NousResearch/hermes-agent-self-evolution
Automated agent self-improvement system using evolutionary search and genetic Pareto optimization to evolve prompts, skills, and code.
Velocity · 7d
+12
★ / day
Trend
↘cooling
star history
Hermes Agent Self-Evolution applies DSPy and GEPA (Genetic-Pareto Prompt Evolution) to iteratively improve AI agent capabilities by generating candidate variants, evaluating execution traces, and selecting optimal improvements. The system operates purely via API calls without GPU training, analyzing why tasks fail rather than just detecting failures. It supports synthetic evaluation data generation or real session history from Claude Code, Copilot, and Hermes, then generates pull requests against the target agent repository.
Frequently asked
- What is NousResearch/hermes-agent-self-evolution?
- Automated agent self-improvement system using evolutionary search and genetic Pareto optimization to evolve prompts, skills, and code.
- Is hermes-agent-self-evolution open source?
- Yes — NousResearch/hermes-agent-self-evolution is an open-source project tracked on heatdrop.
- What language is hermes-agent-self-evolution written in?
- NousResearch/hermes-agent-self-evolution is primarily written in Python.
- How popular is hermes-agent-self-evolution?
- NousResearch/hermes-agent-self-evolution has 4.8k stars on GitHub and is currently cooling off.
- Where can I find hermes-agent-self-evolution?
- NousResearch/hermes-agent-self-evolution is on GitHub at https://github.com/NousResearch/hermes-agent-self-evolution.