Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for AI coding-agent users and research engineers who want to optimize a real codebase against a measurable signal (latency, accuracy, test coverage, eval score) without hand-tuning a custom evolutionary loop, because gepa-research wraps the upstream GEPA optimizer behind a per-host plugin (Claude Code, Codex, OpenClaw, Hermes) and a discover-then-optimize flow that drops candidates into per
Who should use it
Who should skip it
Skip CyrusNuevoDia/gepa-research if the source link, documentation, or setup requirements do not align with your current workflow or stack.
About this signal
CyrusNuevoDia/gepa-research is tracked by RepoRadar as a coding agent plugin 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 Gold tier and moderate setup difficulty. Across RepoRadar's eight signals, CyrusNuevoDia/gepa-research is strongest on workflow potential (9.5) and novelty (9.0) 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 CyrusNuevoDia/gepa-research 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 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
Each GEPA candidate is applied in an isolated git worktree and gate-checked, but the gate is whatever the user wires up — confirm the regression tests / safety checks are exhaustive enough for the codebase you point it at before you trust the loop to run unattended; The inner loop calls the underlying LLM repeatedly with rich side-info; budget accordingly — the documented default `max-metric-calls=50` is a starting point, not a guarantee, and per-candidate side-info can be large for code-heavy repos.