* [Headroom v0.37.0](https://github.com/headroomlabs-ai/headroom) – Headroom compresses tool outputs, logs, RAG chunks, files, and conversation history before they reach an LLM to reduce tokens while preserving answers.

* [Claudish v8.0.0](https://github.com/MadAppGang/claudish) – CLI tool that proxies Claude Code requests to OpenRouter models via a local Anthropic-compatible server.

* [OpenSpec v1.11.0](https://github.com/Fission-AI/OpenSpec) – Spec-driven workflow aligning humans and AI coding assistants to agree on requirements before coding.

* [Claude-Mem v13.16.0](https://github.com/thedotmack/claude-mem) – Persistent memory compression system that preserves and summarizes context across Claude Code sessions for continuity.

* [Gemini CLI v0.57.0](https://github.com/google-gemini/gemini-cli) – Command-line AI workflow tool that connects to tools, understands code, and accelerates workflows.

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

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

* [Claude Code Skills for production-ready Golang projects v2.0.0](https://github.com/samber/cc-skills-golang) – Go-focused agent skills for coding assistants covering language, testing, security, observability, and related best practices.

* [caveman v2.2.0](https://github.com/JuliusBrussee/caveman) – Claude Code skill compressing agent output into telegraphic, technical phrasing to cut output tokens about 65% while preserving accuracy.

* [LocalAI v4.9.0](https://github.com/mudler/LocalAI) – Self-hosted alternative to popular AI APIs for local inferencing on consumer-grade hardware.

* [RAGFlow v0.27.0](https://github.com/infiniflow/ragflow) – RAG engine combining large language models with document understanding for accurate question answering and citation.

* [Ax 24.0.0](https://github.com/ax-llm/ax) – End-to-end streaming framework for building multi-modal agents with typed signatures.

* [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.

* [FanBox v2.14.0](https://github.com/alchaincyf/fanbox) – Local-first cockpit for vibe coding that lets you browse and preview files on one side while running a coding agent in an embedded terminal and seeing every change live.

* [Unify Chat Provider v8.9.0](https://github.com/smallmain/vscode-unify-chat-provider) – Integrates multiple LLM APIs into VS Code's GitHub Copilot Chat, enabling unified configuration and access to many free models.

* [OpenConstructionERP v16.1.0](https://github.com/datadrivenconstruction/OpenConstructionERP) – Construction project management platform offering BOQ, BIM/DWG/PDF takeoff, 5D cost modeling, scheduling, and tendering.

* [Squad v0.13.0](https://github.com/bradygaster/squad) – AI development team via GitHub Copilot using persistent, repo-stored agents that learn and work in parallel.

* [Folia v0.7.0](https://github.com/chthollyphile/folia-major) – Third-party NetEase Cloud Music player focused on vivid animated lyric displays.

* [asm v2.17.0](https://github.com/luongnv89/asm) – Command-line and TUI tool that installs, searches, audits, and organizes AI agent skills across many providers and scopes.

* [OpenWhispr v1.9.0](https://github.com/OpenWhispr/openwhispr) – Desktop dictation application converting speech to text with local and cloud model support and privacy-first design.

* [Mix Space Core v14.4.0](https://github.com/mx-space/core) – Next generation RESTful API service with additional features for Mix Space.

* [CloudBase AI Toolkit v2.32.0](https://github.com/TencentCloudBase/CloudBase-AI-Toolkit) – CloudBase integration layer for AI coding tools, installing MCP servers and skills to manage schemas, permissions, functions, storage, environments, and deployments via chat.

* [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.

* [Midscene.js v1.12.0](https://github.com/web-infra-dev/midscene) – AI-driven tool for operating web pages and extracting data using natural language commands.

* [Data-Analysis-Agent v1.3.0](https://github.com/Zafer-Liu/Data-Analysis-Agent) – LLM-powered SQL and visualization agent that enables chat-based analysis and business insights via a Flask backend and Plotly charts.

* [J-Space Cognition Suite V3.7 v3.7.0](https://github.com/Tiger3807861189/J-Space-Cognition-Suite-V3.7) – Model-agnostic inference-time control suite that manages a workspace for deep reasoning, long-horizon work, tool use, verification, and recovery through selectively loaded skills.

* [OpenChamber v1.20.0](https://github.com/openchamber/openchamber) – Desktop and web interface for the OpenCode AI agent.

* [Crush v0.91.0](https://github.com/charmbracelet/crush) – Terminal-based AI coding assistant supporting multiple LLMs, sessions, and extensible capabilities.

* [Qwen Code v0.22.0](https://github.com/QwenLM/qwen-code) – AI-powered command-line workflow tool optimized for code understanding, editing, and automation.

* [Envoy AI Gateway v1.1.0](https://github.com/envoyproxy/ai-gateway) – Gateway managing request traffic from application clients to multiple Generative AI services with tiered routing and access control.

* [Docker Agent v1.127.0](https://github.com/docker/docker-agent) – Build, run, and share AI agents via declarative YAML, extensible tools, and multi-agent orchestration.

* [Rowboat v0.9.0](https://github.com/rowboatlabs/rowboat) – Local-first AI coworker that builds persistent, editable Markdown knowledge from emails and meeting notes to assist everyday work.

* [AIGCPanel v2.2.0](https://github.com/modstart-lib/aigcpanel) – One-stop AI digital-human platform for video generation, speech synthesis, voice cloning and simplified local model management.

* [Spectrum v12.8.0](https://github.com/photon-hq/spectrum-ts) – Unified TypeScript messaging SDK to write agent logic once and deploy across iMessage, WhatsApp, terminal, or custom platforms.

* [GenOffice v0.8.0](https://github.com/genspark-ai/genoffice) – AI-native office suite for macOS and Windows with AI-first editing across word processing, spreadsheets, presentations, and PDF.

* [AI Gist v2.1.0](https://github.com/yarin-zhang/AI-Gist) – Privacy-first AI prompt management tool with variable substitution, Jinja templating, AI generation, version history, and cloud backup.

* [OpenClaude v0.29.0](https://github.com/Gitlawb/openclaude) – Terminal-first coding-agent CLI unifying cloud APIs and local model backends with prompts, tools, agents, provider profiles, and streaming output.

* [OSpec.ai 2.0.0](https://github.com/clawplays/ospec) – Document-driven development workflow enabling spec-driven AI coding assistants and CLI-based change management.

* [ToolHive v0.44.0](https://github.com/stacklok/toolhive) – Simplifies secure deployment and management of Model Context Protocol servers in isolated containers.

