hermes-agent-self-evolution

by NousResearch · Developer Tools

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

New0 ratings5,270 starsActive
Developer ToolsDeveloper ToolPython
GitHub⚑ Report
hermes-agent-self-evolution — image 1

About this project

🧬 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 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 What It…

Technologies

Python

Project health

Recently updated
Last update2 months ago
Contributors3
Latest release
Open issues & PRs122
License
On GitHubsince 2026

GitHub

5,270
stars
626
forks
3
contributors
122
open issues & PRs
Python
language
2 months ago
last commit
View on GitHub ↗

Reviews

out of 5 · 0 ratings
★★★★★
0%
★★★★
0%
★★★
0%
★★
0%
0%
Sign in to write a review
No reviews yet
Be the first to review hermes-agent-self-evolution.

Built by

NousResearch
Imported from GitHub · not yet claimed on GitPalace
View developer pageSign in with GitHub to claim

Maintain NousResearch/hermes-agent-self-evolution? Claiming verifies admin access through your GitHub account and gives you control of this listing.

You might also like