidian-mcp-server v3.4.0](https://github.com/cyanheads/obsidian-mcp-server) – MCP server for Obsidian vaults that reads, writes, searches, and surgically edits notes, tags, and frontmatter via the Local REST API plugin.

* [Abu v0.41.0](https://github.com/PM-Shawn/Abu-Cowork) – Privacy-first desktop AI coworking app with multi-model support, agent skills, IM integration, MCP/Playwright, scheduling, and built-in security controls.

* [freebuff-proxy v1.1.0](https://github.com/trefeon/freebuff-proxy) – High-performance OpenAI-compatible gateway and protocol bridge that manages sessions, pools tokens, and forwards chat completions with SSE streaming and TLS stealth.

* [Reasonix v1.31.3](https://github.com/esengine/DeepSeek-Reasonix) – DeepSeek-native AI coding agent for your terminal, engineered around prefix-cache stability to keep token costs low across long sessions.

* [avoid-ai-writing v3.25.1](https://github.com/conorbronsdon/avoid-ai-writing) – Audit and rewrite content to remove AI writing patterns, with detect-only or edit-in-place modes and configurable voice profiles for agent skills.

* [Kortix v0.13.2](https://github.com/kortix-ai/suna) – Autonomous company OS where Linux-sandboxed AI agents run code, manage files, and automate operations 24/7.

* [Ax 24.0.4](https://github.com/ax-llm/ax) – End-to-end streaming framework for building multi-modal agents with typed signatures.

* [Ix v0.10.0](https://github.com/ix-infrastructure/Ix) – Command-line tool that parses a codebase into a persistent queryable symbol, call, and import graph for efficient AI and human reasoning.

* [Open Multi-Agent v1.16.1](https://github.com/open-multi-agent/open-multi-agent) – TypeScript-native multi-agent orchestration that decomposes goals into parallel task DAGs and synthesizes results.

* [yzma v1.24.0](https://github.com/hybridgroup/yzma) – Go-based library for hardware-accelerated local inference with llama.cpp integration.

* [NobodyWho nobodywho-flutter-v3...](https://github.com/nobodywho-ooo/nobodywho) – Inference engine for running LLMs locally and efficiently on any device.

* [NobodyWho nobodywho-kotlin-v3....](https://github.com/nobodywho-ooo/nobodywho) – Inference engine for running LLMs locally and efficiently on any device.

* [NobodyWho nobodywho-react-nati...](https://github.com/nobodywho-ooo/nobodywho) – Inference engine for running LLMs locally and efficiently on any device.

* [NobodyWho nobodywho-swift-v3.0...](https://github.com/nobodywho-ooo/nobodywho) – Inference engine for running LLMs locally and efficiently on any device.

* [Ax 24.0.3](https://github.com/ax-llm/ax) – End-to-end streaming framework for building multi-modal agents with typed signatures.

* [Read Frog v1.46.4](https://github.com/mengxi-ream/read-frog) – AI-powered browser extension for immersive language learning with translation and article analysis.

* [Reasonix v1.31.1](https://github.com/esengine/DeepSeek-Reasonix) – DeepSeek-native AI coding agent for your terminal, engineered around prefix-cache stability to keep token costs low across long sessions.

* [Ax 24.0.2](https://github.com/ax-llm/ax) – End-to-end streaming framework for building multi-modal agents with typed signatures.

* [Mastra @mastra/core@1.61.0](https://github.com/mastra-ai/mastra) – Opinionated TypeScript framework for building AI applications and features quickly.

* [MCP Mesh v4.288.0](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [LangChain langchain-fireworks=...](https://github.com/langchain-ai/langchain) – Framework for building agents and LLM-powered applications with modular components and integrations.

* [LangChain langchain-core==1.6....](https://github.com/langchain-ai/langchain) – Framework for building agents and LLM-powered applications with modular components and integrations.

* [LangChain langchain==1.3.18](https://github.com/langchain-ai/langchain) – Framework for building agents and LLM-powered applications with modular components and integrations.

* [MCP Mesh v4.285.0](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [Wegent wework-v0.3.0](https://github.com/wecode-ai/Wegent) – Self-hostable platform for building and running AI agent teams across chat, coding, knowledge, and automation with shared capabilities and local execution via Wework.

* [MCP Mesh v4.283.0](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [HelixML 2.12.7](https://github.com/helixml/helix) – Private GenAI stack for deploying AI agents with support for RAG, API calls, vision, and efficient GPU scheduling.

* [Bifrost core/v1.7.15](https://github.com/maximhq/bifrost) – High-performance AI gateway offering multi-provider access with automatic failover, load balancing, and zero-downtime deployments.

* [Bifrost core/v1.7.14](https://github.com/maximhq/bifrost) – High-performance AI gateway offering multi-provider access with automatic failover, load balancing, and zero-downtime deployments.

* [easy-stock v0.9.2](https://github.com/jundizhou/easy-stock) – Local-first A 股行情分析与AI智能投研代理，支持日常共识与短线研判。

* [RunAnywhere v0.20.30](https://github.com/RunanywhereAI/runanywhere-sdks) – On-device mobile SDKs for running LLMs, speech-to-text, and text-to-speech locally.

* [yibiao-simple v2.25.21](https://github.com/FB208/OpenBidKit_Yibiao) – Out-of-the-box AI bid writing and checking tool with knowledge base and duplicate detection.

* [yibiao-simple v2.25.20](https://github.com/FB208/OpenBidKit_Yibiao) – Out-of-the-box AI bid writing and checking tool with knowledge base and duplicate detection.

* [overtchat v0.17.0](https://github.com/yoloyash/overtchat) – Lightweight self-hosted chat client focused on fast startup, low resource use, and BYO API keys or local models, with optional web search and mobile support.