* [HyperFrames v0.8.0](https://github.com/heygen-com/hyperframes) – HTML-based video rendering framework with first-class AI agent support.

* [Memoh v0.18.0](https://github.com/memohai/Memoh) – Multi-member, containerized AI agent platform with per-bot isolated containers and structured long-term memory for chat.

* [Archon v0.9.0](https://github.com/coleam00/Archon) – Workflow engine that encodes development processes as YAML to make AI coding deterministic and repeatable.

* [llm.rb v15.0.0](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.

* [Copilot for Obsidian 4.0.1](https://github.com/logancyang/obsidian-copilot) – In-vault AI assistant for Obsidian providing chat-based vault search, BYO models, multimedia understanding, and autonomous agent tools while keeping data local.

* [SimplexityAI v5.2.0](https://github.com/inulute/simplexity-ai-app) – Electron-based desktop wrapper for Perplexity AI's web interface, adding native features like tray, global shortcuts, and session persistence.

* [Open Science v0.16.0](https://github.com/aipoch/open-science) – Model-agnostic desktop AI workbench for researchers that runs code, reads files, uses data connectors, and produces inspectable reports and activity histories.

* [LobeHub v2.2.14](https://github.com/lobehub/lobehub) – Platform for discovering, building, and collaborating with multi-agent teams and designing agents as units of work.

* [WPPConnect v2.3.0](https://github.com/wppconnect-team/wppconnect) – Library for exporting functions from WhatsApp Web to Node.js for various interactions.

* [Synkra AIOX v5.4.0](https://github.com/SynkraAI/aiox-core) – AI-powered, agent-driven self-modifying framework for automating full-stack development and domain workflows.

* [CodePilot v0.67.0](https://github.com/op7418/CodePilot) – Native desktop GUI for Claude Code enabling conversational coding, project-aware sessions, and file-tree management.

* [MCP Toolbox for Databases v1.9.0](https://github.com/googleapis/mcp-toolbox) – MCP server connecting AI agents, IDEs, and applications to enterprise databases with prebuilt and customizable tools.

* [Agenvoy v0.33.0](https://github.com/agenvoy/Agenvoy) – Go-based AI agent framework with self-improving error memory, multi-provider LLM routing, script/HTTP tool extensions, and OS-native sandboxing.

* [Strands Agents python/v1.54.0](https://github.com/strands-agents/harness-sdk) – Model-driven SDK for building and running AI agents, with customizable agent loops, multi-agent workflows, and model-agnostic providers.

* [DeskcommCRM v1.7.0](https://github.com/melgarafael/DeskcommCRM) – IA agents-based, self-hosted sales operating system that runs an open-source CRM with native WhatsApp sales, qualification, and conversation handling.

* [txtai.js v9.13.0](https://github.com/neuml/txtai.js) – JavaScript bindings for connecting to a semantic search and language model orchestration API.

* [Voice Key v0.2.0](https://github.com/BuildWithAIs/voicekey) – Converts speech to text via GLM ASR with a one-key desktop input shortcut.

* [Deep Chat 2.5.1](https://github.com/OvidijusParsiunas/deep-chat) – Customizable AI chat component for seamless website integration.

* [DOMD v0.7.0](https://github.com/do-md/domd) – WYSIWYG Markdown editor built on a 20KB, from-scratch Markdown-native engine for human editing and AI streaming.

* [Nomi v0.21.0](https://github.com/aqm857886159/Nomi) – Local-first desktop app for AI video creation that turns a script into images and video, edits on a timeline, then exports the final MP4.

* [DSPy-Go v0.88.0](https://github.com/XiaoConstantine/dspy-go) – Native Go framework providing systematic prompt engineering, composable modules, and automated reasoning for building LLM applications.

* [Sim v0.8.12](https://github.com/simstudioai/sim) – Platform to build and deploy AI agent workflows quickly.

* [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.

* [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.

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

* [MCPProxy v0.61.0](https://github.com/smart-mcp-proxy/mcpproxy-go) – Desktop proxy enabling scalable tool discovery, major token savings, and quarantine of malicious upstream servers for AI agents.

* [aislop v0.15.0](https://github.com/scanaislop/aislop) – Detects AI-originated coding slop: narrative comments, swallowed exceptions, unsafe casts, dead code across seven languages with deterministic, sub-second analysis.

* [ai-react-markdown v2.8.0](https://github.com/AIEPhoenix/ai-react-markdown) – React component library for streaming AI-generated Markdown with LaTeX math, Mermaid diagrams, syntax highlighting, CJK typography, and cross-chunk reference resolution.

* [tapes v0.38.0](https://github.com/papercomputeco/tapes) – Transparent agentic telemetry system for content-addressable LLM interactions with durable session storage, OpenTelemetry instrumentation, and deterministic replay.

* [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.

* [E2B @e2b/python-sdk@2.46...](https://github.com/e2b-dev/E2B) – Infrastructure for running AI-generated code in secure isolated sandboxes in the cloud.

* [Laminar v0.2.2](https://github.com/lmnr-ai/lmnr) – Platform for tracing, evaluating, and analyzing AI applications with support for datasets and scalable performance.

* [CozyClay v1.6.0](https://github.com/NomaDamas/CozyClay) – Browser-based 3D staging studio to block scenes, pose characters, sequence motion prompts on a timeline, and preview generated motion locally.

* [pgbot v0.5.0](https://github.com/pgrundev/pgbot) – In-database observability for PostgreSQL that connects read-only to health-check statistics, grades findings, and reports changes since previous runs.

* [Microsandbox v0.6.15](https://github.com/superradcompany/microsandbox) – Secure, local-first programmable sandboxes using hardware-isolated microVMs that boot in milliseconds for AI agents.

* [NVIDIA AI Cluster Runtime v0.20.0](https://github.com/NVIDIA/aicr) – Tooling for optimized, validated, reproducible GPU-accelerated Kubernetes clusters via version-locked recipes and deployment-ready bundles.

* [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.

* [Plate v53.3.9](https://github.com/udecode/plate) – Rich-text editor framework designed for simplicity and efficiency.

* [CyberStrikeAI v1.7.17](https://github.com/Ed1s0nZ/CyberStrikeAI) – AI-native, Go-based penetration-testing copilot combining hundreds of security tools, MCP orchestration, and an agent that runs engagements via conversation.

