Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
A middleware to provide an openAI compatible endpoint that can call MCP tools
PythonMIT★ 924No key
Build effective agents using Model Context Protocol and simple workflow patterns
PythonApache-2.0★ 8.6kNo key
CodeAgent is an open-source coding agent that lives in your terminal. It understands your repository, plans multi-step changes, writes and edits files, runs commands and tests, and iterates until the
PythonMIT★ 824No key
Local-first, governed AI agent runtime for Python — embed it in your app, or run it as a CLI or ACP server. Permissions, MCP, memory and audit replay built in.
PythonMIT★ 309No key
The deterministic merge gate for AI-generated agent capability changes — a local-first, static Tool-Use Readiness review for MCP, OpenAPI, and SDK tool surfaces. Open-source CLI + GitHub Action.
PythonApache-2.0★ 90No key
Open-source Power BI MCP to build, audit and repair Desktop models and PBIP reports with DAX, TOM, TMDL and PBIR.
PythonApache-2.0★ 29No key
Agent Library personal knowledge base with a search and retrieval system MCP Server and CLI. Preconfigured local models and support for Text, images, OCR/vision, and code embeddings. Use over MCP with
PythonApache-2.0★ 31No key
Your agent has amnesia. Noshy fixes that. Persistent memory for AI agents — LLM extraction, hybrid search, zero deps.
PythonApache-2.0★ 4Few starsNo key
Streaming privacy for LLM apps: pii-leak-benchmark (does your gateway leak PII in streams?), chunk-invariance (one-line test for split-boundary leaks), mcp-ssrf-check, and a self-hosted redacting gate
PythonApache-2.0★ 12No key
Open-source marketing skills that run on any model — with a hosted brand-memory engine. No coding agent required.
SkillApache-2.0★ 25No key
A Python-based API server for creating AI persona agents using Google A2A protocol and Model Context Protocol (MCP) tools integration.
PythonApache-2.0★ 11No key
Ask, compare, and synthesize across 10 LLM providers. Python SDK, CLI, local Arena, MCP, and privacy-aware
PythonMIT★ 34No key
🎬 MCP Server + Agent Skill + CLI — Transcribe any video URL to text. Plug into Claude Desktop / Cursor / Windsurf / Codex. Supports Bilibili, YouTube, TikTok, 1000+ sites × 5 ASR providers.
PythonMIT★ 4Few starsNo key
Reference implementation of an AI Agent using Claude Agent SDK. Transforms videos into knowledge graphs via MCP tools: transcription, entity extraction, graph building, natural language querying.
PythonApache-2.0★ 4Few starsNo key
Description: Local-first pre-commit policy guard for AI-agent repositories. Website: https://pypi.org/project/aigenguard/
PythonMIT★ 3Few starsNo key
An economical and fuel(token) efficient AI tool, graph session memory for looong chat session
PythonMIT★ 2Few starsNo key
Multi-agent orchestrator with cyclic personal-to-org memory · Apache 2.0 · Python 3.11+
PythonApache-2.0★ 9No key
Tensory — Claim-native MCP Memory Server. LLM claim extraction → Graph + Vector + SQLite. Zero-setup persistent memory for Claude, Cursor & any MCP client.
PythonMIT★ 4Few starsNo key
Seven MCP servers for 934 tokens instead of 20,005 (measured). MCP router + native DeepSeek Harness bundle.
PythonMIT★ 2Few starsNo key
Local, cross-provider preflight checks for LLM integration changes
PythonMIT★ 3Few starsNo key
Zero-plaintext secret layer for AI agents & MCP — one local encrypted file, Touch ID unlock, plaintext-leak hunter. | AI 助手/MCP 的零明文密钥层:本地单文件加密、Touch ID 解锁、明文泄漏清剿
PythonMITFew starsNo key
Multi-model AI gateway — 8 providers plus local models, no system prompt injection.
PythonApache-2.0★ 1Few starsNo key
Deterministic, self-hosted long-term memory for AI agents: store facts instead of transcripts, recall only what matters.
PythonMIT★ 9No key
Who stands behind it