Autoresearch

Turn Claude Code, OpenCode, or OpenAI Codex into a relentless improvement engine.

Based on Karpathy's autoresearch — constraint + mechanical metric + autonomous iteration = compounding gains.

"Set the GOAL → The agent runs the LOOP → You wake up to results"

You don't need AGI. You need a goal, a metric, and a loop that never quits.

Supports Claude Code, OpenCode, and OpenAI Codex for the core skill, bundled runtime, installation, and verification surface. Hook guardrails are Claude Code-only.

v2.2.0 — Autonomous Orchestrator: Type a plain-language goal to /autoresearch and it classifies your goal, derives a Success predicate, confirms it once, then loops across subcommands until done. No manual chaining required. Metric:/Verify: invocations run the classic loop unchanged. See guide/autoresearch-orchestrator.md.

How It Works · Commands · Quick Start · Guides · FAQ

     PLAN             LOOP            DEBUG             FIX             SECURE            SHIP
 ┌──────────┐     ┌──────────┐     ┌──────────┐     ┌──────────┐     ┌──────────┐     ┌──────────┐
 │   Goal   │     │  Modify  │     │   Find   │     │   Fix    │     │  STRIDE  │     │  Stage   │
 │  Metric  │────▶│  Verify  │────▶│   Bugs   │────▶│  Errors  │────▶│  OWASP   │────▶│  Deploy  │
 │  Scope   │     │Keep/Drop │     │  Trace   │     │  Repair  │     │ Red Team │     │ Release  │
 └──────────┘     └──────────┘     └──────────┘     └──────────┘     └──────────┘     └──────────┘
 /autoresearch:   /autoresearch    /autoresearch:   /autoresearch:   /autoresearch:   /autoresearch:
   plan                              debug            fix              security         ship

 ┌──────────┐     ┌──────────┐     ┌──────────┐     ┌──────────┐
 │  Probe   │     │ Scenario │     │ Predict  │     │  Reason  │
 │ Require- │     │   Edge   │     │ 5-Expert │     │  Debate  │
 │  ments   │     │  Cases   │     │  Swarm   │     │ Converge │
 └──────────┘     └──────────┘     └──────────┘     └──────────┘
 /autoresearch:   /autoresearch:   /autoresearch:   /autoresearch:
   probe            scenario         predict          reason

 ┌──────────┐     ┌──────────┐     ┌──────────┐     ┌──────────┐
 │  Learn   │     │ Improve  │     │   Eval   │     │ Baseline │
 │   Docs   │     │ Research │     │ Analyze  │     │   Diff   │
 │   Gen    │     │   PRDs   │     │ Results  │     │ Verdict  │
 └──────────┘     └──────────┘     └──────────┘     └──────────┘
 /autoresearch:   /autoresearch:   /autoresearch:   /autoresearch:
   learn            improve          evals            regression

Why This Exists

Karpathy's autoresearch demonstrated that a 630-line Python script could autonomously improve ML models overnight — 100 experiments per night — by following simple principles: one metric, constrained scope, fast verification, automatic rollback, git as memory.

Claude Autoresearch generalizes these principles to ANY domain. Not just ML — code, content, marketing, sales, HR, DevOps, or anything with a number you can measure.

v2.1.0 is a major architecture rebuild. The monolithic SKILL.md (813 lines, ~100K tokens per invocation) is replaced with a thin 41-line routing file and 12 self-contained command files (94–120 lines each, ~5–8K tokens per invocation). That is a 95% token reduction with the same capability surface.

How It Works

LOOP (N iterations or until done):
  1. Review current state + git history + results log
  2. Pick the next change (based on what worked, what failed, what's untried)
  3. Make ONE focused change
  4. Git commit (before verification)
  5. Run mechanical verification (tests, benchmarks, scores)
  6. If improved → keep. If worse → git revert. If crashed → fix or skip.
  7. Log the result
  8. Repeat until N iterations complete or goal is met.

Every improvement stacks. Every failure auto-reverts. Progress is logged in TSV format.

The Setup Phase

Before looping, Claude performs a one-time setup:

1. Read context — reads all in-scope files
2. Define goal — extracts or asks for a mechanical metric
3. Define scope — which files can be modified vs read-only
4. Establish baseline — runs verification on current state (iteration #0)
5. Confirm and go — shows setup, then begins the loop

8 Critical Rules

Hooks & Safety

Hooks are defense-in-depth guardrails, not a security sandbox. Claude Code ships the hook surface; OpenCode and Codex ship the core skill/runtime/install surface without hook parity.

What's Protected

Configuration

All hooks are on by default. Disable individually only for troubleshooting:

# Disable a specific hook
export AR_DISABLE_SCOUT_BLOCK=1
export AR_DISABLE_PRIVACY_BLOCK=1
export AR_DISABLE_DANGEROUS_CMD_BLOCK=1
# ... etc for each hook name

Optional webhook for session completion notifications:

export AR_NOTIFY_WEBHOOK=https://hooks.slack.com/services/...

Customize blocked directories with a .ckignore file (gitignore syntax) at your project root.

See guide/hooks.md for full reference.

Release preparation and contributor verification live in scripts/release.md.

Commands

Universal flags: Iterations: N, Iterations: unlimited, --evals, --evals-interval N, --chain <targets>, --<subcommand> shorthand.

All commands use interactive setup when invoked without arguments. Just type the command — the agent asks for what it needs with smart defaults based on your codebase.

OpenCode users: Commands use underscore naming (/autoresearch_debug, /autoresearch_fix, etc.). All 14 commands available.

Codex users: Inv