* [llm-docs-builder v1.0.0](https://github.com/mensfeld/llm-docs-builder) – Transforms markdown documentation to reduce token usage and optimize content for large language models and retrieval-augmented generation systems.

* [Skybridge v1.4.1](https://github.com/alpic-ai/skybridge) – Fullstack TypeScript framework for type-safe, React-powered ChatGPT apps with zero-config dev tools and HMR.

* [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.

* [WhatsApp Backup Reader v1.31.0](https://github.com/rodrigogs/whats-reader) – Privacy-first desktop and web app to browse WhatsApp exports offline with local AI voice transcription, search, bookmarks, and statistics.

* [Raven v2.4.0](https://github.com/Laxcorp-Research/project-raven) – Local desktop meeting copilot providing real-time dual-stream transcription, WebRTC AEC3 echo cancellation, and context-aware Claude or OpenAI assistance.

* [Conduit v1.17.0](https://github.com/tsouth89/toolport) – Local MCP gateway that centralizes and shares authenticated server tool catalogs across AI clients while reducing per-request token overhead via lazy tool discovery.

* [mu v1.5.0](https://github.com/micro/mu) – Collection of small, privacy-focused web apps that avoid ads, algorithms, and tracking.

* [LunaBox v1.12.0](https://github.com/Saramanda9988/LunaBox) – Lightweight, fast, feature-rich visual novel manager and game statistics tool.

* [Knowns v0.31.0](https://github.com/knowns-dev/knowns) – Local-first, self-hostable project context layer that stores structured tasks, docs, specs, and decisions and exposes them to AI assistants via CLI and MCP.

* [HomeButler v0.22.0](https://github.com/Higangssh/homebutler) – Single-binary CLI and MCP server to monitor servers, control Docker, wake machines, and manage networks from chat or terminal.

* [Composio @composio/cli@0.4.0](https://github.com/ComposioHQ/composio) – Production-ready toolset for AI agents with support for over 250 tools and multiple frameworks.

* [Kelos v0.53.0](https://github.com/kelos-dev/kelos) – Kubernetes-native framework for orchestrating autonomous AI coding agents.

* [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.

* [Vibe v3.1.2](https://github.com/thewh1teagle/vibe) – Offline, privacy-focused app for transcribing audio and video with OpenAI Whisper, multilingual support, batch processing, and multiple export formats.

* [td v0.63.0](https://github.com/marcus/td) – Minimalist CLI tracking tasks and structured handoffs to preserve state across AI coding sessions.

* [KSail v7.180.0](https://github.com/devantler-tech/ksail) – CLI providing a unified interface to create and operate Kubernetes clusters and manage cloud-native workloads.

* [Claude Code Haha v0.5.5](https://github.com/NanmiCoder/cc-haha) – Local cross-platform Claude-compatible client with TUI and desktop apps, multi-agent tooling and Telegram/Discord integrations.

* [ADK Utils Go v1.1.0](https://github.com/achetronic/adk-utils-go) – Go implementations and utilities for Google's Agent Development Kit, including LLM clients, session and memory storage, artifact persistence, and context management.

* [Dive v1.26.0](https://github.com/deepnoodle-ai/dive) – Foundational Go library for building AI agents and LLM-powered applications with multi-provider access, tool calling, and a robust agent loop.

* [PocketRisu v1.10.0](https://github.com/PocketRisu/PocketRisu) – Self-hosted AI roleplay chat platform for PC, tablet, and smartphone with multiple model providers and unified SQLite storage.

* [phi v0.16.0](https://github.com/pulseaiclub/phi) – Minimal Go terminal coding agent with sub-agents, hash-anchored file edits, and a permission gate plus on-demand MCP tool discovery.

* [Kubernetes AI Toolchain Operator (KAITO) v0.12.0](https://github.com/kaito-project/kaito) – Operator automating AI/ML model inference and tuning workloads in Kubernetes clusters with GPU auto-provisioning and large model management.

* [AgentSecrets v3.2.0](https://github.com/The-17/agentsecrets) – Zero-knowledge credential infrastructure that stores and injects credentials for AI agents without ever entering agent context, enabling enforcement, auditing, and redacted responses.

* [GTM MCP Server v1.10.0](https://github.com/sprawz/gtm-mcp-server) – An MCP server that lets AI manage Google Tag Manager containers through natural-language conversations, including tag creation, auditing, and publishing changes.

* [Zero v0.8.0](https://github.com/Gitlawb/zero) – Terminal-based AI coding agent that inspects repositories, edits files, runs commands, and manages local sandboxed sessions with configurable model and permissions.

* [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.

* [PenEcho v1.0.1](https://github.com/penecho/penecho) – A shared canvas that reads handwriting and diagrams with spatial context and generates editable AI answers beside the marks.

* [ccLoad v4.7.0](https://github.com/caidaoli/ccLoad) – Go-based API server integrating Claude, Codex, Gemini and OpenAI models with Gin, DB support and Docker deployment.

* [DBHub v1.2.1](https://github.com/bytebase/dbhub) – Zero-dependency MCP server that provides safe, token-efficient read-only database access across PostgreSQL, MySQL, SQL Server, MariaDB, and SQLite.

* [mcp-use mcp-use@2.3.0](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [Openship v0.6.7](https://github.com/oblien/openship) – Source-available deployment platform that detects app stack, builds, and manages infrastructure with built-in CI/CD across desktop, web dashboard, or CLI.

* [Chat2DB v5.3.4](https://github.com/OtterMind/Chat2DB) – An AI-powered database client and SQL workspace with editing, completion, and execution for developers, DBAs, analysts, and data teams.

* [lazyagent v0.13.0](https://github.com/illegalstudio/lazyagent) – Terminal UI, macOS menu bar app and HTTP API for monitoring coding agent sessions in one place.

* [Apify MCP Server v0.15.1](https://github.com/apify/apify-mcp-server) – Enables AI agents to run Apify Actors as tools to extract web data using ready-made scrapers, crawlers, and automation.

* [ChatLab v0.36.2](https://github.com/ChatLab/ChatLab) – Private, local desktop app for analyzing and exploring chat histories using SQL and AI agents.

* [E.D.D.I 6.3.0](https://github.com/labsai/EDDI) – Multi-agent orchestration middleware coordinating users, LLM agents, and business systems with intelligent routing, conversation management, and API orchestration.

* [Entire CLI v0.10.2](https://github.com/entireio/cli) – CLI integrating with git to capture, index, and checkpoint AI agent sessions alongside commits.

