Commander, your AI coding commander centre for all you ai coding cli agents

the runtime your coding agents live on

⌥ Coding agent with the IDE wired in

Semantic code intelligence MCP server for Claude Code - project maps, symbol search, impact analysis, and more

Like htop, but for AI coding agents. Monitor Claude Code & Codex CLI sessions, tokens, context window, rate limits, and ports in real-time.

All-in-One Desktop Agent Skills Utility. Welcome to the Skill Zoo, where all your skills live!

Universal memory runtime for AI agents

The environment engine for agent worktrees - zero-config dep sync + port/DB/compose isolation

Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.

Find that one coding agent session you want to get back to!

Instant recall for coding agents. Search the history already on your machine. Git blame, but for agent sessions.

Multi-language agent runtime and library for execution scope management, lifecycle events, and middleware on tool and LLM calls.

A terminal that gives AI a body and a living space.

LeanCTX — Context Intelligence for AI systems.

Multi-instance Claude Code manager with intelligent translation proxy. Use Claude Code with Grok, ChatGPT, DeepSeek, Gemini, Kimi, GLM, Ollama and more.

Fast, interruptible verification browser for AI coding agents: 35 ms checks, pixel diffs, live human hand-off

Learn it. Build it. Ship it for others.

AI token usage & quota monitor for the macOS menu bar — native Swift, Liquid Glass, 3D contribution graph. Tracks Claude Code, Codex, Cursor, OpenCode & 25+ agents locally.

Local-first runtime for project-scoped AI coding-agent sessions, with durable state, authority boundaries, and multi-harness interoperability.

A cross-platform desktop app to manage Agent Skills in one place and sync them to multiple AI coding tools’ global skills directories — “Install once, sync everywhere”.

A fast, native RSS reader — plus an agent-facing CLI so your AI agent can read, search and triage your feeds from the shell.

Every file not opened. Every folder not explored. Tokens saved. ProjectAtlas guides coding agents with purpose metadata and an intelligent code graph, reducing token costs by over 90%.

Local-first MCP gateway. One port for every tool and every AI client: lazy discovery (~90% token savings), tool integrity + quarantine, secrets in the OS keychain.

Ultra-fast token & cost tracker for LLM Token Usage (e.g. Claude Code)