#codex

Smart AI proxy router that connects Claude Code, Cursor, Codex, Copilot, and 50+ coding tools to 40+ AI providers with 100+ models. Saves 20-40% tokens via RTK compression, auto-fallback from subscription to cheap to free providers, multi-account round-robin, and a local dashboard.

A simple mobile-focused chat app to talk to an agent via the ACP protocol

Multi-provider coding-agent orchestration in a verified loop: a critic on a different model signs off before work ships. Claude Code, Codex, Gemini, aider, Copilot, opencode, local.

Coverage, security and code quality for coding agents

Architecture diagrams that actually run, generated by AI agents

No repository description published.

Terminal dashboard for Claude Code usage and costs

Remotely view and control local Claude Code / Codex terminal sessions on a mobile device.

Prompt refinement and workflow orchestration for Codex: turn vague ideas into scoped goals, reviewable SPECs, validation evidence, and PR-ready handoffs.

MCP bridge that drives four coding CLIs — Google's Antigravity (agy), OpenAI Codex, GitHub Copilot, and Cursor — as sub-agents inside Claude Code. Text answers, image generation, real repo work, and parallel swarms, on quota you already pay for.

Self-hosted AI agent harness in a single Go binary — writes, sandbox-tests and repairs its own tools, and lets Claude Code, Codex and any MCP client build and share them.

Go library for driving AI coding CLIs in headless mode.

MCP for Ultralytics Platform workflows, datasets, training, prediction, and model operations.

Real-time dashboard for monitoring Claude Code, Codex, and other AI coding agents—with animated 3D robots, live terminals, tool activity, prompt queues, and session resume.

Find out what your coding agents already know. Docmancer indexes the memory, rules, and instructions Claude Code, Codex, Cursor, and Gemini wrote on your machine, then carries the durable parts to every agent. It is local-first and under MIT license.

Keep Claude Code and Codex aligned with task requirements through intent proof, drift checks, visible run state, and evidence-based verification.

Keeping your agents out of trouble with sandboxed coding agent automation

AI assisted code review with a human in the loop

Run Claude Code, Codex, Copilot, Cursor, and Grok CLIs in parallel — approve every session from one browser tab, even from your phone.

Cross-harness AI skill portability CLI. Author an agent skill once, sync it into Claude Code, Cursor, Copilot, Codex, OpenCode & 45+ AI coding agents. Safety scanner, content-hash drift detection. A package manager / dotfiles for AI coding agent skills.

Terminal dashboard for monitoring OpenRouter and Codex API usage in real time

Let AI agents share your everyday, logged-in Chrome through a Skill + CLI — locally or across multiple machines.

No repository description published.

Transform legacy systems into executable specifications for AI coding agents

One binary that organizes your AI coding CLIs — update them all, watch every quota plan, schedule the maintenance.

Session viewer for coding agents — browse, search, trace, and export Claude Code, Codex, and Grok conversations

Unified audit logging, policy enforcement, and sanitization for VMware MCP skills

Give your AI a memory, habits, and a daily routine — with nothing but files. One-line setup for Claude Code and Codex CLI.

Self-hosted remote approvals + live monitoring for Claude Code / Codex — via Telegram, Feishu, or a web terminal. Any subscription or API key.

One command flips Claude Code, Codex, Gemini CLI or Antigravity between your work and personal accounts - no re-login, no browser, no tokens copied. Each account keeps its own permanent home, so switching can never log the other one out. The switch itself never touches the network.