Algorithm inventory
The runner registry contains 13 methods. The resource and selection columns describe their FlashRSI implementations. Each guide documents configuration and any differences from upstream.
| Method | Editable resource | Feedback and selection | Worker |
|---|---|---|---|
| OPRO | Instruction | Rank accumulated candidates by train score and return the best. | Text proposal |
| GEPA | Instruction | Reflect on trajectories and use per-task scores to guide candidate search. | Text proposal |
| EvoPrompt | Instruction | Evolve a population with GA or DE and select using dev scores. | Text proposal |
| ACE | Prompt / playbook | Build and revise a playbook from feedback and reflections. | Text proposal |
| SkillOpt | Skills | Combine fast and slow updates and adopt strict dev gains. | Text proposal |
| Evo-Harness | Native directory skills | Compile training failures into topic and general skills and retain valid updates. | File editing |
| AHE | Harness resources | Diagnose train traces, evaluate each valid edit, and retain it for the next step. | File editing |
| ADAS | Harness resources | Archive measured designs and select the best dev candidate. | File editing |
| DarwinX | Harness resources | Screen and confirm branches, then evaluate complementary recombinations. | File editing |
| Meta-Harness | Harness resources | Use historical sources, traces, and scores to propose edits and select on dev. | File editing |
| ModularRSI | Declared modules | Evolve module branches and integrate them through review and execution gates. | File editing |
| RRSI | Harness resources | Diagnose recurring failures and admit revisions using score and cost gates. | File editing |
| Arbor | Harness resources | Explore a hypothesis tree and synthesize findings from measured branches. | File editing |
Text proposals use worker.ask() and can come from an LLM Worker or an Agent Worker. File editing requires an Agent Worker with edit() support. Each Target must expose the resources and runtime capabilities required by the method. See algorithm configurations and harness capabilities.