
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

Open-source terminal agent for Gemini Code Assist workflows on Google Cloud

Compresses tool outputs, logs and chat history before they reach an LLM to cut input
Not checked yet
Gateway that trims context, remembers sessions and enforces rules for coding agents
Coordination layer that warns when parallel coding agents plan conflicting changes
Runs locallyMCP 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 locallyRemote 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 yetMCP server for starting and prompting coding-agent sessions inside a Codeman dashboard
Runs locallyMCP server serving the GodPrompt coding workflow: task routing, gates and protocols
Not checked yetMeasures where an agent session's tokens and cost go, and trims context safely
Runs locallyShared memory for coding agents: proven fixes, known mistakes, skills and MCP discovery
Runs locally
Hand coding tasks from Claude Code or Cursor to the OpenAI Codex CLI and review the diff
Runs locallySee where your coding agent's tokens and money went, with cache-safe fixes
Runs locallyShared mailbox, handoffs and file-clash warnings for your coding agents
Runs locallyLocal runtime for routing work between Claude Code, Codex, Cursor and other coding agents
Runs locallyServe 112 bilingual SDLC prompts to coding agents, each with an autonomy contract
Runs locallyFocused repo context for Claude Code and Codex, with a token receipt for every request
Runs locallyLocal control plane that routes coding work across Claude Code, Codex, Cursor and OpenCode
Runs locallyLocal project memory for coding agents that suggests paths and flags stalled work
Runs locallyLocal MCP node where two coding agent sessions compare what they agree on
Not checked yetDelegate tasks to Claude Code, Codex or Antigravity coding agents from any MCP client
Runs locallyLet Claude Code, Codex, Grok and Antigravity review each other's work
Runs locallyCalibrated yes/no and multiple-choice odds that help coding agents decide ask or act
Runs locallyDelegate coding tasks from Claude Code or Codex to a local DeepSeek Harness
Runs locallyMCP and proxy that compresses coding-agent context before it reaches the model
Not checked yetVerified rankings of AI coding-agent harnesses with local setup recommendations
Runs locallyPersistent memory, code map, undo and fact checking for AI coding agents
Runs locally