RSIHub

Build agents that improve — and keep the evidence.

RSIHub is a file-based framework for running agent-evolution experiments without rebuilding candidate snapshots, evaluation, lineage, and reporting for every method. It provides composable recipes inspired by A-Evolve, AHE, GEPA, Hill Climb, and HyperAgents.

Start here

Run an experiment

Step	Guide
1. Install RSIHub and verify the local setup	Getting started
2. Configure credentials and the host runtime	Environment Variables
3. Initialize a workspace and launch an experiment	From recipe to experiment
4. Check, monitor, and recover a real run	Running RSIHub reliably

Build your own method

Goal	Guide
Compose a custom experiment configuration	Creating a custom recipe
Choose stages and built-in operators	Operator overview
Configure the editing agent and isolation model	Mutate operator execution
Run trusted local tasks without Docker isolation	Local Harbor environment

For the framework model and vocabulary, see Framework design and Terminology.

What RSIHub keeps fixed

Each experiment is a separate Git repository. Generation tags identify exact candidates, archive.jsonl records stamped outcomes, and the evaluator stays outside the candidate's mutable surface.

The mechanism enforces three core rules:

1. Scores and statuses are written by the mechanism, not workspace operators.
2. Canonical evaluation runs on clean candidate snapshots against a frozen evaluator.
3. Reports are recomputed from stamped archive records rather than mutable operator claims.

See the design guide for the complete model and invariants.

Repository resources

• Supported recipes
• Source architecture map
• Contributing guide
• GitHub repository

For AI agents

Reading this site from an LLM or coding agent? Fetch llms.txt — a machine-friendly index of this documentation with links to the raw Markdown sources — and AGENTS.md for repository working instructions and the test policy.