Back to directory

all-your-agents

An event-driven, harness-neutral API and command-line tool that watches every coding agent running on a machine and lets a developer inspect the sessions, subagents and tool calls they leave behind, without polling.

all-your-agents

all-your-agents watches every coding agent running on a machine and lets a developer inspect the live and historical sessions they leave behind, across harnesses including Claude Code, Grok, Codex, a project called omp, and others. It works entirely by watching the files each harness already writes and the processes that write them, coalescing bursts of activity per path rather than polling on a timer.

Because each harness records its own state differently, the project documents specific compatibility quirks per tool, such as which harnesses fail to persist an approval request so a session blocked on approval reads as merely running, which tools need a bundled SQLite reader for their first-turn history, and how a session is distinguished as live, running headless, or found only in history. It is used as a library, imported into a Node.js or TypeScript project, with an event-based API and no built-in polling.

More in Coding agents

See all 793
  • The City

    github.com

    A native macOS app that shows Claude Code runs as a city, with each project as a building, each team as a floor of robots, and every animation driven by a real event from the claude CLI's stream.

  • rig

    tryrig.ai

    A small, single-binary agent runtime that points at any OpenAI-compatible model, local or hosted, reads and edits a repository's code, runs its tests and remembers what it learned, with a loop implemented in a few hundred lines.

  • Jauvex

    jauvex.reindent.com

    An Electron desktop app that puts Claude Code, Codex and Grok coding-agent sessions side by side and lets you steer them by voice, with a small model handling fast routing decisions.