NousResearch /hermes-agent-self-evolution

⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA

★ 5,715⑂ 705👁 51⑃ 167● 36▤ 0
PythonCreated 2026-03-09
More from this author
+9
Daily
5,715
stars
705
forks
51
watchers
167
prs
36
issues
0
releases

README

🧬 Hermes Agent Self-Evolution

Evolutionary self-improvement for Hermes Agent.

Hermes Agent Self-Evolution uses DSPy + GEPA (Genetic-Pareto Prompt Evolution) to automatically evolve and optimize Hermes Agent's skills, tool descriptions, system prompts, and code — producing measurably better versions through reflective evolutionary search.

No GPU training required. Everything operates via API calls — mutating text, evaluating results, and selecting the best variants. ~$2-10 per optimization run.

 How It Works


Read current skill/prompt/tool ──► Generate eval dataset
                                        │
                                        ▼
                                   GEPA Optimizer ◄── Execution traces
                                        │                    ▲
                                        ▼                    │
                                   Candidate variants ──► Evaluate
                                        │
                                   Constraint gates (tests, size limits, benchmarks)
                                        │
                                        ▼
                                   Best variant ──► PR against hermes-agent


GEPA reads execution traces to understand why things fail (not just that they failed), then proposes targeted improvements. ICLR 2026 Oral, MIT licensed.

 Quick Start

bash
 Install
git clone https://github.com/NousResearch/hermes-agent-self-evolution.git
cd hermes-agent-self-evolution
pip install -e ".[dev]"

 Point at your hermes-agent repo
export HERMES_AGENT_REPO=~/.hermes/hermes-agent

 Evolve a skill (synthetic eval data)
python -m evolution.skills.evolve_skill \
    --skill github-code-review \
    --iterations 10 \
    --eval-source synthetic

 Or use real session history from Claude Code, Copilot, and Hermes
python -m evolution.skills.evolve_skill \
    --skill github-code-review \
    --iterations 10 \
    --eval-source sessiondb


 What It Optimizes

| Phase | Target | Engine | Status |
|-------|--------|--------|--------|
| Phase 1 | Skill files (SKILL.md) | DSPy + GEPA | ✅ Implemented |
| Phase 2 | Tool descriptions | DSPy + GEPA | 🔲 Planned |
| Phase 3 | System prompt sections | DSPy + GEPA | 🔲 Planned |
| Phase 4 | Tool implementation code | Darwinian Evolver | 🔲 Planned |
| Phase 5 | Continuous improvement loop | Automated pipeline | 🔲 Planned |

 Engines

| Engine | What It Does | License |
|--------|-------------|---------|
| DSPy + GEPA | Reflective prompt evolution — reads execution traces, proposes targeted mutations | MIT |
| Darwinian Evolver | Code evolution with Git-based organisms | AGPL v3 (external CLI only) |

 Guardrails

Every evolved variant must pass:
1. Full test suite — pytest tests/ -q must pass 100%
2. Size limits — Skills ≤15KB, tool descriptions ≤500 chars
3. Caching compatibility — No mid-conversation changes
4. Semantic preservation — Must not drift from original purpose
5. PR review — All changes go through human r

Top issues

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON