System One Harness (SOH)
github.com/harnessrouter/systemoneharness- Category
- AI Agents
- Rank
- No. 2256Tools index
- Pricing
- Open Source
- Type
- TOOL
- GitHub
- 12 stars
- Date
About
System One Harness is a framework that turns a "System One" decision model into an agent loop: it observes an environment, compiles the environment's finite action space into typed questions for the model, gates each decision by a confidence threshold, executes the chosen action, and logs the full decision trace. It makes one model call per step with no free-form generated actions, and currently supports the Jev model from TypeSafe via OpenRouter or TypeSafe's own API.
Why it made the leaderboard
Proposes a decision-model agent loop (one model call per step, no generated control text) that could reduce hallucinated or malformed actions compared to standard code-generation agent loops.
Tags
Tech Stack
Comments (0)
No comments yet
Editorially curated, with community endorsements as a secondary signal. Corrections welcome.