* [MiMoCode v0.1.13](https://github.com/XiaomiMiMo/MiMo-Code) – Terminal-native AI coding assistant with cross-session persistent memory, task tracking, multi-agent orchestration, and integrated Git and command execution.

* [markstream-vue markstream-vue@2.0.0](https://github.com/Simon-He95/markstream-vue) – Vue 3 renderer for streaming Markdown with progressive Mermaid, streaming code diffs, and jitter-free real-time previews.

* [J-Space Cognition Suite V3.6 v3.6.1](https://github.com/Tiger3807861189/J-Space-Cognition-Suite-V3.6) – Model-agnostic inference-time cognitive control suite for deep reasoning, long-horizon work, tool use, verification, and recovery via a managed workspace protocol.

* [Eino v0.9.15](https://github.com/cloudwego/eino) – Framework for developing LLM applications in Golang with a focus on simplicity and scalability.

* [Myriade 2.177.0](https://github.com/myriade-ai/myriade) – AI-native data platform for exploring, cleaning, transforming, and governing data warehouses with collaborative AI agents.

* [Maka v0.1.11](https://github.com/apache/maka) – Local-first AI agent workspace that runs controlled tools, records execution facts in an append-only event log, and supports desktop, TUI/CLI, and evaluation.

* [A2A Go SDK v2.5.0](https://github.com/a2aproject/a2a-go) – Go library for running agentic applications as A2A servers, compliant with the Agent2Agent protocol.

* [SAP Cloud SDK for AI v2.15.0](https://github.com/SAP/ai-sdk-js) – SDK for integrating SAP AI Core, SAP Generative AI Hub, and orchestration services into JavaScript/TypeScript applications.

* [CharacterArc v1.18.0](https://github.com/uu201/character-arc) – Desktop writing tool that manages project settings, character relationships, outlines, and chapter drafting with multi-model AI agent workflows.

* [qm v0.1.5](https://github.com/yc-software/qm) – Multiplayer agent harness that provides isolated per-user workspaces with scoped memory, files, permissions, and background tasks across Slack and the web.

* [llm-d Router v0.10.0](https://github.com/llm-d/llm-d-router) – llm-d Router provides load and prefix-cache aware inference routing with prioritization and flow control, supporting standalone and Gateway API deployment via an endpoint picker.

* [mcp-1c v1.18.0](https://github.com/feenlace/mcp-1c) – 1C:Enterprise MCP server that inspects configurations and uses AI to generate accurate BSL code.

* [Alethe v1.6.0](https://github.com/Kc1t/alethe-agents) – Local-first desktop workspace that runs multiple coding agents and shells side by side with persistent PTYs, shared tooling, and recoverable session history.

* [aimux v0.3.0](https://github.com/arcships/aimux) – Rust-based unified LLM provider access layer exposing an object-safe interface with unified support for text, tools, embeddings, multimodal, and streaming across many providers.

* [TokenHub v0.6.0](https://github.com/astaxie/TokenHub) – Private enterprise AI gateway providing OpenAI-compatible APIs, role-based workspaces, project-scoped keys, and configurable routing with usage analytics and RBAC.

* [rails-ai-context v5.24.0](https://github.com/crisnahine/rails-ai-context) – Provides AI agents a complete, actionable model of a Rails app, including schema, models, routes, controllers, views, and conventions.

* [Liyuan v1.5.0](https://github.com/weidu12123/Liyuan) – AI Agent-based roleplaying app with memory ledger, decision cards, custom dashboard, and worldlines, compatible with character sheets and worldbooks.

* [IRIS v1.8.0](https://github.com/IRISX-AI/IRIS-AI) – Voice-first desktop AI assistant that executes real system actions using Gemini Live WebRTC audio, biometric security, and autonomous orchestration.

* [sqz v1.6.0](https://github.com/ojuschugh1/sqz) – Compress LLM context to save tokens and reduce costs

* [Inbox Zero - Your AI Email Assistant desktop-v0.1.0](https://github.com/elie222/inbox-zero) – AI email assistant that helps users manage their inbox efficiently.

* [React Grab @react-grab/cli@0.2....](https://github.com/aidenybai/react-grab) – Convert browser UI selections into source-rich context containing component stack and source locations for agents.

* [GolemBot v0.49.0](https://github.com/0xranx/golembot) – Connect coding agents to Slack, Telegram, Discord, Feishu, DingTalk, WeCom, WeChat, or any HTTP client with configurable LLM providers.

* [eBay API MCP Server v1.15.0](https://github.com/YosefHayim/ebay-mcp) – MCP server providing AI assistants comprehensive access to eBay Sell APIs with 325 tools for inventory, fulfillment, marketing, and analytics.

* [AI Gate v4.8.0](https://github.com/inulute/ai-gate) – Unified desktop app providing access to multiple AI assistants with customizable multi-panel layouts and privacy-focused features.

* [Civitai v5.1.11](https://github.com/civitai/civitai) – Platform for sharing, browsing, and collaborating on Stable Diffusion models and related assets.

* [Sigbound v2.4.0](https://github.com/surya-koritala/sigbound) – Sigbound runs multiple AI coding agents in parallel on one git repository, merging results only after verified builds and tests succeed.

* [LifeOS v7.40.4](https://github.com/danielmiessler/LifeOS) – LifeOS is a Life Operating System that uses AI to capture identity and goals, and then coordinates skills, memory, and a dashboard-based assistant workflow.

* [SparkyFitness v1.6.2](https://github.com/CodeWithCJ/SparkyFitness) – Comprehensive fitness tracking app for nutrition, exercise, hydration, body metrics, and goal management with AI coaching.

* [GitDesktop v0.9.0](https://github.com/theBGuy/GitDesktop) – AI-native, keyboard-first Git desktop client that manages the full pull-request lifecycle, reviews, CI, issues, and AI workflows across GitHub, GitLab, and Bitbucket via gh and system git.

* [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.

* [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.

* [NeverWrite v0.7.4](https://github.com/jsgrrchg/NeverWrite) – Local-first knowledge workspace with code-editor-like Markdown editing, multi-agent workflows, AI-powered change review, and rich navigation tools.

* [DecisionBox v0.24.0](https://github.com/decisionbox-io/decisionbox-platform) – AI-powered platform that autonomously explores data warehouses, runs AI agents to generate validated insights and actionable recommendations.

* [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.

* [Deep Agents deepagents-talon==0....](https://github.com/langchain-ai/deepagents) – Batteries-included agent harness offering planning, filesystem tools, sub-agents, sandboxed shell, and context management.

