Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
Autoresearch enables AI research engineers to run measured experiment loops within Claude Code or Codex. It automates the cycle of applying a scoped change, measuring it against a benchmark, and recording the outcome to iteratively optimize performance.
The system operates within defined budgets and user authorizations, allowing researchers to pause, resume, or inspect the progress of an optimization loop while maintaining manual control over scope changes.
WHO IT'S FOR
AI research engineers
running autonomous experiment loops for optimization
ML performance engineers
measuring scoped changes against fixed benchmarks
Claude Code power users
automating iterative code optimization tasks
Automation engineers
configuring unattended optimization loops via Python
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Installs: Loads the autoresearch Claude Code plugin for the current session, including its shared skill and registered Claude hooks. Use this instead of the manual Claude installation to avoid duplicate hooks. · Claude Code
Before you start
Python 3.10+
Bash
Git
Claude Code client
A local checkout of the repository
Linux or macOS; use WSL on Windows
Platform: Linux and macOS; WSL on Windows
In a terminal, start Claude Code with the session-local plugin. Replace `/absolute/path/to/autoresearch-claude-code` with the absolute path to the existing repository checkout while preserving the rest of the command.
claude --plugin-dir /absolute/path/to/autoresearch-claude-code