中文
~/home / Python / GitHub
GitHub · Python

evo

evo is a skill AI agent for Automatically detect performance issues in code and iteratively optimize them through self-directed benchmarking and agent-driven search without human intervention. Pricing: not stated on the product page. As of 2026-10-28, KanonAgent records 1.5k upvotes. First indexed by KanonAgent on 2026-07-24.
An autonomous system that turns a codebase into a self-improving loop, automatically identifying performance bottlenecks, adding benchmarks, and running parallel agent-based optimizations.
1.5k upvotes
Tracked by Kanon since Jul 24, 2026
no signal yet
status
44/100
momentum · conf 0.92
66d
tracked since 2026-08-22
6
evidence records

No signal event on file yet — status is unknown, not "quiet".

📈 Timelinewhat changed, and when
🔎 Known / Unknown 15 of 23 fields unknown
Machine-callable— unknown —
Open source1 verified 1 quote(s)
Self-hostable— unknown —
Bring your own key— unknown —
Autonomy level4 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.

🤖 Agent teardown · skill
Job to be doneAutomatically detect performance issues in code and iteratively optimize them through self-directed benchmarking and agent-driven search without human intervention.
AutonomyL4 · long-running & self-correcting(evidence: "Spawn multiple subagents and run them simultaneously, each i…")
Who it is forEngineering teams and technical leads
Prerequisitesopen source
Traction · why it is rising1349 on Product Hunt
Why it matters

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
Python
Signal source: GitHub
Visit official site →
📛 Official badgefor your site / README
evo badge
Building evo? Pick a style above — the embed code updates live. Deep color control via URL params: bg= / fg= / accent= (hex). It links back to this page.
Share on X
On mobile tap Share for WeChat / RED (Xiaohongshu) / X; on desktop use Copy text and paste into the app.

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: Stealth Venture, taste-skill, open-design, deer-flow, ruflo, career-ops.

evo alternatives — similar AI agents

Stealth Venturetaste-skillopen-designdeer-flowruflocareer-ops

Where this fits — browse the same shelf

AI Agent Skills & Plugins