
Skills, hooks, memory and security layer for coding agent harnesses
- Freemium
- Open-source agent
- 306K 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
MCP server that lets AI coding agents on one machine discover and message each other
Runs locallyStores every fix your coding agent makes and brings it back when the problem returns
Runs locallyShared context and file queues so coding agents on one team stop overwriting each other
Runs locallyPersistent project memory and Python verification MCP server for coding agents
Not checked yet
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 locallyShared local Markdown memory for coding agents across Copilot, Cursor and Claude Code
Runs locallyMCP server and CLI giving coding agents version-matched docs and a dependency check
Runs locally
Compiler-built code map of calls, data flow and class hierarchy for coding agents
Runs locallyProject-aware code-quality rules, findings, safe fixes and gate results for coding agents
Runs locallyLocal MCP server exposing Copado DevOps and Salesforce release tasks to AI coding agents
Runs locallyQuery your team's AI coding-agent session history and apply fix recommendations
Not checked yetLocal code graph that shows coding agents what a change breaks before they edit
Runs locally
Ask Bluebox about live production health, errors and investigations from your coding agent
Not checked yetPlan review gate for Claude Code and Cursor teams; builds wait for a teammate's approval
Runs locallyLocal orchestrator that drives your coding agent from spec to merge request with human
Runs locallyLocal repo index with call graphs, git history and durable memory for coding agents
Runs locallyTypeScript inferred types, completions and errors for AI coding agents
Runs locallyPersistent encrypted project memory and a team of AI personas for Claude Code
Not checked yet