* [OpenScience v2.0.49](https://github.com/synthetic-sciences/openscience) – Model-agnostic AI workbench that loops through literature review, hypothesis building, code and experiment execution, and research write-ups in a browser workspace.

* [OpenScience v2.0.48](https://github.com/synthetic-sciences/openscience) – Model-agnostic AI workbench that loops through literature review, hypothesis building, code and experiment execution, and research write-ups in a browser workspace.

* [OpenScience v2.0.47](https://github.com/synthetic-sciences/openscience) – Model-agnostic AI workbench that loops through literature review, hypothesis building, code and experiment execution, and research write-ups in a browser workspace.

* [Bifrost ent-v2.0.0-base](https://github.com/maximhq/bifrost) – High-performance AI gateway offering multi-provider access with automatic failover, load balancing, and zero-downtime deployments.

* [AI SDK @ai-sdk/zai@3.0.1](https://github.com/vercel/ai) – TypeScript toolkit for building AI-powered applications with popular frameworks.

* [MCP Mesh v4.276.0](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [Ix v0.10.4](https://github.com/ix-infrastructure/Ix) – Command-line tool that parses a codebase into a persistent queryable symbol, call, and import graph for efficient AI and human reasoning.

* [RunAnywhere v0.20.29](https://github.com/RunanywhereAI/runanywhere-sdks) – On-device mobile SDKs for running LLMs, speech-to-text, and text-to-speech locally.

* [OpenScience v2.0.46](https://github.com/synthetic-sciences/openscience) – Model-agnostic AI workbench that loops through literature review, hypothesis building, code and experiment execution, and research write-ups in a browser workspace.

* [MCP Mesh v4.272.0](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh v4.269.0](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [Bifrost core/v1.8.1](https://github.com/maximhq/bifrost) – High-performance AI gateway offering multi-provider access with automatic failover, load balancing, and zero-downtime deployments.

* [OpenScience v2.0.45](https://github.com/synthetic-sciences/openscience) – Model-agnostic AI workbench that loops through literature review, hypothesis building, code and experiment execution, and research write-ups in a browser workspace.

* [OpenScience v2.0.44](https://github.com/synthetic-sciences/openscience) – Model-agnostic AI workbench that loops through literature review, hypothesis building, code and experiment execution, and research write-ups in a browser workspace.

* [OpenScience v2.0.43](https://github.com/synthetic-sciences/openscience) – Model-agnostic AI workbench that loops through literature review, hypothesis building, code and experiment execution, and research write-ups in a browser workspace.

* [Gerbil v1.28.1](https://github.com/lone-cloud/gerbil) – Desktop app for running Large Language Models locally with cross-platform support and integrated image generation.

* [OpenScience v2.0.42](https://github.com/synthetic-sciences/openscience) – Model-agnostic AI workbench that loops through literature review, hypothesis building, code and experiment execution, and research write-ups in a browser workspace.

* [OpenScience v2.0.41](https://github.com/synthetic-sciences/openscience) – Model-agnostic AI workbench that loops through literature review, hypothesis building, code and experiment execution, and research write-ups in a browser workspace.

* [MCP Mesh v4.268.0](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [OpenScience v2.0.40](https://github.com/synthetic-sciences/openscience) – Model-agnostic AI workbench that loops through literature review, hypothesis building, code and experiment execution, and research write-ups in a browser workspace.

* [OpenScience v2.0.39](https://github.com/synthetic-sciences/openscience) – Model-agnostic AI workbench that loops through literature review, hypothesis building, code and experiment execution, and research write-ups in a browser workspace.

* [MCP Mesh v4.264.0](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [Token Optimizer MCP v5.7.1](https://github.com/ooples/token-optimizer-mcp) – Model Context Protocol server that optimizes Claude Code context usage using caching, Brotli compression, and smart tool replacements for large text and file operations.

* [PasteGuard v0.9.3](https://github.com/sgasser/pasteguard) – OpenAI-compatible privacy proxy that masks personal data and secrets before they reach external LLMs.

* [OpenScience v2.0.38](https://github.com/synthetic-sciences/openscience) – Model-agnostic AI workbench that loops through literature review, hypothesis building, code and experiment execution, and research write-ups in a browser workspace.

* [easy-stock v0.9.1](https://github.com/jundizhou/easy-stock) – Local-first A 股行情分析与AI智能投研代理，支持日常共识与短线研判。

* [OpenScience v2.0.37](https://github.com/synthetic-sciences/openscience) – Model-agnostic AI workbench that loops through literature review, hypothesis building, code and experiment execution, and research write-ups in a browser workspace.

* [OpenScience v2.0.36](https://github.com/synthetic-sciences/openscience) – Model-agnostic AI workbench that loops through literature review, hypothesis building, code and experiment execution, and research write-ups in a browser workspace.

* [RunAnywhere v0.20.28](https://github.com/RunanywhereAI/runanywhere-sdks) – On-device mobile SDKs for running LLMs, speech-to-text, and text-to-speech locally.

* [OpenScience v2.0.35](https://github.com/synthetic-sciences/openscience) – Model-agnostic AI workbench that loops through literature review, hypothesis building, code and experiment execution, and research write-ups in a browser workspace.

* [AionUi v2.1.61](https://github.com/iOfficeAI/AionUi) – Modern GUI for multi-model AI chat with integrated file management and Excel processing.

* [LangChain langchain==1.3.17](https://github.com/langchain-ai/langchain) – Framework for building agents and LLM-powered applications with modular components and integrations.