* [Azure Developer CLI azure-dev-cli\_1.32.0](https://github.com/Azure/azure-dev) – Developer-centric CLI tool that streamlines Azure application creation and enforces best practices.

* [Obot v0.24.2](https://github.com/obot-platform/obot) – MCP Gateway and AI platform that provides LLM chat, server discovery, knowledge integration, and centralized administration for self-hosted or cloud deployments.

* [Goink v1.4.2](https://github.com/sigpanic/goink) – Cross-platform desktop AI novel writing assistant with conversational prompting, automatic status tracking, and local semantic search over SQLite using ONNX and BGE embeddings.

* [OpenSandbox server/v0.2.3](https://github.com/opensandbox-group/OpenSandbox) – General-purpose sandbox platform for AI applications, with unified APIs, multi-language SDKs, and Docker or Kubernetes runtimes for agent coding, evaluation, and training.

* [altimate-code v0.9.7](https://github.com/AltimateAI/altimate-code) – Deterministic data engineering harness offering SQL analysis, column-level lineage, dbt integration, FinOps, and multi-cloud warehouse connectivity.

* [sandboxed v0.3.12](https://github.com/tastyeffectco/sandboxd) – Self-hosted developer sandboxes providing live preview URLs, one-command install, agent-driven code generation, and on-demand sleep/wake.

* [Marinara Engine v2.4.4](https://github.com/Pasta-Devs/Marinara-Engine) – Local AI-powered chat, roleplay, and game engine offering plug-and-play setup.

* [TanStack AI @tanstack/ai-lovable...](https://github.com/TanStack/ai) – Type-safe SDK for building provider-agnostic, multimodal AI applications with chat, streaming, agent loops, and isomorphic tools.

* [Photoshop MCP Server v1.7.2](https://github.com/alisaitteke/photoshop-mcp) – MCP server that lets AI assistants control Photoshop with structured, state-aware tools, recipe workflows, and an optional standalone web UI with plan-then-execute runs.

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

* [Montscan v1.3.2](https://github.com/sh4den/Montscan) – Automated scanner document processor using Vision AI for text extraction, Ollama-based naming, and configurable FTP/SMB/WebDAV ingestion and upload workflows.

* [DBCrust v0.37.0](https://github.com/clement-tourriere/dbcrust) – Fast psql-style terminal workbench offering a unified workflow for multiple databases and local files, with optional AI, scripting, and Django/Python support.

* [MyAgents v0.4.11](https://github.com/hAcKlyc/MyAgents) – Desktop AI agent workspace and task center with multi-provider runtimes, IM/chat integrations, and CLI/SDK tooling.

* [Eliza pr-evidence-11](https://github.com/elizaOS/eliza) – Framework for developing and deploying multi-agent systems with real-time communication and extensible integrations.

* [CLI WeChat Bridge 1.1.4](https://github.com/UNLINEARITY/CLI-WeChat-Bridge) – Bridges AI command-line tools into WeChat with bidirectional chat and thread/session sync between WeChat and the local terminal.

* [Sidemantic v0.11.0](https://github.com/sidequery/sidemantic) – SQL-first semantic layer for consistent metrics and cross-format semantic model compatibility across data warehouses.

* [GoNavi v0.9.4](https://github.com/Syngnat/GoNavi) – Modern native database manager supporting MySQL, PostgreSQL, SQLite and more, built with Go/Wails and React.

* [assaio v0.24.0](https://github.com/assaio/assaio) – Offline-first AI-engineering analytics that reads local session logs to compute per-project effectiveness and costs across Claude Code, Codex CLI, Gemini CLI, Copilot CLI, and Cline without telemetry.

* [Open Photo AI (OPAI) 26.8.4](https://github.com/vegidio/open-photo-ai) – Open Photo AI (OPAI) provides photo denoise, face recovery, and colorization enhancements as a photo AI editor alternative.

* [AI Job Hunter v0.143.0](https://github.com/saeedkolivand/ai-job-hunter-app) – Local-first desktop assistant that scrapes job boards, matches roles to your resume, and generates resumes and cover letters offline with supported AI backends.

* [Lapian Notes v0.5.2](https://github.com/bkingfilm/lapian-notes) – AI-assisted film lapian notes with local frame extraction, timeline and structure tree views, emotion curves, and export to Markdown.

* [Coolify MCP Server v2.19.4](https://github.com/StuMason/coolify-mcp) – MCP server enabling AI assistants to manage, debug, and batch-operate Coolify instances via token-optimized tools.

* [omi context-for-claude-v...](https://github.com/BasedHardware/omi) – Wearable platform that captures conversations, transcribes them in real time, and generates summaries and action items.

* [SurfSense v0.0.38](https://github.com/MODSetter/SurfSense) – Highly customizable AI research agent integrating personal knowledge bases with multiple external sources and advanced search capabilities.

* [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.

* [The Pair v2.7.1](https://github.com/timwuhaotian/the-pair) – Automated pair-programming app where two AI agents cross-check code and collaborate with real-time monitoring.

* [DEEIX Chat v0.3.6](https://github.com/DEEIX-AI/DEEIX-Chat) – Enterprise AI workspace unifying model routing, multimodal chat, file/RAG workflows, tools, billing, identity, and operations.

* [tRPC-Agent-Go v1.11.2](https://github.com/trpc-group/trpc-agent-go) – Go framework for building autonomous intelligent agents with multi-agent orchestration, persistent memory, and tool integration.

* [skill-up v0.9.1](https://github.com/alibaba/skill-up) – Evaluation and evolution tool for Agent Skills that runs declarative YAML cases across engines and iteratively repairs or expands eval suites based on failures.

* [Stagehand stagehand-server-v3/...](https://github.com/browserbase/stagehand) – AI-enhanced browser automation framework combining code and natural language for reliable production use.

* [OfficeDex v0.6.9](https://github.com/officecli/officedex) – AI-native desktop workspace that generates and formats .docx, .pptx, and .xlsx from natural language.

* [web-researcher-mcp v1.49.0](https://github.com/zoharbabin/web-researcher-mcp) – MCP-based web research assistant that performs real web search and full-page reading with verifiable, never-fabricated citations.

* [HeyGen CLI v0.8.0](https://github.com/heygen-com/heygen-cli) – Command-line tool to create and manage AI-generated videos via a video-generation API.

