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.
Git MCP server
PythonMIT★ 4Few starsNo key
Smart git diff context for LLMs and AI agents: budgeted fragment selection, deterministic, MCP server included
PythonApache-2.0★ 6No key
Multi-agent orchestration loop: worker → cross-model reviewer → score ≥ 9. Ships as an MCP server, agent skill, and CLI. Supports Codex, Grok, Claude, OpenCode, and Kimi.
PythonMIT★ 5No key
为 AI 编程智能体提供本地项目记忆层 | Project memory layer for AI coding agents
PythonMIT★ 3Few starsNo key
GitPR CLI is a high-performance Git helper solution that uses AI to automate the code contribution lifecycle. It analyzes Git diffs to generate commit messages and Pull Request descriptions, while app
PythonLGPL-2.1★ 5No key
PythonMITFew starsNo key
PythonMIT★ 1Few starsNo key
git diff for your agent's context window. See exactly what your LLM saw — turn by turn, block by block.
PythonMIT★ 6No key
17 MCP query tools for codebase navigation — functions, classes, imports, dependency graphs, change impact. Zero dependencies. 87% token reduction.
PythonAGPL-3.0★ 63No key
Local-first, auditable Python code agent. Ships its own 30-task hidden-test benchmark plus SWE-bench Verified scored by the official harness -- every number reproducible, negative results included.
PythonMIT★ 154No key
A Python CLI coding agent powered by remote Ollama, with workspace inspection and command-execution tools over Tailscale.
PythonMIT★ 5No key
Universal, deterministic context compressor for AI coding agents & IDEs (Claude Code, Cursor, Antigravity, Codex, Gemini, Hermes) — 88.3% token reduction, lossless TOON v2 JSON tables, AST code skelet
PythonMITFew starsNo key
Codex Skill for behavior-preserving Windows 98, XP, 7, and Japanese freeware-style web UI conversions.
SkillMIT★ 2Few starsNo key
Open-source Python agent harness for auditable, cost-controlled LLM workflows with YAML playbooks and MCP server support.
PythonApache-2.0★ 9No key
Universal project extractor for LLMs — turn any local codebase into clean, structured, AI-ready data.
PythonApache-2.0★ 15No key
Comprehensive docstring quality vetting for Python projects
PythonMIT★ 9No key
Provenance, governed context, and code-impact analysis for coding agents.
PythonApache-2.0★ 3Few starsNo key
Agent Skills for generating and maintaining citation-backed repository wikis as MkDocs-compatible Markdown. Enables AI agents to create, update, and validate documentation with proper citations, incre
SkillMIT★ 9No key
PythonMIT★ 2Few starsNo key
Local-first Engineering Intelligence for software repositories.
PythonApache-2.0★ 11No key
AI code review agent MCP server. Reviews code like a kernel maintainer: blunt, technical, no sugarcoating. Detects bugs + OWASP Top 10 security vulnerabilities. 4 harshness levels. Anti-RLHF.
PythonMIT★ 5No key
PythonMIT★ 3Few starsNo key
Round-trips Uniface exports to plain-text files and back, byte for byte, so git, code review, grep and AI assistants work on Uniface code. Python, with a read-only MCP server.
PythonMIT★ 2Few starsNo key
Who stands behind it