MCP servers and skills: search, filter by where they run, and compare.
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
SkillMIT★ 42No key
Agent skill that turns your git diff into clean Conventional Commits — plus on-request file staging and full pull-request drafting. Works with Claude, Codex, Cursor, and Gemini.
SkillMIT★ 4Few starsNo key
Durable task planning for Codex/AI coding agents: recovery, bug memory, Mermaid-first design, verification evidence, and safe multi-agent collaboration. 为 GPT-5.6 深度优化，也兼容其他模型。
SkillMIT★ 6No key
Local-first task manager for humans and AI agents. Tasks are plain Markdown files, shared by a CLI, a TUI, and an MCP server
GoMIT★ 1Few starsNo key
Enables squad agents on different machines to share work via git-based task queuing
OfficialSkillMIT★ 5.4k in collectionNo key
本地优先的跨平台 Claude Code / AI Agent 桌面工作台：多 Agent 协作、Git Worktree、代码 Diff、技能市场、多模型、Computer Use、桌面宠物；支持微信、飞书、钉钉及 H5 等远程访问。 | Local-first Claude Code / AI Agent desktop workspace: multi-agent teams, Git wo
MCPLink only★ 15k
Open-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSocket transcripts, MCP server for AI agents. Self-host or use hosted SaaS.
Hosted by authorApache-2.0★ 2.9kNo key
When Claude keeps giving you bad answers, make 100 versions of it fight to the death. Same task, 100 different strategies, a bracket, one answer left. Free Claude Code skill.
SkillMIT★ 843No key
AI agent orchestration platform — pipeline-based task runner for Claude, Codex, and Gemini CLI agents with a visual dashboard and MCP server
Node.jsApache-2.0★ 9No key
A git-native, review-gated knowledge base for AI agents: they propose writes, you approve them. Every claim cites a source, every change is a diff in your repo. MCP + CLI.
PythonMIT★ 72No key
Open-source, local-first control plane for multi-model AI coding agents in VS Code and MCP: task DAGs, source intelligence, durable context and evidence-based review.
PythonMIT★ 11No key
An intelligent agent that understands your code and crafts perfect Git artifacts
SkillApache-2.0★ 43No key
Event-driven agentic development. Webhook in, coding agent out. No polling loops.
Node.jsMIT★ 4Few starsNo key
Local-first career tracker for 1:1s, performance reviews, and IDPs in plain Markdown. An AI Skill structures your raw notes into schema-validated data; a local dashboard turns that into visible progre
SkillMIT★ 6No key
Filesystem-driven four-lane kanban board (todo / doing / blocked / done) as a read-only MCP server and Python API. Works with DeepSeek Harness and any MCP client.
PythonMIT★ 1Few starsNo key
Inline comments and GitHub-style suggested edits for Obsidian, stored in note frontmatter. Readable by agents over CLI and MCP.
Node.jsMIT★ 2Few starsNo key
Run and steer Claude Code and Antigravity agents from a pixel-art office: each agent gets its own git worktree, chat, terminal and diff view, with approval gates, workflows, a shared skills library an
SkillApache-2.0★ 3Few starsNo key
Dispatch and review AI coding agents, hand them disposable VMs to test in, capture and summarize meetings and keep tickets, pipelines and your calendar on one deck. Available on macOS, Windows, Linux,
SkillMIT★ 7No key
AI-native task management for Claude Code. Track tasks in MASTER_PLAN.md — pick, save, ship.
SkillMIT★ 27No key
Self-hosted, open-source agent workspace — file tasks on a kanban board, let AI agents build them on your own machines.
SkillApache-2.0★ 3Few starsNo key
Sandboxed coding-agent workers for AI supervisors over MCP. Delegate tasks from Grok Bot or any MCP client to Kilo CLI or OpenCode running in per-task git worktrees inside bubblewrap, with any OpenAI-
SkillMIT★ 5No key
Who stands behind it
