evo
turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.
- Ask Claude to identify performance bottlenecks in your codebase automatically.
- Generate benchmark metrics for code quality without manually defining test criteria.
- Find optimization opportunities by running parallel performance searches across code branches.
Automates discovery of performance bottlenecks and measurement gaps in production codebases, reducing manual profiling effort and enabling data-driven optimization decisions at scale.
Engineering teams managing large or complex systems needing systematic performance analysis without manual benchmark design.
By evo-hq
How to Get It
claude plugins install evo-hq/evo
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Trust Signals Auto-scanned
Community Pulse Emerging
Discussed on Hacker News
- Pre-Startup School Happy Hour at Eventbrite HQ in SF — Hacker News · 4 pts
- Show HN: Evo – parallel autoresearch experiments for Claude Code and Codex — Hacker News · 2 pts
- EventBrite loses data from Make Faire registrations :( — Hacker News · 2 pts
3 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 1,179 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 1,179 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.