* [Reasonix desktop-v1.31.4](https://github.com/esengine/DeepSeek-Reasonix) – DeepSeek-native AI coding agent for your terminal, engineered around prefix-cache stability to keep token costs low across long sessions.

* [MCP Mesh v4.263.0](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [OpenScience v2.0.34](https://github.com/synthetic-sciences/openscience) – Model-agnostic AI workbench that loops through literature review, hypothesis building, code and experiment execution, and research write-ups in a browser workspace.

* [OpenScience v2.0.32](https://github.com/synthetic-sciences/openscience) – Model-agnostic AI workbench that loops through literature review, hypothesis building, code and experiment execution, and research write-ups in a browser workspace.

* [Ix v0.10.3](https://github.com/ix-infrastructure/Ix) – Command-line tool that parses a codebase into a persistent queryable symbol, call, and import graph for efficient AI and human reasoning.

* [HelixML 2.12.6](https://github.com/helixml/helix) – Private GenAI stack for deploying AI agents with support for RAG, API calls, vision, and efficient GPU scheduling.

* [HelixML 2.12.5](https://github.com/helixml/helix) – Private GenAI stack for deploying AI agents with support for RAG, API calls, vision, and efficient GPU scheduling.

* [RunAnywhere v0.20.27](https://github.com/RunanywhereAI/runanywhere-sdks) – On-device mobile SDKs for running LLMs, speech-to-text, and text-to-speech locally.

* [FinanceMCP (Synapse) - MCP v4.10.2](https://github.com/guangxiangdebizi/FinanceMCP) – MCP integrating Tushare and Binance APIs to provide real-time multi-asset financial data and news for language models.

* [Hermes Studio v0.6.47](https://github.com/EKKOLearnAI/hermes-studio) – Hermes Studio is a desktop app, local runtime, and web console for managing Hermes Agent chat, models, profiles, automation jobs, and analytics while keeping everything local.

* [MemOS memos-local-plugin-v...](https://github.com/MemTensor/MemOS) – Memory operating system for LLMs and AI agents providing unified store/retrieve/manage, multi-modal long-term memory and skill reuse.

* [Ix v0.10.2](https://github.com/ix-infrastructure/Ix) – Command-line tool that parses a codebase into a persistent queryable symbol, call, and import graph for efficient AI and human reasoning.

* [or v0.6.16](https://github.com/ktsoator/or) – Modular Go toolkit with provider-neutral language model access and stateful agent tool loops with typed streaming events.

* [Ix v0.10.1](https://github.com/ix-infrastructure/Ix) – Command-line tool that parses a codebase into a persistent queryable symbol, call, and import graph for efficient AI and human reasoning.

* [FinanceMCP (Synapse) - MCP v4.10.1](https://github.com/guangxiangdebizi/FinanceMCP) – MCP integrating Tushare and Binance APIs to provide real-time multi-asset financial data and news for language models.

* [Libre WebUI v0.28.0](https://github.com/libre-webui/libre-webui) – Privacy-first self-hosted chat interface connecting to local and cloud AI providers with a plugin system and no telemetry or tracking.

* [Super-Agent-Party v0.4.3](https://github.com/heshengtao/super-agent-party) – 3D AI desktop companion platform with modular LLM enhancements, multi-terminal deployment, and cross-platform compatibility.

* [CortexDB v2.74.1](https://github.com/liliang-cn/cortexdb) – Pure-Go, single-file embedded AI memory and knowledge graph library that provides hybrid vector and lexical retrieval, RDF/SPARQL graph features, and MCP tools via SQLite.

* [Hermes Studio v0.6.46](https://github.com/EKKOLearnAI/hermes-studio) – Hermes Studio is a desktop app, local runtime, and web console for managing Hermes Agent chat, models, profiles, automation jobs, and analytics while keeping everything local.

* [RunAnywhere v0.20.25](https://github.com/RunanywhereAI/runanywhere-sdks) – On-device mobile SDKs for running LLMs, speech-to-text, and text-to-speech locally.

* [liter-llm v1.18.1](https://github.com/xberg-io/liter-llm) – A lighter, faster, safer universal LLM API client built with a Rust core and many native language bindings, with a drop-in OpenAI-compatible proxy.

* [Libre WebUI v0.27.0](https://github.com/libre-webui/libre-webui) – Privacy-first self-hosted chat interface connecting to local and cloud AI providers with a plugin system and no telemetry or tracking.

* [overtchat v0.16.0](https://github.com/yoloyash/overtchat) – Lightweight self-hosted chat client focused on fast startup, low resource use, and BYO API keys or local models, with optional web search and mobile support.

* [SigMap v8.28.1](https://github.com/manojmallick/sigmap) – Finds relevant files in a codebase and supplies compact function and class signatures to AI models to reduce tokens and improve answers.

* [Hermes Studio v0.6.45](https://github.com/EKKOLearnAI/hermes-studio) – Hermes Studio is a desktop app, local runtime, and web console for managing Hermes Agent chat, models, profiles, automation jobs, and analytics while keeping everything local.

* [Reasonix desktop-v1.31.3](https://github.com/esengine/DeepSeek-Reasonix) – DeepSeek-native AI coding agent for your terminal, engineered around prefix-cache stability to keep token costs low across long sessions.

* [llm.rb v15.0.3](https://github.com/r-uby-dev/llm) – Advanced Ruby AI runtime for building capable applications with multiple LLM providers, streaming, tool calls, and RAG support.

* [OpenScience v2.0.31](https://github.com/synthetic-sciences/openscience) – Model-agnostic AI workbench that loops through literature review, hypothesis building, code and experiment execution, and research write-ups in a browser workspace.