* [Agent-Native @agent-native/dispat...](https://github.com/BuilderIO/agent-native) – Framework unifying autonomous agents and interactive UIs with shared state, database support, and production-ready templates.

* [dario v5.5.18](https://github.com/askalf/dario) – Local LLM router exposing one endpoint to proxy Anthropic and OpenAI-compatible providers, enabling tools to use Claude subscriptions and other backends.

* [agentmemory v0.9.29](https://github.com/rohitg00/agentmemory) – Persistent, searchable, versioned memory system for AI coding agents with BM25, vector, knowledge-graph retrieval and provenance.

* [Cursor History v0.18.0](https://github.com/S2thend/cursor-history) – POSIX-style CLI for browsing, searching, exporting, and backing up Cursor AI chat history.

* [Anki MCP Server v0.24.1](https://github.com/ankimcp/anki-mcp-server) – Model Context Protocol server that lets AI assistants sync with Anki, review cards, and create or edit notes through exposed tools.

* [ReadAny v1.3.6](https://github.com/codedogQBY/ReadAny) – AI-powered e-book reader with semantic search, intelligent chat, local vector store, annotations, TTS, and knowledge management.

* [CloudTerm v1.4.0](https://github.com/BradPerbs/cloudterm) – CloudTerm is an Electron-based terminal workspace that combines SSH, SFTP, Telnet, and Windows RDP with file transfers, port forwarding, and an AI session assistant.

* [LettuceAI desktop-release-2.2....](https://github.com/LettuceAI/app) – Privacy-first AI roleplay and storytelling app with long-term memory, custom characters, and support for 20+ model providers on Android, Windows, macOS, and Linux.

* [exxperts v0.9.2](https://github.com/EXXETA/exxperts) – Local-first agentic runtime providing persistent AI rooms with approval-gated memory, shared across a web app and CLI/TUI while keeping data on disk.

* [K8M v0.26.18](https://github.com/weibaohui/k8m) – Lightweight cross-platform Mini Kubernetes AI Dashboard for multi-cluster management, intelligent analysis, and real-time anomaly detection.

* [AI-Driven Dev Framework v5.8.1](https://github.com/ai-driven-dev/framework) – Marketplace framework for AI-driven development that provides skills, agents, commands, rules, prompts, templates, and SDLC orchestration to ship high-quality production features.

* [Pane v2.4.82](https://github.com/dcouple/Pane) – Terminal-first agent manager that runs any CLI AI agent, manages worktrees, and centralizes agent workflows.

* [go-utcp v1.12.3](https://github.com/universal-tool-calling-protocol/go-utcp) – Go library implementing the Universal Tool Calling Protocol for discovering and calling tools across multiple transports.

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

* [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.

* [sx v2.3.8](https://github.com/sleuth-io/sx) – Package manager for team-shared AI assets including skills, MCP configs, commands, and scoped installs.

* [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.

* [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.

* [Cyrus v0.2.69](https://github.com/cyrusagents/cyrus) – LLM-powered background agent that monitors issues, creates per-issue git worktrees, runs sessions, and streams rich updates to Linear, GitHub, GitLab, and Slack.

* [fount runner-v0.0.0.4](https://github.com/steve02081504/fount) – Extensible framework for building and hosting AI character interactions with modular components and custom AI integration.

* [Eino Extension components/model/age...](https://github.com/cloudwego/eino-ext) – Extensions providing official implementations, callback handlers, and DevOps tools for the Eino framework.

* [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.

* [Whispering Tiger UI v1.3.10.2](https://github.com/Sharrnah/whispering-ui) – Native desktop interface to control live transcription, translation, TTS, and output plugins for audio and image sources.

* [AutoMem MCP mcp-automem-v0.16.0](https://github.com/verygoodplugins/mcp-automem) – AutoMem MCP is an MCP server that connects AI assistants to persistent graph-vector memory for durable cross-session recall and syncing across platforms.

* [Modelence modelence@0.23.0](https://github.com/modelence/modelence) – TypeScript framework that eliminates boilerplate for common modern web app features like authentication, database, and AI observability.

* [Utsuwa v0.13.2](https://github.com/The-Lab-by-Ordinary-Company/utsuwa) – Utsuwa is a privacy-focused AI companion platform with 3D VRM avatars, WebXR AR mode, photo and touch interactions, and local-first data storage.

* [yorishiro v0.7.4](https://github.com/sktkkoo/Yorishiro) – Presence-focused macOS terminal that lets an AI inhabit and reshapes its scene and UI in real time through editable, self-modifiable packs.

* [vscode-dbt-power-user 0.64.4](https://github.com/AltimateAI/vscode-dbt-power-user) – VSCode extension enhancing dbt workflows with autocomplete, query preview, lineage, documentation, health checks, and cost estimation.

* [VelaTerm v0.1.105](https://github.com/vlinx-io/VelaTerm) – A terminal manager that organizes AI coding sessions into a persistent project group session tree with agent-aware status and remote browser or SSH access.

* [Oh My OpenCode v5.0.0-beta.19](https://github.com/code-yeongyu/oh-my-openagent) – Agent harness that orchestrates diverse models for automated coding, reasoning, and task execution.

* [ai-rulez v4.11.3](https://github.com/Goldziher/ai-rulez) – Directory-based manager that centralizes AI assistant rules and context and generates native configs for various AI tools.

* [iii iii-alpha/v0.22.1-al...](https://github.com/iii-hq/iii) – Unifies backend tools into a single engine with two primitives: Function and Trigger.

* [Agent SDK for Go v0.3.5](https://github.com/agenticenv/agent-sdk-go) – Temporal or Restate-backed Go SDK for running AI agents durably, with pluggable components for state, tool calls, and execution loops across restarts.

* [Comfy Portal release-v1.1.0](https://github.com/ShunL12324/comfy-portal) – Native iOS and Android companion for ComfyUI that provides real-time monitoring, seamless LAN or remote connections, and on-the-go workflow management.

* [ReadAware v0.5.0-6](https://github.com/ahpxex/read-aware) – Sentence-by-sentence reading app with an agent that uses annotations and conversations to answer questions and build durable memory from books.

* [AI LocalBase v1.4.7](https://github.com/veyliss/ai-localbase) – Local-first RAG knowledge base connecting local Markdown, TXT, and PDF documents to retrieval search and LLM chat.

* [Waveloom v0.7.8](https://github.com/Menfre01/waveloom) – DeepSeek-native terminal code agent with prefix-cache optimized turns, auto-selecting reasoning or flash modes and providing a premium TUI with drop-in skill configuration.

