by gepa-ai · Agent Tool · ★ 7.4k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
pip install gepa
pip install git+https://github.com/gepa-ai/gepa.git
Taken from the project's README on GitHub. Check the security audit before running it.
None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 7,359 |
| Forks | 615 |
| Language | Jupyter Notebook |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 66/100 |
| Open Issues | 162 |
| Last Updated | 2026-11-09 |
| Created | 2025-08-05 |
| Est. Tokens | ~26k |
Optimize any text parameter — prompts, code, agent architectures, configurations — using LLM-based reflection and Pareto-efficient evolutionary search. Website  |  Quick Start  |  Paper  |  Blog  |  Discord <a href="https://join.slack.com/t/gepa-ai/sharedinvite/zt-3o3
These tools work well together with gepa for enhanced workflows:
Looking for a gepa alternative? If you're comparing gepa with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, sessio
Multi-Agent Harness for Production AI
DeepBot is a system-level AI assistant built for both personal productivity and enterprise workflows — one-cli
turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then run
410 Claude Code skills & agent skills & plugins (120+ Agents, custom commands, 410+ skills, customizable refer
How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: