MCP servers and skills: search, filter by where they run, and compare.
A Claude Code skill: capture cognitive cracks from coding sessions, distill into reusable engineering knowledge
SkillMIT★ 32No key
面向可信个人开发机的 MCP 编程运行时：Agent Transport、Windows Workbench、证据优先的项目连续性 | Personal-workstation MCP coding runtime
PythonApache-2.0★ 18No key
Workflow-agnostic guardrails for AI coding agents: spec sync + risk-triggered engineering discipline for Claude Code and Codex.
SkillMIT★ 25No key
Query-aware context compression for LLMs and coding agents. Cut ~65% of input tokens.
Node.jsMIT★ 137No key
ZAP is a terminal-first, local AI coding agent built in Rust. It uses AST-powered codebase indexing and lazy-loaded skills to completely eliminate prompt bloat and minimize context token costs.
SkillMIT★ 36No key
Codingbuddy orchestrates 29 specialized AI agents to deliver code quality comparable to a team of human experts through a PLAN → ACT → EVAL workflow.
SkillMIT★ 31No key
Adopt repository-level harness engineering for coding agents. Use when a user wants to prevent repeated AI coding-agent mistakes by turning failures into durable instructions, drift checks, regression
OfficialSkillMIT★ 40k in collectionNo key
Local-first, inspectable memory for coding agents: durable context across sessions and repositories, code-aware recall, bi-temporal history, MCP, and a self-hosted WebUI.
PythonApache-2.0★ 180No key
A human-in-the-loop control plane for reliable agentic coding—plan, challenge, implement, verify, and preserve progress.
SkillMIT★ 22No key
Honeydew AI plugins for coding agents (Claude Code, Codex, Cursor, Github Copilot, Gemini, etc...)
SkillApache-2.0★ 42No key
Detect configuration drift across environments before it causes incidents
Node.jsMIT★ 4Few starsNo key
Use your ChatGPT or Claude Web quota for remote coding without a second server-side API token meter
SkillMIT★ 18No key
Multi-agent orchestration for Claude Code. Persistent memory, tasks, rules, and skills that make AI agents actually coordinate.
SkillMIT★ 177No key
Run coding agents without babysitting them. Keep jobs focused, bounded, checked and accountable from start to finish. Finally run your agents swarms overnight and get your time back.
Node.jsApache-2.0★ 413No key
An open-source agentic CLI + Agent Skill that turns "I want an agent that debugs production" into a validated, buildable multi-agent system — through progressive questioning, pluggable context framewo
SkillMITFew starsNo key
Claude Code scaffolding and first steps for complex brownfield projects
SkillApache-2.0★ 32No key
Turn Lighthouse audits into coding-agent tasks.
Node.jsMIT★ 4Few starsNo key
AI coding harness: AST-powered code navigation, impact analysis, phased task chains, and cross-session memory.
SkillMIT★ 17No key
VAP AI platform: AI Room, Media API MCP tools, and Coding Plan API for coding agents and IDE workflows.
Hosted by authorMIT★ 2Few starsNo key
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo w
PythonMIT★ 32kNo key
A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenCode) with built‑in Skills/tools and a desktop GUI to capture, search, and reuse project kn
Node.jsMIT★ 1.3kNo key
Run DeepSeek as a real sub-agent inside Claude Code / Codex CLI — with its own 7-tool agent loop, workspace-scoped file access, and bounded Bash.
PythonMIT★ 45No key
Who stands behind it
