
Skills, hooks, memory and security layer for coding agent harnesses
- Freemium
- Open-source agent
- 305K GitHub stars
- AI models and LLM tooling

Skills, hooks, memory and security layer for coding agent harnesses

Ruleset that makes AI coding agents write less code that still works

MCP toolkit giving coding agents symbol-level code retrieval and editing
Runs locally
Open-source terminal coding agent with IDE integrations, MCP and sub-agents
Stores every fix your coding agent makes and brings it back when the problem returns
Runs locallyPersistent project memory, code search and shared decisions for your coding assistant
Solve ASPIC+, ABA and abstract argumentation theories from an AI assistant
Runs locallyQuery and edit Firestore documents and look up Firebase Auth users from your agent
Runs locallyShared context and file queues so coding agents on one team stop overwriting each other
Runs locallyDecode MsgPack bytes into readable text, including from paused debugger variables
Runs locallyRun website SEO audits and read ranked fixes from an AI assistant

Narrow VS Code connector for Hydracept: text jobs, quotes and receipts over OAuth
Find and free developer cache and old node_modules disk space, with an AI-assistant mode
Runs locallyChecks JS/TS written by AI for risky patterns, fake npm packages and weakened tests
Runs locally
Write floor plans as code and compile, lint and repair them to SVG, DXF and PDF
Versioned shared memory for Claude Code, Cursor and Codex, with diff and rollback
Runs locallyPersistent project memory and Python verification MCP server for coding agents
Not checked yetSearch, plan and install Wensity React and Tailwind components from your coding agent
Runs locallyGive coding agents the real UIDs, schemas and references of a Strapi project
Runs locally
Check AI-written code for leaked keys and invented packages on your own machine
Not checked yetStart timers and log hours on GitHub issues and pull requests from an assistant
Not checked yetAPI tests in YAML that coding agents write and a 9 MB native binary runs in CI
Runs locallyPublish static sites from an AI agent and get a live link, no account needed
Not checked yetPersistent agent memory, behavior-based code search and bug localization
Runs locally
Hand coding work from Claude Code or Codex to Cursor's CLI agent and review the diff
Runs locally
Hand coding tasks from Claude Code or Cursor to the OpenAI Codex CLI and review the diff
Runs locallyItemize AI coding spend and plan quotas across 40+ tools, from local session files
Runs locallyWrites AGENTS.md, CLAUDE.md and .cursorrules from one project.faf file, locally
Runs locallyRead-only MCP server that shows which git name, email and SSH key a repo will use
Runs locallyShared local Markdown memory for coding agents across Copilot, Cursor and Claude Code
Runs locally