Skip to content
Chimera
ChimeraAgent

A terminal agent that does real work on its own, and a desktop app to work with it. Open source, runs on your machine, and publishes the benchmarks where it lost.

Many minds, one answer

The lion, the goat, the dragon and the snake were on the logo before they were an argument. A panel of models answers, a judge names where they agree and where they do not, and a synthesiser writes the result — but only when the question is hard enough to be worth it. Fusion itself is not unique; wiring it into the agent loop behind a cost-aware router, and measuring it, is.

Three bets, and where each one stands

  • Evolution with a fitness signal

    Other agents learn by appending what happened. Chimera keeps a learned change only when a verified result proves it helped — gated on the real working-tree diff and an honest A/B, never on what the model says about itself. Whether that accumulation makes it better at new tasks is measured, and the answer so far is on the evidence page.

  • Security as architecture

    Prompt injection is widely considered unpatchable, and most agents mitigate it in the application layer or declare it out of scope. There is a real defence layer here — taint tracking, control tokens stripped from untrusted content, dangerous tools narrowed for the rest of a tainted run, side-effecting retries protected — and it is opt-in and off by default, which the security page states before it states anything else.

  • Benchmarks published, including the losses

    Every figure comes with a confidence interval, the runs that went nowhere are published unchanged, and a claim that stops surviving replication is withdrawn. Nothing on this site is typed by hand; it is read from the snapshot the product stamps at each release.

What is actually measured

+23ppMeasured on our own Docker-free suite, graded by pytest — one model, small self-contained Python tasks. This is not SWE-bench, and it does not generalise to real repositories.
+9.8ppA deliberately easy, single-repo slice of SWE-bench Verified. This is not a SWE-bench Verified score — a real one needs the full 500 instances. The delta is not significant on its own.

See every number, with its caveats

Two products

It is alpha, and it says so

Solid and heavily tested, not yet battle-hardened in production. The installers are not signed by a certificate authority, so Windows and macOS warn on first run. Both of those are on the download page too, before the button.