Multi-model AI agent runtime. Define agents in YAML, connect 6 LLM providers, orchestrate with ReAct/Plan&Execute/Fan-Out/Pipeline/Supervisor/Swarm patterns, and deploy as REST/WebSocket API with RAG, memory, MCP tools, guardrails, and OpenTelemetry observability.

🔍 AI observability skill for Claude Code. Debug LangChain/LangGraph agents by fetching execution traces from LangSmith Studio directly in your terminal.

Production-ready TypeScript SDK for MCP servers: auth, multi-tenant, observability. Build enterprise AI agents fast.

Semantic code search engine - by Verivus (sqry.dev)

Plugins and Knowledge Patches for AI - filling gaps in Claude's knowledge about language and framework features released after training cutoff

OpenCode AI 助手配置项目，支持 Google Gemini、Anthropic Claude、智谱 GLM、小米 Mimo 等 7+ 个 AI 模型。提供智能 Git 提交工作流、跨平台环境适配（NixOS/Windows/Debian/CentOS）和 MCP 协议集成，提升 AI 辅助开发效率。

A unified, multi-repo workspace for AI coding agents and developers.

Antigravity Supercharged Project Engine. A complete AI Agent architecture featuring jCodeMunch for 99% token savings, NotebookLM for deep research, and OpenSpec workflows for precise spec-driven development.

Local-first Trello cache with Git-style sync — built and optimised for AI agent workflows.

Discord CLI + MCP Server — sync, search, and send Discord messages from your terminal. Built for developers and AI agents.

Visual PR changelog plugin for Claude Code — generates structured JSON from git diffs and test results, rendered as an interactive visual report.

Beautiful status line for Claude Code with per-window token tracking, visual indicators, and intelligent fallbacks

MCP server for intelligent memory management with confidence tracking and relationship mapping. Build persistent knowledge bases for AI assistants across IDEs and CLI tools.

AI-powered platform for exploring GitHub repositories — combining hybrid RAG, AST-based code analysis, and multi-LLM routing to deliver codebase chat, architecture visualization, developer analytics, and AI pull-request reviews.

Stop your AI coding assistant from making the same mistakes. An experience evolution framework that gives AI a quantifiable long-term memory. 别让你的 AI 编程助手重复踩坑。一个赋予 AI 可量化长期记忆的经验进化框架。

Outil de refactoring assisté par IA pour codebases C++/Qt legacy. Pipeline en 4 étapes avec validation humaine à chaque étape. Réduit la complexité jusqu'à -42% en production.

Python SDK for connecting your AI agent to real-time voice, phone, and chat — with zero dead air. Plug in your existing agent and give it a voice.

🔍 Fetch execution traces from LangSmith Studio to debug LangChain and LangGraph agents effectively with Claude Code.

PM framework for teams building with AI agents. Persistent product memory, agent-ready specs, and zero cold starts - from signal to ship.🚀

Code Trajectory MCP Keep your coding momentum across AI sessions.