All projects

ego-decision-layer

jiangkoumo/ego-decision-layer

Pluggable decision layer for the ego lite browser: one System One (Jev) call per step replaces the per-step LLM turn, and the backend can be swapped for a local OpenAI-compatible model. Fail-closed execution guards. The measured one — raw bench data, 16 suites, changelog with corrections.

JavaScript
Stars
31
Forks
2

Why it is listed

A pluggable ego lite decision layer using Jev/System One by default to select next actions and indexed elements, while preserving a separate observation and execution layer. Local/other backends are alternatives.

Related projects

  • qc-use

    Test the most important path in your app. Describe it in plain words. Powered by TypeSafe Jev.

    Shared topics: agent-skills, ai-agents, browser-automation

  • wrangle

    Hand one Safari window to a program, and no more than that.

    Shared topics: agent-skills, ai-agents, browser-automation

  • hunch

    ⚡ Browser agent that acts on a hunch: Jev (TypeSafe System One) picks every click in ~150 ms, an LLM is only needed when confidence drops. Zero-dependency Python on top of agent-browser.

    Shared topics: ai-agents, automation, browser-automation