* [MCP Mesh v4.256.0](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [Reasonix desktop-v1.31.2](https://github.com/esengine/DeepSeek-Reasonix) – DeepSeek-native AI coding agent for your terminal, engineered around prefix-cache stability to keep token costs low across long sessions.

* [LangChain langchain-perplexity...](https://github.com/langchain-ai/langchain) – Framework for building agents and LLM-powered applications with modular components and integrations.

* [Sokuji v0.37.4](https://github.com/kizuna-ai-lab/sokuji) – Desktop application providing live speech translation and audio routing using multiple AI-powered APIs.

* [AionUi v2.1.60](https://github.com/iOfficeAI/AionUi) – Modern GUI for multi-model AI chat with integrated file management and Excel processing.

* [obsidian-mcp-server v3.3.1](https://github.com/cyanheads/obsidian-mcp-server) – MCP server for Obsidian vaults that reads, writes, searches, and surgically edits notes, tags, and frontmatter via the Local REST API plugin.

* [Sokuji v0.37.3](https://github.com/kizuna-ai-lab/sokuji) – Desktop application providing live speech translation and audio routing using multiple AI-powered APIs.

* [Pinvou Agent v0.8.6](https://github.com/Pinvou/pinvou-agent) – Desktop AI agent workspace that connects models with tools and personal knowledge to produce and manage real deliverable artifacts.

* [or v0.6.15](https://github.com/ktsoator/or) – Modular Go toolkit with provider-neutral language model access and stateful agent tool loops with typed streaming events.

* [Reasonix desktop-v1.31.1](https://github.com/esengine/DeepSeek-Reasonix) – DeepSeek-native AI coding agent for your terminal, engineered around prefix-cache stability to keep token costs low across long sessions.

* [OpenScience v2.0.30](https://github.com/synthetic-sciences/openscience) – Model-agnostic AI workbench that loops through literature review, hypothesis building, code and experiment execution, and research write-ups in a browser workspace.

* [Whisplay-AI-Chatbot v2.1.2](https://github.com/PiSugar/whisplay-ai-chatbot) – Pocket-sized AI chatbot device built for Raspberry Pi Zero 2w with push-to-talk voice interaction, wake-word, and image generation.

* [MCP Mesh native-v4.287.0](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [AI SDK @ai-sdk/xai@2.0.91](https://github.com/vercel/ai) – TypeScript toolkit for building AI-powered applications with popular frameworks.

* [MCP Mesh v4.286.3](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [AI SDK @ai-sdk/harness-fx@1...](https://github.com/vercel/ai) – TypeScript toolkit for building AI-powered applications with popular frameworks.

* [MCP Mesh v4.286.1](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [Reasonix studio-v2.10.0-rc.2](https://github.com/esengine/DeepSeek-Reasonix) – DeepSeek-native AI coding agent for your terminal, engineered around prefix-cache stability to keep token costs low across long sessions.

* [VoltAgent @voltagent/voltagent...](https://github.com/VoltAgent/voltagent) – TypeScript framework for building and orchestrating AI agents with modular components and standardized patterns.

* [AI SDK @ai-sdk/xai@4.0.48](https://github.com/vercel/ai) – TypeScript toolkit for building AI-powered applications with popular frameworks.

* [Blade Code v0.10.101](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [MCP Mesh v4.281.1](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [OpenBiliClaw extension-v0.3.213](https://github.com/whiteguo233/OpenBiliClaw) – Local, private, self-improving content discovery agent that learns from interactions to find videos and posts across Bilibili, Xiaohongshu, Douyin, YouTube, and more.

* [Bifrost core/v1.8.4](https://github.com/maximhq/bifrost) – High-performance AI gateway offering multi-provider access with automatic failover, load balancing, and zero-downtime deployments.

* [scribe v0.5.1](https://github.com/oliver-kriska/scribe) – Single-binary CLI that continuously extracts and indexes git, coding-agent sessions, and iMessage bookmarks into an LLM-written wiki for semantic search.

* [Context7 MCP ctx7@0.5.9](https://github.com/upstash/context7) – Fetches up-to-date documentation and code examples for prompts in LLMs.

* [Wegent wework-v0.2.7](https://github.com/wecode-ai/Wegent) – Self-hostable platform for building and running AI agent teams across chat, coding, knowledge, and automation with shared capabilities and local execution via Wework.

* [Blade Code v0.10.100](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [RepoWiki v0.3.3](https://github.com/he-yufeng/RepoWiki) – RepoWiki generates structured wiki documentation for local or GitHub codebases from a CLI or web interface, exporting Markdown, JSON, or self-contained HTML with terminal Q&A.

* [go-llama v0.2.3](https://github.com/goccy/go-llama) – Pure Go inference engine for GGUF models, built from llama.cpp compiled to WebAssembly and translated to Go without wasm runtime.

* [MCP Mesh native-v4.280.0](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh native-v4.279.0](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [AgentField v0.1.135](https://github.com/Agent-Field/agentfield) – Control-plane infrastructure that deploys, scales, and secures autonomous AI agents as observable, identity-aware backend services.

* [AI SDK @ai-sdk/workflow-har...](https://github.com/vercel/ai) – TypeScript toolkit for building AI-powered applications with popular frameworks.

* [CopilotKit python-sdk/v0.1.96](https://github.com/CopilotKit/CopilotKit) – Tool for building integrated AI assistants and agents that operate within user applications.

* [MCP Mesh native-v4.278.0](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [Bifrost helm-chart-v2.1.37](https://github.com/maximhq/bifrost) – High-performance AI gateway offering multi-provider access with automatic failover, load balancing, and zero-downtime deployments.

* [MCP Mesh v4.277.2](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh native-v4.276.0](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh v4.274.3](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [AI SDK @ai-sdk/xai@3.0.127](https://github.com/vercel/ai) – TypeScript toolkit for building AI-powered applications with popular frameworks.

