Status basis: github_stars gained 5 in the last 3d vs 3 in the 3d before (ratio 1.7x, threshold 1.5x)
- Accelerating github_stars gained 5 in the last 3d vs 3 in the 3d before (ratio 1.7x, threshold 1.5x)
- Accelerating github_stars gained 8 in the last 3d vs 2 in the 3d before (ratio 4.0x, threshold 1.5x)
- Accelerating github_stars gained 5 in the last 3d vs 3 in the 3d before (ratio 1.7x, threshold 1.5x)
- Accelerating github_stars gained 5 in the last 3d vs 3 in the 3d before (ratio 1.7x, threshold 1.5x)
- Accelerating github_stars gained 7 in the last 3d vs 4 in the 3d before (ratio 1.8x, threshold 1.5x)
- first observed Kanon started keeping permanent history for this agent
| Machine-callable | — | unknown | — |
| Open source | 1 | verified | 1 quote(s) |
| Self-hostable | — | unknown | — |
| Bring your own key | — | unknown | — |
| Autonomy level | 4 | inferred | 4 quote(s) |
| Pricing model | — | unknown | — |
| Integrations | — | unknown | — |
“Unknown” means we have not verified it — it is not a “no”. Hard filters never treat unknown as false.
It pioneers a closed-loop, self-researching approach to code optimization, marking a significant step toward AI-driven, continuous performance engineering.
Evidence quotesverbatim, from the product’s own materials
“public GitHub repository (README fetched)”— structural
“Spawn multiple subagents and run them simultaneously, each in its own git worktree”— readme
“Tree search over greedy hill climb. Multiple directions can fork”— readme
“trying things, keeping what improves the score, throwing away what doesn't”— readme
“runs experiments in a loop -- trying things, keeping what improves”— readme
“A plugin for your agentic framework that optimizes code through experiments”— readme
FAQ
What is evo?
An autonomous system that turns a codebase into a self-improving loop, automatically identifying performance bottlenecks, adding benchmarks, and running parallel agent-based optimizations.
What does evo do?
Automatically detect performance issues in code and iteratively optimize them through self-directed benchmarking and agent-driven search without human intervention.
Why does evo matter?
It pioneers a closed-loop, self-researching approach to code optimization, marking a significant step toward AI-driven, continuous performance engineering.
Is evo open source?
Yes — evo is open source.
How popular is evo?
As tracked by KanonAgent: 1.5k upvotes (first indexed 2026-07-24).
What are the best evo alternatives?
Similar AI agents tracked by KanonAgent: open-design, deer-flow, Agent-Reach, ruflo, career-ops, cherry-studio.