Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for research engineers and AI coding-agent users who want to push a hard algorithmic-discovery task (designing algorithms, improving code, solving a math problem) past a static performance ceiling, because EvE is the published reference implementation of the NUS Scaling Group's arXiv 2605.09018 paper and is the only open-source framework that ties a synchronous race + empirical Elo update l
Who should use it
Who should skip it
Skip scaling-group/eve if the source link, documentation, or setup requirements do not align with your current workflow or stack.
About this signal
scaling-group/eve is tracked by RepoRadar as a research framework in the Coding Agents section. It was first seen on 2026-07-02 and last updated on 2026-07-02. The current verdict is 'try now' with a Silver tier and moderate setup difficulty. scaling-group/eve leads on novelty (10.0) and workflow potential (9.4); its lowest signal is maturity (5.8), so factor that in before investing setup time. 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 scaling-group/eve a composite score of 7.9 out of 10, placing it in the Silver 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 1.0 and never affects the composite score or tier. The risk label of 'none' 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
This is research code from an academic group, not a production-ready product — expect rough edges in error handling, logging, and packaging, and pin a specific commit / tag for any reproducible run; The synchronous race + empirical Elo loop assumes the user's eval scripts produce stable, comparable scores; flaky or non-deterministic scoring will cause the Elo updates to drift and the ensemble to converge on a spurious winner.