* [MCP Mesh v4.274.2](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh v4.272.1](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh native-v4.270.0](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh v4.269.5](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [Headroom v0.8.9](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [MCP Mesh native-v4.269.0](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [OpenBiliClaw extension-v0.3.212](https://github.com/whiteguo233/OpenBiliClaw) – Local, private, self-improving content discovery agent that learns from interactions to find videos and posts across Bilibili, Xiaohongshu, Douyin, YouTube, and more.

* [go-llama v0.2.2](https://github.com/goccy/go-llama) – Pure Go inference engine for GGUF models, built from llama.cpp compiled to WebAssembly and translated to Go without wasm runtime.

* [ElevenLabs Monorepo for NPM Package @elevenlabs/react@1....](https://github.com/elevenlabs/packages) – Monorepo managing multiple npm packages under the @elevenlabs scope.

* [QVAC sdk-v0.18.2](https://github.com/tetherto/qvac) – Local-first, cross-platform SDK for building peer-to-peer AI apps with local model inference, speech, translation, and RAG.

* [Noobot v4.2.5](https://github.com/xiayu1987/noobot) – Self-hosted AI agent workspace providing isolated sessions, tool calling, multi-model routing, MCP connectors, and multi-agent workflows via web and desktop clients.

* [react-native-litert-lm v0.6.1](https://github.com/hung-yueh/react-native-litert-lm) – React Native library for high-performance on-device LLM inference with LiteRT-LM and Nitro Modules, featuring crash-free memory handling and structured outputs.

* [MCP Mesh native-v4.267.0](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [overtchat v0.16.8](https://github.com/yoloyash/overtchat) – Lightweight self-hosted chat client focused on fast startup, low resource use, and BYO API keys or local models, with optional web search and mobile support.

* [overtchat v0.16.7](https://github.com/yoloyash/overtchat) – Lightweight self-hosted chat client focused on fast startup, low resource use, and BYO API keys or local models, with optional web search and mobile support.

* [MCP Mesh v4.266.3](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh native-v4.264.0](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [ElevenLabs Monorepo for NPM Package @elevenlabs/types@0....](https://github.com/elevenlabs/packages) – Monorepo managing multiple npm packages under the @elevenlabs scope.

* [go-llama v0.2.1](https://github.com/goccy/go-llama) – Pure Go inference engine for GGUF models, built from llama.cpp compiled to WebAssembly and translated to Go without wasm runtime.

* [overtchat v0.16.6](https://github.com/yoloyash/overtchat) – Lightweight self-hosted chat client focused on fast startup, low resource use, and BYO API keys or local models, with optional web search and mobile support.

* [WhatIfIBought v2.0.4](https://github.com/mamawai/wtfibought) – Live arena where LLM trading agents trade real market data with virtual money while exposing every thought, tool call, and post-trade review.

* [AI SDK @ai-sdk/xai@4.0.44](https://github.com/vercel/ai) – TypeScript toolkit for building AI-powered applications with popular frameworks.

* [AI SDK @ai-sdk/xai@3.0.126](https://github.com/vercel/ai) – TypeScript toolkit for building AI-powered applications with popular frameworks.

* [overtchat v0.16.5](https://github.com/yoloyash/overtchat) – Lightweight self-hosted chat client focused on fast startup, low resource use, and BYO API keys or local models, with optional web search and mobile support.

* [overtchat v0.16.4](https://github.com/yoloyash/overtchat) – Lightweight self-hosted chat client focused on fast startup, low resource use, and BYO API keys or local models, with optional web search and mobile support.

* [MCP Mesh native-v4.262.0](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [AI SDK @ai-sdk/workflow-har...](https://github.com/vercel/ai) – TypeScript toolkit for building AI-powered applications with popular frameworks.

* [MCP Mesh v4.260.10](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh v4.260.7](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [Wegent wework-v0.2.6](https://github.com/wecode-ai/Wegent) – Self-hostable platform for building and running AI agent teams across chat, coding, knowledge, and automation with shared capabilities and local execution via Wework.

* [MCP Mesh v4.260.5](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [Headroom v0.8.8](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [San v1.22.5](https://github.com/genai-io/san) – Terminal-native unified runtime for specialized AI agents built on pluggable LLMs, search backends, personas, and skills.

* [QVAC sdk-v0.18.1](https://github.com/tetherto/qvac) – Local-first, cross-platform SDK for building peer-to-peer AI apps with local model inference, speech, translation, and RAG.

* [overtchat v0.16.3](https://github.com/yoloyash/overtchat) – Lightweight self-hosted chat client focused on fast startup, low resource use, and BYO API keys or local models, with optional web search and mobile support.

* [AgentField v0.1.133](https://github.com/Agent-Field/agentfield) – Control-plane infrastructure that deploys, scales, and secures autonomous AI agents as observable, identity-aware backend services.

* [Headroom v0.8.7](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [Wegent wework-v0.2.5](https://github.com/wecode-ai/Wegent) – Self-hostable platform for building and running AI agent teams across chat, coding, knowledge, and automation with shared capabilities and local execution via Wework.

* [Noobot v4.2.4](https://github.com/xiayu1987/noobot) – Self-hosted AI agent workspace providing isolated sessions, tool calling, multi-model routing, MCP connectors, and multi-agent workflows via web and desktop clients.

* [freebuff-proxy v1.1.5](https://github.com/trefeon/freebuff-proxy) – High-performance OpenAI-compatible gateway and protocol bridge that manages sessions, pools tokens, and forwards chat completions with SSE streaming and TLS stealth.

