Back to directory

Chimera

An open-source, self-hostable AI agent that asks several models the same hard question and blends their answers, then plans, uses tools and checks its own work on longer tasks, remembering what works across sessions.

Chimera

Chimera is an autonomous AI agent that, for difficult questions, queries several language models at once, has one model compare their answers, and has a final model write a combined response, rather than relying on a single model's answer. Beyond conversation it can be given a goal and will plan the work, use tools, edit files, run tests, and undo a change if it breaks something rather than leaving a partial edit in place.

It remembers user preferences and facts across conversations and can turn a repeated task into a reusable skill, though the project is explicit that measurable improvement from this accumulated learning is not yet proven. It can run as a chat bot on messaging apps or deployed on a server around the clock, is Apache-2.0 licensed, and the authors describe it as alpha quality with a large automated test suite but not yet battle-hardened in production.

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.