GEPA 알고리즘(Genetic-Pareto LLM-driven search)을 사용하여 코드를 최적화하는 에이전트 프레임 워크의 플러그인입니다. 현재 Claude Code, Codex, OpenClaw 및 Hermes에 지원됩니다.

코드베이스를 제공합니다. 그것은 최적화하는 메트릭을 발견하고 평가를 설정하고, GEPA에 대한 검색을 손 – 후보자의 파레토 국경을 유지하고 진단 피드백에서 대상 개선을 제안하는 LLM을 사용합니다.

• GEPA 백업 검색. 최적화 내부 루프는 gepa.optimize_anything: LLM 구동 반사 풍부한 측 정보, Pareto-efficient 후보 선택 및 자동 인장 / 판자 처리.
• Per-candidate git worktrees. 모든 후보자 GEPA 제안은 격리 된 워크 트리에 적용되며 게이트 통과 – 전체 감사 트레일, 안전한 롤백.
• Gating. 회귀 시험 또는 안전 검사는 문으로 위로 타전될 수 있습니다. 게이트 점수가 0.0을 실패하고 버려지는 후보.
• **Observability. ** 로컬 대시보드는 후보 선량 DAG ([T1]]) 및 per-task 추적을 렌더링합니다.
• **Benchmark 발견.

GEPAResearch

A plugin for your agentic framework that optimizes code using the GEPA algorithm (Genetic-Pareto LLM-driven search). Currently supported on Claude Code, Codex, OpenClaw, and Hermes.

You give it a codebase. It discovers metrics to optimize, sets up the evaluation, and hands the search to GEPA – a reflection-driven evolutionary optimizer that maintains a Pareto frontier of candidates and uses an LLM to propose targeted improvements from diagnostic feedback.

• GEPA-backed search. The optimization inner loop is gepa.optimize_anything: LLM-driven reflection over rich side-info, Pareto-efficient candidate selection, and automatic stall/budget handling.
• Per-candidate git worktrees. Every candidate GEPA proposes is applied in an isolated worktree and committed if it passes gates – full audit trail, safe rollback.
• Gating. Regression tests or safety checks can be wired up as a gate. Candidates that fail the gate score 0.0 and are discarded.
• Observability. A local dashboard renders the candidate lineage DAG (from GEPAResult.parents) and per-task traces.
• Benchmark discovery. The discover skill explores the repo, figures out what to measure, and instruments the evaluation.

Install

Common: git, uv, Python 3.10+.

1. Install the gepa-research CLI (non-Claude Code hosts)

Claude Code bundles its own copy. Every other host calls gepa-research as an external binary. The CLI is not published to PyPI – install it directly from this GitHub repo (the package lives in the plugins/gepa-research/ subdirectory):

uv tool install "git+https://github.com/CyrusNuevoDia/gepa-research#subdirectory=plugins/gepa-research"
# or: pipx install "git+https://github.com/CyrusNuevoDia/gepa-research#subdirectory=plugins/gepa-research"
gepa-research --version              # gepa-research-cli 0.2.2

To pin a release, append @ to the repo URL (e.g. [email protected]#subdirectory=...).

2. Add the plugin

Claude Code

/plugin marketplace add CyrusNuevoDia/gepa-research
/plugin install gepa-research@CyrusNuevoDia-gepa-research

Invoke: /gepa-research:discover, /gepa-research:optimize.

Codex (requires 0.121.0-alpha.2 or newer – npm install -g @openai/codex@alpha if you’re on 0.120.0 stable)

codex marketplace add CyrusNuevoDia/gepa-research

Then /plugins → gepa-research → install. Invoke: $gepa-research discover, $gepa-research optimize.

OpenClaw

openclaw plugins install gepa-research --marketplace https://github.com/CyrusNuevoDia/gepa-research

Invoke: /discover, /optimize.