* [Ferro Labs AI Gateway v1.4.5](https://github.com/ferro-labs/ai-gateway) – High-performance Go-based AI gateway routing OpenAI-compatible LLM requests across 30+ providers with caching, guardrails, and cost controls.

* [Wegent readme-assets](https://github.com/wecode-ai/Wegent) – Self-hostable platform for building and running AI agent teams across chat, coding, knowledge, and automation with shared capabilities and local execution via Wework.

* [Wegent wework-v0.2.4](https://github.com/wecode-ai/Wegent) – Self-hostable platform for building and running AI agent teams across chat, coding, knowledge, and automation with shared capabilities and local execution via Wework.

* [freebuff-proxy v1.1.4](https://github.com/trefeon/freebuff-proxy) – High-performance OpenAI-compatible gateway and protocol bridge that manages sessions, pools tokens, and forwards chat completions with SSE streaming and TLS stealth.

* [GoAI v0.9.7](https://github.com/zendev-sh/goai) – Go SDK providing a unified API for 25+ AI providers with streaming, structured output, and MCP support.

* [freebuff-proxy v1.1.3](https://github.com/trefeon/freebuff-proxy) – High-performance OpenAI-compatible gateway and protocol bridge that manages sessions, pools tokens, and forwards chat completions with SSE streaming and TLS stealth.

* [OpenBiliClaw extension-v0.3.210](https://github.com/whiteguo233/OpenBiliClaw) – Local, private, self-improving content discovery agent that learns from interactions to find videos and posts across Bilibili, Xiaohongshu, Douyin, YouTube, and more.

* [freebuff-proxy v1.1.2](https://github.com/trefeon/freebuff-proxy) – High-performance OpenAI-compatible gateway and protocol bridge that manages sessions, pools tokens, and forwards chat completions with SSE streaming and TLS stealth.

* [Wegent wework-v0.2.3](https://github.com/wecode-ai/Wegent) – Self-hostable platform for building and running AI agent teams across chat, coding, knowledge, and automation with shared capabilities and local execution via Wework.

* [Headroom v0.8.6](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [AI SDK @ai-sdk/xai@4.0.43](https://github.com/vercel/ai) – TypeScript toolkit for building AI-powered applications with popular frameworks.

* [OpenBiliClaw extension-v0.3.209](https://github.com/whiteguo233/OpenBiliClaw) – Local, private, self-improving content discovery agent that learns from interactions to find videos and posts across Bilibili, Xiaohongshu, Douyin, YouTube, and more.

* [Wegent wework-v0.2.2](https://github.com/wecode-ai/Wegent) – Self-hostable platform for building and running AI agent teams across chat, coding, knowledge, and automation with shared capabilities and local execution via Wework.

* [Headroom v0.8.5](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [AI SDK @ai-sdk/workflow-har...](https://github.com/vercel/ai) – TypeScript toolkit for building AI-powered applications with popular frameworks.

* [MCP Mesh native-v4.260.0](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh native-v4.258.0](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh native-v4.257.0](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [Lattice v1.14.8](https://github.com/Protocol-Lattice/go-agent) – Go agent framework with graph-aware memory, UTCP-native tools, and multi-agent orchestration.

* [MCP Mesh v4.255.4](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [dsh-commandcode-provider v0.6.2](https://github.com/Mars-Sea/dsh-commandcode-provider) – Unofficial DeepSeek Harness provider plugin that adds a Command Code provider route with live model catalog, plan/deal annotations, and reasoning-effort plus vision support.

* [MCP Mesh native-v4.254.0](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [dsh-commandcode-provider v0.6.1](https://github.com/Mars-Sea/dsh-commandcode-provider) – Unofficial DeepSeek Harness provider plugin that adds a Command Code provider route with live model catalog, plan/deal annotations, and reasoning-effort plus vision support.

* [Context7 MCP @upstash/context7-mc...](https://github.com/upstash/context7) – Fetches up-to-date documentation and code examples for prompts in LLMs.

* [AI SDK @ai-sdk/workflow-har...](https://github.com/vercel/ai) – TypeScript toolkit for building AI-powered applications with popular frameworks.

* [AgentField v0.1.137-rc.2](https://github.com/Agent-Field/agentfield) – Control-plane infrastructure that deploys, scales, and secures autonomous AI agents as observable, identity-aware backend services.

* [Coddy 0.9.82](https://github.com/coddy-project/coddy-agent) – Coddy is a distroless-friendly Go-based general-purpose agent harness with a ReAct loop, ACP/HTTP/Telegram interfaces, MCP and skills integration, and long-term memory.

* [Coddy 0.9.80](https://github.com/coddy-project/coddy-agent) – Coddy is a distroless-friendly Go-based general-purpose agent harness with a ReAct loop, ACP/HTTP/Telegram interfaces, MCP and skills integration, and long-term memory.

* [Blade Code v0.10.99](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [Blade Code v0.10.98](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [Blade Code v0.10.97](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [Blade Code v0.10.96](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [MCP Mesh native-v4.275.1](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [Blade Code v0.10.95](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [AgentField v0.1.135-rc.2](https://github.com/Agent-Field/agentfield) – Control-plane infrastructure that deploys, scales, and secures autonomous AI agents as observable, identity-aware backend services.

* [MCP Mesh native-v4.269.2](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [Blade Code v0.10.93](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [Blade Code v0.10.91](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [Blade Code v0.10.90](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [Blade Code v0.10.89](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [MCP Mesh native-v4.266.1](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [Blade Code v0.10.88](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [AgentField v0.1.134-rc.6](https://github.com/Agent-Field/agentfield) – Control-plane infrastructure that deploys, scales, and secures autonomous AI agents as observable, identity-aware backend services.

