penguin-harness
π§ Harness for RSI. Let AI Build AI. Multi-Agent Auto-Dev Platform. Everything is Transparent.
Install one, then just prompt in plain English. The FLOW.md fires the right skill at the right moment. No re-orchestration, no babysitting.
Featured
π§ Harness for RSI. Let AI Build AI. Multi-Agent Auto-Dev Platform. Everything is Transparent.
Run one specified Test Agent on one specified Benchmark Case exactly once, privately score that execution, and return one protocol result.
Initialize an Agent's settings from a user requirement by writing AGENTS.md, setting identity metadata, and installing only needed Skills.
Improve an Agent State through versioned scores and score-linked Traces from a frozen Benchmark.
Design and calibrate a multi-Case capability Benchmark and establish a traceable Formal Baseline.
Create and edit Bento presentations β self-contained .bento.html decks whose document is JSON. Use whenever the user wants a slide deck or presentation: fromβ¦
Run a PenguinHarness organization as its CEO β turn the mission into a ticket tree, hire HR and finance first, partition the shared workspace, schedule theβ¦
Β© 2026 Flowy Β· Free and open source
Built for Claude Code Β· Not affiliated with Anthropic