* [LocalAI v4.0.0](https://github.com/mudler/LocalAI) – Self-hosted alternative to popular AI APIs for local inferencing on consumer-grade hardware.

* [Langfuse v3.160.0](https://github.com/langfuse/langfuse) – LLM engineering platform for collaboratively developing, monitoring, evaluating, and debugging AI applications.

* [Cherry Studio v1.8.0](https://github.com/CherryHQ/cherry-studio) – Desktop client supporting multiple LLM providers, available on Windows, Mac, and Linux.

* [Ollama v0.18.0](https://github.com/ollama/ollama) – Tool for running and managing large language models.

* [CopilotKit v1.54.0](https://github.com/CopilotKit/CopilotKit) – Tool for building integrated AI assistants and agents that operate within user applications.

* [Wiseflow v5.1.0](https://github.com/TeamWiseFlow/wiseflow) – Browser automation and web interaction add-on enhancing agents' browser usage and web-search capabilities.

* [Prompt Optimizer v2.6.0](https://github.com/linshenkx/prompt-optimizer) – Tool for enhancing prompt quality to improve AI interaction results.

* [Ax 19.0.0](https://github.com/ax-llm/ax) – End-to-end streaming framework for building multi-modal agents with typed signatures.

* [Dify 1.13.2](https://github.com/langgenius/dify) – Platform for developing large language model applications with AI workflows, model management, and observability.

* [Rulesync v7.20.0](https://github.com/dyoshikawa/rulesync) – Node.js CLI that generates configuration files for AI development tools from unified rule files, with selective generation and import/export support.

* [RubyLLM 1.14.0](https://github.com/crmne/ruby_llm) – A Ruby library providing a unified API for interacting with various AI models and services.

* [Read Frog v1.30.0](https://github.com/mengxi-ream/read-frog) – AI-powered browser extension for immersive language learning with translation and article analysis.

* [mcp-ui client/v7.0.0](https://github.com/MCP-UI-Org/mcp-ui) – SDK providing interactive web components and UI resources for the Model Context Protocol.

* [OpenClaw Agent Dashboard v3.0.0](https://github.com/tugcantopaloglu/openclaw-dashboard) – Secure real-time monitoring dashboard for AI agents offering session management, API usage and cost tracking, memory browsing, system health, and TOTP MFA.

* [Repomix v1.12.0](https://github.com/yamadashy/repomix) – Tool for packing entire repositories into AI-friendly formats.

* [PandaWiki v3.73.0](https://github.com/chaitin/PandaWiki) – AI-driven knowledge base system for quickly building intelligent product documentation, technical documents, FAQs, and blog systems.

* [zeroshot CLI v5.5.0](https://github.com/covibes/zeroshot) – Coordinates isolated agents to implement, test, and deliver verified production-ready pull requests from GitHub issues.

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

* [MCP Mesh v2.179.0](https://github.com/decocms/studio) – Control plane routing MCP client traffic through one governed endpoint with auth, RBAC, policy enforcement, and observability.

* [Oksskolten v0.2.0](https://github.com/babarot/oksskolten) – AI-native RSS reader that fetches full articles, converts to clean Markdown, and enables full-text search, summarization, and offline reading.

* [AIKit v0.21.0](https://github.com/kaito-project/aikit) – Platform to host, deploy, build, and fine-tune large language models with OpenAI API compatibility.

* [llm.rb v4.8.0](https://github.com/llmrb/llm.rb) – Zero-dependency Ruby toolkit for multiple LLM providers with chat, streaming, tool calling, audio, images, files, and structured outputs.

* [HelixML 2.9.0](https://github.com/helixml/helix) – Private GenAI stack for deploying AI agents with support for RAG, API calls, vision, and efficient GPU scheduling.

* [yzma v1.11.0](https://github.com/hybridgroup/yzma) – Go-based library for hardware-accelerated local inference with llama.cpp integration.

* [Vurb.ts v3.6.0](https://github.com/vinkius-labs/vurb.ts) – TypeScript framework for building MCP servers with type-safe APIs, machine-readable SKILL.md, AI-agent integration, and built-in security.

* [AI Agent Automation v0.6.0](https://github.com/vmDeshpande/ai-agent-automation) – Developer-first, local-first workflow execution engine enabling deterministic, inspectable AI-driven automation.

* [MoLing v0.5.0](https://github.com/gojue/moling) – Dependency-free local MCP server enabling OS-level file operations, command execution, and browser control for office automation.

* [MCP PostgreSQL Operations Server 3.2.0](https://github.com/call518/MCP-PostgreSQL-Ops) – Professional MCP server for PostgreSQL database operations, monitoring, and performance analysis with version-adaptive features.

