
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

Gateway that trims context, remembers sessions and enforces rules for coding agents
MCP server that tells a coding agent which AI model to call and what to connect
Checks OpenAI, Anthropic and Google model IDs for retirement dates before agents use them
Runs locallyCheck SWE-bench tasks for leaked fixes: tier, quoted evidence and fix-commit date
Remote MCP server for building and calling small task-specific models from an agent
Plan and run drills that test AI agents against synthetic users and cloud worlds
Not checked yetShared memory for coding agents: proven fixes, known mistakes, skills and MCP discovery
Runs locallyGive coding agents a read-only library of current AI papers, models and tools
Not checked yetLet an AI client check on, message and read output from your AgentX coding-agent fleet
Not checked yetRead-only MCP catalog of prompt packs and rule files for Cursor, CLAUDE.md and AGENTS.md
Not checked yetFocused repo context for Claude Code and Codex, with a token receipt for every request
Runs locallySeat your own AI in a Bordet boardroom: ask members, search memory and log decisions
Not checked yetMCP and proxy that compresses coding-agent context before it reaches the model
Not checked yetPersistent memory, code map, undo and fact checking for AI coding agents
Runs locallyLocal repo context bundles and evidence for AI coding agents before and after a task
Runs locallySession memory for coding agents with local-first recall and on-device model routing
Runs locally