Skip to content

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.

RSIHub architecture

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 variants Operator overview
Configure the editing agent and isolation model Meta-agent 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