* [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.

* [IM.codes android-dev-v1.1-117...](https://github.com/im4codes/imcodes) – IM.codes provides a shared memory layer and managed MCP tool surface for coding agents, including supervised execution and cross-agent audit across AI providers.

* [elevenlabs v0.2.5](https://github.com/taigrr/elevenlabs) – Unofficial Go client for voice synthesis on elevenlabs.io, supporting streaming text-to-speech, speech-to-text, sound generation, and voice management.

* [ClawRouter v0.12.246](https://github.com/BlockRunAI/ClawRouter) – Smart LLM router that locally routes requests to the cheapest capable model across 30+ providers, reducing inference costs.

* [Bilibili AI Skip v2.3.29](https://github.com/qingmeng1/bilijump-ai) – Browser extension that uses AI to automatically skip embedded ads in Bilibili videos.

* [Joanium v2026.822.0](https://github.com/Joanium/Joanium) – Local-first AI desktop agent that runs scheduled background tasks, supports multi-model chat, and can use real integrations via MCP.

* [Claude Terminal v1.2.18](https://github.com/Sterll/claude-terminal) – Cross-platform desktop app for managing Claude Code projects with integrated terminal, git workflows, and plugin management.

* [GoModel v0.1.80](https://github.com/ENTERPILOT/GoModel) – High-performance Go-based AI gateway providing an OpenAI-compatible API and unified access to multiple LLM providers with observability, guardrails, and streaming.

* [KektorDB v0.6.2](https://github.com/sanonone/kektordb) – Embeddable in-memory vector and graph database combining HNSW-based similarity, hybrid BM25 search, and built-in RAG and AI gateway features.

* [Hivemind v0.7.148](https://github.com/activeloopai/hivemind) – Persistent cloud-backed shared memory for Claude Code, OpenClaw, and Codex agents.

* [Incognide v0.2.28](https://github.com/NPC-Worldwide/incognide) – Unified tileable workspace combining chat, code, documents, web browsing, and media with context-aware automations.

* [chartr v0.2.4](https://github.com/rengwu/chartr) – Agent multiplexer that visualizes work as a star-map and coordinates agent sessions with contextual tickets and blockers.

* [LangGraph.js @langchain/langgraph...](https://github.com/langchain-ai/langgraphjs) – Graph-based low-level orchestration framework for building controllable language agents with long-term memory and human-in-the-loop.

* [AI-Native ITSM v1.6.9](https://github.com/heidsoft/itsm) – AI-native IT service management platform with ITIL and BPMN workflows, CMDB support, and an AI-assisted interface built with Go and Next.js.

* [BeeAI Framework python\_v0.1.83](https://github.com/i-am-bee/beeai-framework) – Toolkit for building intelligent, autonomous agents and multi-agent systems with reasoning and collaboration capabilities.

* [Poracode v1.6.5](https://github.com/SDSLeon/lightcode) – Poracode is a desktop app that runs multiple AI coding agents side-by-side with shared terminal, chat, flexible layouts, and built-in MCP-based orchestration.

* [Nylas CLI v3.1.30](https://github.com/nylas/cli) – Command-line tool for Nylas API authentication and managing email, calendar, contacts, webhooks, timezone utilities, and OTP extraction.

* [aiusage v1.5.12](https://github.com/juliantanx/aiusage) – Local-first dashboard tracking tokens, costs, and sessions across multiple AI coding tools without accounts.

* [RoleCraft v2.3.2](https://github.com/rolecraft-sh/rolecraft) – Zero-dependency CLI package manager for AI agents that installs, tests, publishes, and manages skills and MCP servers across 86+ agents with offline-first support.

* [OpenWiki v0.3.23](https://github.com/kdsz001/OpenWiki) – macOS desktop app capturing clipboard content into a local AI-organized personal wiki with search, graph visualization, and insight reports.

* [archestra platform-v1.3.39](https://github.com/archestra-ai/archestra) – MCP-native centralized platform for orchestrating, securing, and observing MCP servers with private registry and cost controls.

* [MCP Google Maps v0.0.55](https://github.com/cablate/mcp-google-map) – MCP-based server providing Google Maps API integration with 17 geo tools, routing, geocoding, and agent skills.

* [Terraphim AI Assistant v1.21.3](https://github.com/terraphim/terraphim-ai) – Privacy-first deterministic AI assistant running locally with semantic knowledge graph search and fast offline capability.

* [OpenClaw pr-124528-profiles](https://github.com/openclaw/openclaw) – Personal, single-user AI assistant that runs locally and connects to messaging channels, voice input/output, and a live Canvas.

* [EverFern v1.1.6](https://github.com/Everfern-AI/Everfern) – Local desktop AI agent that plans and executes computer actions, including browser research, with sandboxed execution and persistent memory.

* [mcpd v0.5.2](https://github.com/mozilla-ai/mcpd) – Daemon that manages MCP servers via declarative configuration, exposing them as HTTP endpoints while handling lifecycle management, secret injection, and environment promotion.

* [burn v0.5.3](https://github.com/tanrikuluozlem/burn) – CLI tool to analyze Kubernetes cluster costs and identify expensive resources using real-time cloud pricing and AI insights.

* [clai v1.10.22](https://github.com/baalimago/clai) – Command-line context feeder for LLMs, enabling vendor-agnostic conversations, profiles, and Unix-like piping workflows.

* [OpenCode Mobile v0.4.15](https://github.com/dzianisv/opencode-mobile) – OpenCode Mobile is an Android React Native client for the opencode AI coding agent, streaming chat sessions from a self-hosted server with diff and tool-call approval UI.

* [LibreChat v0.8.8-rc1](https://github.com/danny-avila/LibreChat) – ChatGPT-inspired interface supporting multiple AI models, code execution, agents, web search, image generation, and advanced context management.

* [COMandA v0.0.219](https://github.com/kris-hansen/comanda) – Command-line tool to define, version-control, and run YAML-based LLM pipelines locally or as servers.

* [Rove v0.8.201](https://github.com/Sma1lboy/rove) – Terminal-native workspace that runs multiple coding tasks in parallel using isolated git worktrees and persistent agent or shell sessions.

* [agent-inspect @agent-inspect/studi...](https://github.com/rajudandigam/agent-inspect) – Local evidence debugger for TypeScript AI agents that turns runs into execution trees for debugging, regression checks, and share-checked offline artifacts.