* [Blade Code v0.10.86](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [MCP Mesh native-v4.262.1](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [AgentField v0.1.134-rc.4](https://github.com/Agent-Field/agentfield) – Control-plane infrastructure that deploys, scales, and secures autonomous AI agents as observable, identity-aware backend services.

* [Blade Code v0.10.85](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [MCP Mesh native-v4.261.1](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [Blade Code v0.10.84](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [MCP Mesh native-v4.260.11](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [Blade Code v0.10.83](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [Coddy 0.9.79](https://github.com/coddy-project/coddy-agent) – Coddy is a distroless-friendly Go-based general-purpose agent harness with a ReAct loop, ACP/HTTP/Telegram interfaces, MCP and skills integration, and long-term memory.

* [Blade Code v0.10.82](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [RunAnywhere qairt-runtime-v2.47....](https://github.com/RunanywhereAI/runanywhere-sdks) – On-device mobile SDKs for running LLMs, speech-to-text, and text-to-speech locally.

* [overtchat cli-v0.1.10](https://github.com/yoloyash/overtchat) – Lightweight self-hosted chat client focused on fast startup, low resource use, and BYO API keys or local models, with optional web search and mobile support.

* [Blade Code v0.10.81](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [Blade Code v0.10.80](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [Blade Code v0.10.79](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [AgentField v0.1.133-rc.4](https://github.com/Agent-Field/agentfield) – Control-plane infrastructure that deploys, scales, and secures autonomous AI agents as observable, identity-aware backend services.

* [Blade Code v0.10.78](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [Coddy 0.9.78](https://github.com/coddy-project/coddy-agent) – Coddy is a distroless-friendly Go-based general-purpose agent harness with a ReAct loop, ACP/HTTP/Telegram interfaces, MCP and skills integration, and long-term memory.

* [llama.rn v0.13.0-rc.1](https://github.com/mybigday/llama.rn) – React Native binding for running LLaMA model inference with multimodal support including vision and audio.

* [Blade Code v0.10.77](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [overtchat cli-v0.1.9](https://github.com/yoloyash/overtchat) – Lightweight self-hosted chat client focused on fast startup, low resource use, and BYO API keys or local models, with optional web search and mobile support.

* [overtchat cli-v0.1.8](https://github.com/yoloyash/overtchat) – Lightweight self-hosted chat client focused on fast startup, low resource use, and BYO API keys or local models, with optional web search and mobile support.

* [Blade Code v0.10.76](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [Blade Code v0.10.75](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [Blade Code v0.10.74](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [MCP Mesh native-v4.260.2](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [Blade Code v0.10.73](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [AgentField v0.1.133-rc.2](https://github.com/Agent-Field/agentfield) – Control-plane infrastructure that deploys, scales, and secures autonomous AI agents as observable, identity-aware backend services.

* [Blade Code v0.10.72](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [overtchat mobile-v1.3.1](https://github.com/yoloyash/overtchat) – Lightweight self-hosted chat client focused on fast startup, low resource use, and BYO API keys or local models, with optional web search and mobile support.

* [Blade Code v0.10.71](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [Blade Code v0.10.69](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [MCP Mesh native-v4.260.1](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh native-v4.259.1](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [AI SDK @ai-sdk/vue@3.0.263](https://github.com/vercel/ai) – TypeScript toolkit for building AI-powered applications with popular frameworks.

* [AI SDK @ai-sdk/vue@2.0.243](https://github.com/vercel/ai) – TypeScript toolkit for building AI-powered applications with popular frameworks.

* [MCP Mesh native-v4.255.2](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [Off Grid AI v0.0.43](https://github.com/off-grid-ai/OGAD) – Local-first AI runtime with a studio and an OpenAI-compatible gateway, running open multimodal models entirely on-device with an optional always-on assistant layer.

* [MCP Mesh native-v4.253.2](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh native-v4.253.1](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh native-v4.252.10](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [AgentSphere v1.0.71-alpha](https://github.com/nullpointexception-i/agent-sphere) – LLM-driven AI agent orchestration platform that coordinates a perception–planning–execution–feedback loop with tool, MCP, CLI, and browser capabilities.

* [MCP Mesh native-v4.286.9](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh native-v4.286.8](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [Headroom v0.9.3-rc.1](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [MCP Mesh native-v4.281.6](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh native-v4.281.3](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [Headroom v0.9.2-rc.6](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [Headroom v0.9.2-rc.3](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [Headroom v0.9.1-rc.5](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [Headroom v0.9.1-rc.4](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [MCP Mesh native-v4.280.3](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [Headroom v0.9.1-rc.1](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [Wegent wework-v0.2.7-beta.4](https://github.com/wecode-ai/Wegent) – Self-hostable platform for building and running AI agent teams across chat, coding, knowledge, and automation with shared capabilities and local execution via Wework.

* [MCP Mesh native-v4.278.6](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh native-v4.278.4](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh native-v4.278.3](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [Wegent wework-v0.2.7-beta.3](https://github.com/wecode-ai/Wegent) – Self-hostable platform for building and running AI agent teams across chat, coding, knowledge, and automation with shared capabilities and local execution via Wework.

* [Headroom v0.9.0-rc.2](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [MCP Mesh native-v4.269.5](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [Wegent wework-v0.2.7-beta.2](https://github.com/wecode-ai/Wegent) – Self-hostable platform for building and running AI agent teams across chat, coding, knowledge, and automation with shared capabilities and local execution via Wework.

