Discover and explore top open-source AI tools and projects—updated daily.
evo-hqCode optimization via autonomous experimentation
New!
Top 61.8% on SourcePulse
Evo is an open-source plugin for Claude Code and Codex designed to automate code optimization. It transforms a codebase into an autoresearch loop, enabling developers to discover relevant metrics, instrument benchmarks, and iteratively improve code performance through parallel experimentation. It targets developers seeking automated performance tuning.
How It Works
Evo uses a novel tree search over greedy hill-climbing, enabling broader optimization exploration. It spawns multiple parallel subagents, each operating within its own git worktree, to concurrently test hypotheses and iterate on code improvements. A shared state mechanism ensures all agents benefit from collective learnings, while a gating system can automatically discard experiments failing predefined regression tests or safety checks. This parallel approach accelerates discovery of optimal code configurations.
Quick Start & Requirements
uv package manager./plugin install evo-hq/evo.uv tool install evo-hq-cli or pipx install evo-hq-cli), then add plugin via marketplace (codex marketplace add evo-hq/evo). Requires Codex 0.121.0-alpha.2+./evo:discover or $evo discover. Launch optimization with /evo:optimize or $evo optimize, configurable via subagents, budget, and stall parameters.evo:discover or evo init, providing live monitoring via a local URL (e.g., http://127.0.0.1:8080).uv run --project /path/to/evo evo status.Highlighted Details
Maintenance & Community
No specific details regarding maintainers, community channels (e.g., Discord, Slack), or a public roadmap are provided in the README.
Licensing & Compatibility
Limitations & Caveats
Distributed evaluation via Harbor is a listed TODO, implying current benchmarks run locally. The effectiveness is dependent on the underlying LLM's ability to generate relevant hypotheses and code modifications.
18 hours ago
Inactive
microsoft
uditgoenka
smallcloudai
algorithmicsuperintelligence