Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Most developers + AI researchers building self-modifying coding agents today have been either (a) hand-rolling a custom self-modifying pipeline (custom AST mutation + custom test runner + custom git automation + custom memory synthesis -- high maintenance burden, no public history), (b) adopting closed-source agent frameworks (Devin, Factory) that lock-in the user's tool choices and provide no ins
Who should use it
Who should skip it
Consider yoyo-evolve: MIT Self-Evolving Coding Agent (200 Lines Rust on Day One, 115,000+ Lines After 128 Days of Agent-Written + Tests-Gated Commits) lower priority if you already have a working solution in this category.
About this signal
yoyo-evolve: MIT Self-Evolving Coding Agent (200 Lines Rust on Day One, 115,000+ Lines After 128 Days of Agent-Written + Tests-Gated Commits) is tracked by RepoRadar as a tool in the Radar section. It was first seen on 2026-07-08 and last updated on 2026-07-08. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. Across RepoRadar's eight signals, yoyo-evolve: MIT Self-Evolving Coding Agent (200 Lines Rust on Day One, 115,000+ Lines After 128 Days of Agent-Written + Tests-Gated Commits) is strongest on novelty (9.0) and workflow potential (8.7) and weakest on maturity (6.3) — a profile worth weighing against your own priorities. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.
How this item is evaluated
RepoRadar assigned yoyo-evolve: MIT Self-Evolving Coding Agent (200 Lines Rust on Day One, 115,000+ Lines After 128 Days of Agent-Written + Tests-Gated Commits) a composite score of 8.0 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 0.0 and never affects the composite score or tier. The risk label of 'low' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
The 1; 836* / 122-fork / 22-subscriber repo is at active maintenance but the consumer SHOULD note the self-evolution loop is autonomous -- the consumer SHOULD review the GitHub Actions workflow configuration (evolve.yml) and the journal to understand the current evolution schedule before relying on the agent; the consumer SHOULD note the social session pattern is autonomous -- the consumer SHOULD review the GitHub Actions workflow configuration (social.yml) and the active social learnings to understand the current social schedule before relying on the agent; the consumer SHOULD note the daily synthesis job is autonomous -- the consumer SHOULD review the synthesis job output (active context files) before relying on the agent's memory.