MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
Production-grade multi-agent RAG workflow + an ML-infrastructure platform (PyTorch/DDP, RAG, evals, guardrails, MCP). Keyless-by-default; ships a real, reproducible Banking77 retrieval benchmark.
PythonMIT★ 4Few starsNo key
Python terminal AI agent CLI with ReAct tools, MCP, Runtime API, memory, snapshots, web search, and image input
PythonMIT★ 108No key
Task-scoped least-privilege security proxy and Wazuh detection bridge for MCP-based AI agents
MCPLink only★ 1Few stars
Framework profissional de orquestracao multi-agente em Python: crews, flows orientados a eventos, ReAct, RAG, memoria, MCP/A2A e multi-provider LLM
PythonMIT★ 208No key
Tracy profiler MCP adapter for AI agents to capture instrumented applications, export trace CSV data, and analyze zone timing through the DCC-MCP ecosystem.
PythonMITFew starsNo key
Learn a codebase's unwritten conventions (Python, React, Next.js, TypeScript, Tailwind) and condition AI coding agents (Claude Code, Cursor, Google Antigravity, Windsurf, Copilot, MCP) to ghostwrite c
PythonMIT★ 1Few starsNo key
A highly configurable, self-evolving AI Agent operating system with plugin pipeline, multi-layer memory, hot‑reload, and MCP support. Built on FastAPI & React.高度可配置、自进化的智能体操作系统，支持插件化管道、多层记忆、热替换和 MCP 协
PythonApache-2.0★ 7No key
Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.
PythonMIT★ 230No key
Universal autonomous agent framework with ReAct loop, multi-provider LLM routing, reasoning graph, and MCP integration, domain-agnostic for building specialized AI agents.
PythonMIT★ 34No key
MCP server to interact with LogSeq via its Local HTTP API - enabling AI assistants like Claude to seamlessly read, write, and manage your LogSeq graph.
PythonMIT★ 347No key
A from-scratch Python agent harness: tool orchestration, multi-agent routing, session lifecycle, event-driven hooks, and cross-session memory recall.
PythonMIT★ 3Few starsNo key
A lightweight terminal AI coding assistant powered by dual-mode LLM (ReAct + Plan Mode). Features multi-agent collaboration, memory persistence, MCP integration, and more.
PythonMIT★ 1Few starsNo key
MCP server that builds a real-time code knowledge graph via Tree-sitter AST parsing, giving AI coding agents instant structural and semantic codebase navigation.
PythonMIT★ 3Few starsNo key
🔧 Compose Model Context Protocol (MCP) servers with management capabilities, REST API, and Web UI — Similar to Docker Compose
PythonBSD-3-Clause★ 12No key
Python-first Model Context Protocol (MCP) toolkit: a guarded MCP server (4 tools), a framework-free agent loop, a versioned Prompt Registry with gated A/B promotion and a hash-chained audit log, a Fas
PythonMITFew starsNo key
企业级多智能体 + RAG 知识库问答平台 | Enterprise multi-agent + RAG knowledge assistant: 多模型网关 / 混合检索 / ReAct Agent / 多Agent编排 / MCP，零 API Key 离线可跑，克隆即演示。Runs fully offline out of the box.
PythonMIT★ 1Few starsNo key
Terminal AI coding agent built from scratch — ReAct loop, multi-LLM providers, 5-layer permissions, MCP, context compaction, subagents & teams. 716 tests.
PythonMIT★ 1Few starsNo key
AI agent that actually operates your Windows apps — real clicks & keystrokes, persistent memory, 12+ IM channels. An AI Agent that truly operates your desktop
PythonApache-2.0★ 4Few starsNo key
Production-grade template for AI agent harnesses: ReAct loop, sandboxed tools, policy & human approval, memory, multi-agent, observability, evals. Agent = Model + Harness.
PythonMIT★ 3Few starsNo key
An AI agent framework that builds itself — multi-model ReAct + tiered cache-friendly context + async multi-agent + XML workflows. CLI & WebUI, zero LangChain.
PythonMIT★ 1Few starsNo key
Who stands behind it