* [NoteGen note-gen-v0.27.0](https://github.com/codexu/note-gen) – Cross-platform Markdown note-taking application using AI to organize fragmented knowledge into readable notes.

* [RubyLLM::Agents v3.11.0](https://github.com/adham90/ruby_llm-agents) – Rails engine providing an agent DSL, execution tracking, cost analytics, reliability controls, and a real-time dashboard for LLM-powered agents.

* [@inductiv/node-red-openai-api v6.29.0](https://github.com/allanbunch/node-red-openai-api) – Node-RED nodes exposing OpenAI-compatible APIs for event-driven AI workflows, including streaming, realtime, tools, and webhook handling.

* [Mastra @mastra/core@1.13.0](https://github.com/mastra-ai/mastra) – Opinionated TypeScript framework for building AI applications and features quickly.

* [Dingo v2.1.0](https://github.com/MigoXLab/dingo) – Data quality evaluation tool supporting built-in and custom methods for text and multimodal datasets.

* [Promptfoo 0.121.2](https://github.com/promptfoo/promptfoo) – Developer-friendly local tool for testing, evaluating, and securing large language model applications.

* [FastGPT v4.14.8.2](https://github.com/labring/FastGPT) – Knowledge-based platform leveraging LLMs for data processing, retrieval, and AI workflow orchestration.

* [Mattermost Agents Plugin v1.13.0](https://github.com/mattermost/mattermost-plugin-agents) – Integrates local and cloud LLMs into Mattermost to provide assistants, thread summarization, transcription, semantic search, and action-item extraction.

* [DecoCMS v2.153.0](https://github.com/decocms/mesh) – Context management system that centralizes MCP connections, tools, and policies to compose governed AI apps and workflows.

* [My-neuro v6.3.2](https://github.com/morettt/my-neuro) – Desktop AI companion with customizable characters, fast voice conversations, long-term memory, visual recognition, voice cloning, and LLM training.

* [RunAnywhere genie-v0.1.0](https://github.com/RunanywhereAI/runanywhere-sdks) – On-device mobile SDKs for running LLMs, speech-to-text, and text-to-speech locally.

* [gollem v0.23.0](https://github.com/m-mizutani/gollem) – Go framework for agentic AI applications with MCP-based tool support, automatic session handling, and conversational memory management.

* [Murasaki Translator v2.2.0](https://github.com/soundstarrain/Murasaki-Translator) – Inference frontend supporting Chain-of-Thought and long-context ACGN translation for light novels, subtitles, games, and comics.

* [Hydra v0.1.0](https://github.com/PrimeLocus/Hydra) – Multi-agent AI orchestrator that routes tasks across Claude, Gemini, and Codex using a shared queue, intelligent routing, and multi-round deliberation.

* [UnicomAI/wanwu v0.4.2](https://github.com/UnicomAI/wanwu) – Enterprise-grade multi-tenant platform for developing large model applications including intelligent agents, workflows, and text Q&A with model management.

* [WeKnora v0.3.3](https://github.com/Tencent/WeKnora) – LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using the RAG paradigm.

* [Cactus React Native v1.10.0](https://github.com/cactus-compute/cactus-react-native) – React Native package for running AI language models locally with support for text, vision, and tool calling.

* [RapidFire AI v0.15.0](https://github.com/RapidFireAI/rapidfireai) – Hyperparallelized, shard-based experiment framework for rapid LLM customization, RAG, context engineering, and fine-tuning with real-time control.

* [Sokuji v0.15.0](https://github.com/kizuna-ai-lab/sokuji) – Desktop application providing live speech translation and audio routing using multiple AI-powered APIs.

* [Frontman v0.10.0](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.

* [SAP Cloud SDK for AI v2.8.0](https://github.com/SAP/ai-sdk-js) – SDK for integrating SAP AI Core, SAP Generative AI Hub, and orchestration services into JavaScript/TypeScript applications.

* [AionUi v1.8.19](https://github.com/iOfficeAI/AionUi) – Modern GUI for multi-model AI chat with integrated file management and Excel processing.

* [Full-Stack AI Agent Template 0.2.0](https://github.com/vstorm-co/full-stack-ai-agent-template) – Production-ready FastAPI+Next.js template for building type-safe AI/LLM agents with streaming, auth, observability, multi-DB support, and 20+ integrations.

* [tRPC-Agent-Go v1.6.0](https://github.com/trpc-group/trpc-agent-go) – Go framework for building autonomous intelligent agents with multi-agent orchestration, persistent memory, and tool integration.

