chi v0.2.0

Second release — the autonomous director is now genuinely usable, plus safety and onboarding hardening. Driven by a multi-agent usability audit against real user journeys.

New

• Director self-stop — give it a goal and walk away: "get it under 500µs then stop" (target score) or "don't spend over $5" (cost ceiling); it halts itself.
• Sandboxed eval — run an untrusted candidate's correctness+benchmark inside a jail (eval_sandbox: docker), so a hostile candidate can't reach the host.
• Offline no-key demo — chi run examples/offline.yaml improves a champion with zero API keys (scripted fleet).
• /director and /resume replay — see the rounds a director run completed, from the store.
• NoiseGuard for local noisy evals — median-of-N verification beyond leaderboards.

Fixed

• Director is stoppable — /stop (and a bare "stop") now halt a running director; quitting warns instead of silently killing it.
• Export ships the verified champion, not whatever the coder last wrote (data-integrity fix; every scored candidate is archived by hash).
• Domain-generic brain — the director's research/steering prompts are templated from your problem, not hardcoded to a CUDA kernel.
• A perma-plateau now escalates to research; zero-eval timeouts steer the coder to a smaller edit; query_ledger searches the right tables.

Install: uv tool install getchi then chi. Docs: https://getchi.dev

chi v0.1.0

First public release of chi (χ) — an autoresearch harness.

Point a fleet of heterogeneous coding agents (claude + codex + grok) at any problem with a programmatic evaluator; the autonomous director runs the fleet in rounds, meta-reviews from a SQLite blackboard, researches when stuck, mutates strategies, and improves the answer until you stop it. Ranked leaderboard submissions stay in your hands.

Install: uv tool install getchi then chi.
Docs: https://getchi.dev