* [PR Cockpit nightly](https://github.com/taovc/pr-cockpit) – Local AI PR workbench that uses Claude or Codex to review PR queues in isolated worktrees, with human-gated GitHub inline comments.

* [RocketRide server-v3.3.0-prerel...](https://github.com/rocketride-org/rocketride-server) – High-performance C++ core data-processing engine with Python-extensible nodes and IDE-based visual builder for scalable AI and data pipelines.

* [DeepChat v1.1.1-beta.5](https://github.com/ThinkInAIXYZ/deepchat) – Feature-rich multi-model AI chat platform supporting cloud/local LLMs, search enhancement, tool calling, and multimodal interaction.

* [Kition v0.1.39](https://github.com/KitionAI/kition) – Desktop workspace that combines Markdown documents, structured data tables, an infinite whiteboard, a tool-using AI agent, browser research, and visual workflows.

* [HASH @hashintel/petrinaut...](https://github.com/hashintel/hash) – Self-building knowledge graph database that integrates, structures, and autonomously maintains trusted data across sources.

* [Shelly optional-packs-lates...](https://github.com/RYOITABASHI/Shelly) – Android phone-based agent workspace that runs tasks via local or API AI accounts inside an on-device native terminal IDE, without cloud execution or Termux.

* [ComputeSDK @computesdk/microsan...](https://github.com/computesdk/computesdk) – Provider-agnostic TypeScript toolkit for securely running untrusted code in isolated sandboxes.

* [Gokin v0.100.140](https://github.com/ginkida/gokin) – CLI-based AI coding assistant that understands codebases, performs file operations, code search, shell and git workflows via natural language.

* [Everroom desktop-v0.1.5](https://github.com/NxcoreAI/EverRoom) – A local-first context workspace that connects evidence to AI agents, governing memory and project decisions through reviewable, room-scoped documents and operations.

* [Yao v1.0.0-rc17](https://github.com/YaoApp/yao) – Engine for event-driven, proactive, self-scheduling autonomous agents with scheduling, multi-agent orchestration, and built-in vector/graph retrieval.

* [@rpamis/comet 0.4.0-beta.19](https://github.com/rpamis/comet) – OpenSpec and Superpowers-based five-phase pipeline that automates spec lifecycle, design handoff, state detection, and archival.

* [LLMKube llmkube-0.9.19](https://github.com/defilantech/LLMKube) – Kubernetes operator managing self-hosted LLM inference on NVIDIA GPUs and Apple Silicon, with autoscaling, model routing, and OpenAI-compatible API.

* [DevWeek app-v0.1.5](https://github.com/JYYYYYT/dev-report-weekly) – Desktop app that uses AI to turn locally reviewed Git commits into editable weekly Markdown work reports, with commit filtering and checks.

* [@microcharts/react @microcharts/react@0...](https://github.com/ganapativs/microcharts) – @microcharts/react provides word-sized, accessible React chart components with 106 SVG chart types and zero runtime dependencies, optimized for server components and AI streaming.

* [kagent v0.10.0-rc3](https://github.com/kagent-dev/kagent) – Kubernetes-native framework for building, deploying, and managing AI agents.

* [AI-Enabled Search Engine using LLM Embeddings, Django, and pgvector v1.0-video](https://github.com/thinknimble/embeddings-search-demo) – Prototype job-description search app that matches unstructured natural-language seeker profiles using LLM embeddings stored in pgvector with a Django backend.

* [OpenYida v2026.8.17](https://github.com/openyida/openyida) – Yida low-code app builder using AI for zero-config development and instant deployment.

* [Thunderbolt v0.1.123-nightly.202...](https://github.com/thunderbird/thunderbolt) – Cross-platform AI client for on-prem and local models with enterprise features and self-hosting support.

* [MCP DevTools v0.59.98](https://github.com/sammcj/mcp-devtools) – Modular MCP server providing commonly used developer tools for AI coding agents.

* [AI Free v0.4.23](https://github.com/Staks-sor/ai-free) – Local-first AI client and coding assistant that unifies DeepSeek, Qwen and ChatGPT via desktop UI, CLI, and OpenAI/Anthropic-compatible APIs with code-agent workflows, memory, and skills.

* [Parliament v2.2.2+18](https://github.com/kornha/parliament) – Pre-release news project that organizes stories by Confidence, Bias, Newsworthiness, and Contextualization to present clear, measurable claims.

* [Sdcb Chats 1.17.0.772](https://github.com/sdcb/chats) – Enterprise-ready AI chat interface supporting multiple APIs and storage backends.

* [Amical v1.12.0-beta.3](https://github.com/amicalhq/amical) – AI-powered dictation and note-taking app with context-aware transcription and multi-platform support.

* [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.

* [OpenCove v0.2.0-nightly.20260...](https://github.com/DeadWaveWave/opencove) – Infinite 2D canvas workspace that organizes AI agents, terminals, tasks, and notes.

* [Pi Desktop v0.1.6-alpha](https://github.com/FaqFirebase/pi-desktop) – Electron-based desktop GUI for the Pi coding agent, providing streaming chat, file management, command execution, package installation, and review/permissions views in one window.

* [\_mom\_ v0.53.0-alpha](https://github.com/momhq/mom) – Local-first persistent memory layer for AI coding agents, storing decisions and tool transcripts for recall across sessions and tools.

* [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.

* [Emdash v1.1.41-canary.84](https://github.com/generalaction/emdash) – Orchestration layer for running multiple coding agents in parallel with isolated Git worktrees and provider-agnostic support.

* [Grix v3.2.4+869](https://github.com/askie/grix) – Mobile and desktop chat app for DeepSeek Harness and other coding agents, managing agents as contacts and enabling shared threaded collaboration with controls and approvals.

* [aiscan v1.0.0-rc2](https://github.com/chainreactors/aiscan) – AI-driven single-binary pentest agent combining LLM agents with traditional scanning engines in scan, agent, and multi-agent IOA modes.

* [Litex 0.9.115-beta](https://github.com/litexlang/golitex) – Simple formal language for writing and automatically verifying mathematical proofs with step-by-step inference.

* [E2B @e2b/code-interprete...](https://github.com/e2b-dev/code-interpreter) – Infrastructure for running AI-generated code in secure isolated cloud sandboxes with JavaScript and Python SDKs.

* [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.

* [Monadic Chat v1.0.0-beta.30](https://github.com/yohasebe/monadic-chat) – Locally hosted web application for creating and utilizing intelligent chatbots with advanced task execution capabilities.