* [DIAL Chat 0.43.0](https://github.com/epam/ai-dial-chat) – Default UI for DIAL offering conversation interface, IDP support, model side-by-side comparison, extensions and theming.

* [Easy Dataset 1.7.2](https://github.com/ConardLi/easy-dataset) – Tool for creating fine-tuning datasets for Large Language Models.

* [Distill v0.4.0](https://github.com/Siddhant-K-code/distill) – Deterministically deduplicates, compresses, summarizes, and caches LLM context to reduce redundancy and token costs.

* [VoltAgent @voltagent/core@2.6....](https://github.com/VoltAgent/voltagent) – TypeScript framework for building and orchestrating AI agents with modular components and standardized patterns.

* [mcp-fusion v1.3.0](https://github.com/vinkius-labs/mcp-fusion) – Framework for building MCP servers that deliver structured agent-centric perception packages via the MVA (Model-View-Agent) architecture.

* [Context Engineering Kit v2.1.0](https://github.com/NeoLabHQ/context-engineering-kit) – Hand-crafted plugin marketplace offering token-efficient, quality-focused context engineering techniques and plugins for multiple agent platforms.

* [llama_cpp.rb v0.24.0](https://github.com/yoshoku/llama_cpp.rb) – Ruby bindings for llama.cpp, enabling easy integration of the library in Ruby applications.

* [SearXNG MCP Server v0.9.0](https://github.com/ihor-sokoliuk/mcp-searxng) – MCP server integrating a SearXNG-compatible web search API with URL content extraction, caching, pagination, and filtering.

* [AutoBE v0.30.3](https://github.com/wrtnlabs/autobe) – No-code AI agent that analyzes requirements and generates validated backend applications using TypeScript, NestJS, and Prisma.

* [M-Courtyard v0.5.0](https://github.com/Mcourtyard/m-courtyard) – Zero-code desktop assistant for local LLM fine-tuning and AI-powered data preparation on Apple Silicon with privacy-first MLX optimization.

* [Harbor v0.4.5](https://github.com/av/harbor) – Containerized toolkit to run local LLM backends, frontends, and related services with minimal configuration.

* [RESTai v5.0.6](https://github.com/apocas/restai) – AI-as-a-Service platform providing a REST API to create and serve RAG, RAGSQL, agent, inference, vision, and image-generation projects.

* [Continue v1.2.17-vscode](https://github.com/continuedev/continue) – Enables developers to create, share, and use custom AI code assistants with IDE extensions and a hub of models, rules, and tools.

* [WebLLM v0.2.82](https://github.com/mlc-ai/web-llm) – High-performance in-browser LLM inference engine using WebGPU for hardware-accelerated, serverless model inference.

* [NestJS MCP Server Module v1.9.7](https://github.com/rekog-labs/MCP-Nest) – NestJS module that exposes tools, resources, and prompts using the Model Context Protocol.

* [Warren v0.12.0](https://github.com/secmon-lab/warren) – AI-powered security alert management that reduces noise and speeds incident response.

* [clai v1.10.1](https://github.com/baalimago/clai) – Command-line context feeder for LLMs, enabling vendor-agnostic conversations, profiles, and Unix-like piping workflows.

* [llama.rn v0.11.4](https://github.com/mybigday/llama.rn) – React Native binding for running LLaMA model inference with multimodal support including vision and audio.

* [Context7 MCP ctx7@0.3.2](https://github.com/upstash/context7) – Fetches up-to-date documentation and code examples for prompts in LLMs.

* [PromptHub v0.4.2](https://github.com/legeling/PromptHub) – Local-first AI prompt manager for organizing, versioning, and reusing prompts.

* [Adaline Gateway v1.11.8](https://github.com/adaline/gateway) – Fully local, production-ready SDK that provides a unified interface for calling over 300 LLMs with batching, caching, and extensibility.

* [NativeMind v1.12.3](https://github.com/NativeMindBrowser/NativeMindExtension) – Browser extension integrating local AI models for private, offline AI assistance and productivity tools.

* [FinanceMCP (Synapse) - MCP v4.7.1](https://github.com/guangxiangdebizi/FinanceMCP) – MCP integrating Tushare and Binance APIs to provide real-time multi-asset financial data and news for language models.

* [The Web MCP v2.8.6](https://github.com/brightdata/brightdata-mcp) – MCP-based server that provides LLMs real-time, unblocked access to live web data and browser automation.

* [ClaraVerse v0.1.5-oss](https://github.com/claraverse-space/ClaraVerse) – Private AI workspace combining chat, image generation, visual workflows, and local model support with browser-local storage for confidential conversations.

* [Lattice v1.11.2](https://github.com/Protocol-Lattice/go-agent) – Go agent framework with graph-aware memory, UTCP-native tools, and multi-agent orchestration.