* [MCP Mesh native-v4.269.3](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [Headroom v0.8.9-rc.6](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [Headroom v0.8.9-rc.5](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [Headroom v0.8.9-rc.4](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [pgEdge Postgres MCP Server and Natural Language Agent v1.1.0-beta3](https://github.com/pgEdge/pgedge-postgres-mcp) – PostgreSQL MCP server enabling SQL queries from MCP-compatible clients, with a natural-language agent plus CLI and web UIs.

* [Headroom v0.8.9-rc.3](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [MCP Mesh native-v4.268.3](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh native-v4.266.3](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh native-v4.263.6](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh native-v4.263.5](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh native-v4.263.4](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [Headroom v0.8.9-rc.2](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [MCP Mesh native-v4.263.3](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh native-v4.262.7](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh native-v4.262.6](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh native-v4.262.5](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh native-v4.262.4](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh native-v4.262.3](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh native-v4.260.5](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [MCP Mesh native-v4.260.4](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [Headroom v0.8.8-rc.5](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [Headroom v0.8.8-rc.3](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [Headroom v0.8.8-rc.2](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [Headroom v0.8.8-rc.1](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [Headroom v0.8.7-rc.10](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [Headroom v0.8.7-rc.8](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [Headroom v0.8.7-rc.5](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [senpi v2026.8.23](https://github.com/code-yeongyu/senpi) – Opinionated TypeScript monorepo fork of pi-mono that provides a curated coding-agent runtime with builtin extensions and core tweaks.

* [Headroom v0.8.7-rc.4](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [Headroom v0.8.7-rc.3](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [senpi v2026.8.22-2](https://github.com/code-yeongyu/senpi) – Opinionated TypeScript monorepo fork of pi-mono that provides a curated coding-agent runtime with builtin extensions and core tweaks.

* [Headroom v0.8.7-rc.2](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [Headroom v0.8.7-rc.1](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [Headroom v0.8.6-rc.1](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [Headroom v0.8.5-rc.1](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [warpdrv v0.6.17-beta](https://github.com/mikjee/warpdrv) – Desktop toolkit for managing llama-server instances and chatting with local LLMs, featuring a rich UI, voice, MCP tools, and workflow helpers like RAG and agents.

* [Wegent wework-v0.2.2-beta.4](https://github.com/wecode-ai/Wegent) – Self-hostable platform for building and running AI agent teams across chat, coding, knowledge, and automation with shared capabilities and local execution via Wework.

* [MCP Mesh native-v4.255.3](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [opencodex v2.30.0-preview.2026...](https://github.com/lidge-jun/opencodex) – Lightweight local proxy that translates Codex Responses API into multiple LLM providers with full support for streaming, tools, reasoning tokens, and images.

* [AgentSphere v1.0.70-alpha](https://github.com/nullpointexception-i/agent-sphere) – LLM-driven AI agent orchestration platform that coordinates a perception–planning–execution–feedback loop with tool, MCP, CLI, and browser capabilities.

* [MCP Mesh native-v4.253.3](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [DIAL Chat 1.0.0-rc.6](https://github.com/epam/ai-dial-chat) – Default UI for DIAL offering conversation interface, IDP support, model side-by-side comparison, extensions and theming.

* [AgentSphere v1.0.69-alpha](https://github.com/nullpointexception-i/agent-sphere) – LLM-driven AI agent orchestration platform that coordinates a perception–planning–execution–feedback loop with tool, MCP, CLI, and browser capabilities.

* [Wegent wework-v0.2.2-beta.3](https://github.com/wecode-ai/Wegent) – Self-hostable platform for building and running AI agent teams across chat, coding, knowledge, and automation with shared capabilities and local execution via Wework.

* [freebuff-proxy v2.0.0-alpha.1](https://github.com/trefeon/freebuff-proxy) – High-performance OpenAI-compatible gateway and protocol bridge that manages sessions, pools tokens, and forwards chat completions with SSE streaming and TLS stealth.

* [Wegent wework-v0.2.2-beta.2](https://github.com/wecode-ai/Wegent) – Self-hostable platform for building and running AI agent teams across chat, coding, knowledge, and automation with shared capabilities and local execution via Wework.

* [Ix v0.10.0-rc.16](https://github.com/ix-infrastructure/Ix) – Command-line tool that parses a codebase into a persistent queryable symbol, call, and import graph for efficient AI and human reasoning.

* [Ix v0.10.0-rc.15](https://github.com/ix-infrastructure/Ix) – Command-line tool that parses a codebase into a persistent queryable symbol, call, and import graph for efficient AI and human reasoning.

* [MCP Mesh native-v4.252.6](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [Tingly Box v0.260827.0-rc2](https://github.com/tingly-dev/tingly-box) – High-performance desktop LLM proxy that unifies access to many models and providers via a single OpenAI-compatible API.

* [Tingly Box v0.260827.0-rc1](https://github.com/tingly-dev/tingly-box) – High-performance desktop LLM proxy that unifies access to many models and providers via a single OpenAI-compatible API.

* [NodeTool v0.7.1-nightly.20260...](https://github.com/nodetool-ai/nodetool) – Visual platform for building and deploying AI workflows, agents, and multimodal pipelines via drag-and-drop nodes.

* [NodeTool v0.7.1-nightly.20260...](https://github.com/nodetool-ai/nodetool) – Visual platform for building and deploying AI workflows, agents, and multimodal pipelines via drag-and-drop nodes.

* [Stately Agent @statelyai/agent@2.0...](https://github.com/statelyai/agent) – State-machine-powered LLM agent logic built on XState, where model decisions and tool effects run within explicit, inspectable control flow.

* [NodeTool v0.7.1-nightly.20260...](https://github.com/nodetool-ai/nodetool) – Visual platform for building and deploying AI workflows, agents, and multimodal pipelines via drag-and-drop nodes.