gianfrancopiana/openclaw-autoresearch

Registry

Summary

OpenClaw AutoResearch is a TypeScript plugin that enables autonomous experiment loops for the OpenClaw platform, allowing Claude Skill to automatically design, execute, and analyze experiments without manual intervention.

Key features

• Autonomous experiment loop execution
• Seamless integration with OpenClaw platform
• TypeScript-based plugin architecture
• Automated experiment design and analysis

Use cases

• Automated scientific research workflows
• Continuous experimentation in AI model training
• Self-optimizing system testing
• Data-driven hypothesis validation

README excerpt

# openclaw-autoresearch Autonomous experiment loop for any optimization target. Faithful OpenClaw port of [`davebcn87/pi-autoresearch`](https://github.com/davebcn87/pi-autoresearch), including upstream statistical confidence scoring. ## How it works The agent runs a loop: edit code, run a benchmark, measure the result, keep or discard. Each iteration is logged. The loop runs autonomously until interrupted. Three tools drive the loop: | Tool | What it does | |---|---| | `init_experiment` | Configures the session: name, primary metric, unit, direction (lower/higher). Once runs exist, starting a new segment requires `reset: true`, and the prior segment's best result is carried forward into checkpoint context. | | `run_experiment` | Executes a shell command, times it, captures stdout/stderr, parses `METRIC name=number` lines, and opens a pending experiment window that must be logged before another run can start. | | `log_experiment` | Records the pending run. The first logged run in a segment is tagged as the baseline automatically. `keep` auto-commits to git. `discard`/`crash` log without committing, and `discard` now requires an `idea` note that is appended to `autoresearch.ideas.md`. If the prior `run_experiment` captured the primary metric, `log_experiment` can infer `commit` and `metric` automatically. After 3+ runs in a segment, it also reports a confidence score for the best improvement versus noise. | In OpenClaw sessions, the plugin uses the host-provided `workspaceDir` as the normal repo root. Each tool also accepts an optional `cwd` so callers can explicitly target a nested or non-session repo when needed. All state lives in six repo-root files: | File | Purpose | |---|---| | `autoresearch.md` | Session doc. The plugin keeps the Metrics, How to Run, What

Topics

No topics yet.