* [Super-Agent-Party v0.3.8](https://github.com/heshengtao/super-agent-party) – 3D AI desktop companion platform with modular LLM enhancements, multi-terminal deployment, and cross-platform compatibility.

* [PasteGuard v0.3.2](https://github.com/sgasser/pasteguard) – OpenAI-compatible privacy proxy that masks personal data and secrets before they reach external LLMs.

* [Dexto @dexto/tools-schedul...](https://github.com/truffle-ai/dexto) – Universal intelligence layer that orchestrates LLMs, tools, and data to build stateful, multimodal agentic applications.

* [Nerve v1.4.9](https://github.com/daggerhashimoto/openclaw-nerve) – Self-hosted web cockpit for OpenClaw agents with voice, live workspace editing, charts, scheduling, and token visibility.

* [AgentField v0.1.59](https://github.com/Agent-Field/agentfield) – Control-plane infrastructure that deploys, scales, and secures autonomous AI agents as observable, identity-aware backend services.

* [Teleton v0.8.5](https://github.com/TONresistor/teleton-agent) – Autonomous AI agent platform running as a Telegram user with TON blockchain native integration, multi-provider LLM support, persistent memory, 125+ built-in tools, and plugin SDK.

* [Off Grid v0.0.81](https://github.com/alichherawalla/off-grid-mobile-ai) – On-device AI suite for offline chat, image generation, vision, speech transcription, and document analysis.

* [Vellium v0.7.1](https://github.com/tg-prplx/vellium) – Desktop chat app using Electron, local Express API, and SQLite for roleplay and creative-writing LLM workflows.

* [Capsule v0.6.5](https://github.com/mavdol/capsule) – Secure, durable runtime for coordinating AI agent tasks in isolated WebAssembly sandboxes.

* [CSGHub Server v1.17.0-ce](https://github.com/OpenCSGs/csghub-server) – Backend server managing models, datasets, and large language model assets through REST API.

* [DSPy.rb v0.34.4](https://github.com/vicentereig/dspy.rb) – Ruby framework for building reliable LLM applications using composable, type-safe modules and structured programming.

* [ActionMCP action_mcp/v0.107.0](https://github.com/seuros/action_mcp) – Ruby gem providing Model Context Protocol server support for Rails applications with network-based deployments.

* [Off Grid v0.0.61](https://github.com/alichherawalla/off-grid-mobile) – On-device AI suite for mobile supporting chat, image generation, vision, voice transcription, and document analysis with offline privacy.

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

* [BeeAI Framework python_v0.1.78](https://github.com/i-am-bee/beeai-framework) – Toolkit for building intelligent, autonomous agents and multi-agent systems with reasoning and collaboration capabilities.

* [@emqx-ai/mcp-mqtt-sdk v0.2.7](https://github.com/emqx/mcp-typescript-sdk) – TypeScript SDK implementing Model Context Protocol over MQTT for browser and Node.js, with full type safety and automatic environment detection.

* [WenShape v0.3.6](https://github.com/unitagain/WenShape) – Deep context-aware, agent-based system for novel writing.

* [Bifrost helm-chart-v2.0.8](https://github.com/maximhq/bifrost) – High-performance AI gateway offering multi-provider access with automatic failover, load balancing, and zero-downtime deployments.

* [jsonrepair v0.2.16](https://github.com/kaptinlin/jsonrepair) – High-performance Go library for repairing malformed JSON and normalizing common JSON issues, including output from LLMs.

* [Qbit v0.2.43](https://github.com/qbit-ai/qbit) – Agentic terminal app providing unified AI conversations, tool integrations, project management, and Git-based workflows.

* [Agent Sessions v0.1.27](https://github.com/ozankasikci/agent-sessions) – macOS desktop app for monitoring multiple AI coding agent sessions in real time.

* [Airstore v0.1.97](https://github.com/beam-cloud/airstore) – Virtual filesystem that turns integrations into searchable folders and files for AI-assisted workflows.

* [Zypher Agent ui/v0.3.3](https://github.com/corespeed-io/zypher-agent) – Production-ready AI agents that live in your applications.

* [Nosia v0.4.0.beta11](https://github.com/dilolabs/nosia) – Platform to run AI models on personal data with easy installation and usage.

* [BrowserWing v1.0.1-beta.2](https://github.com/browserwing/browserwing) – Turns browser actions into MCP commands, enabling AI agents to control browsers efficiently and reliably.

* [pgEdge Postgres MCP Server and Natural Language Agent v1.0.0-beta3-test](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.

* [Tingly Box npx-bundle-v0.260307...](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.