All projects

jev-harness

TypeSafeAI/jev-harness

A custom coding harness for TypeSafe AI's Jev: an LLM proposes, Jev answers narrow questions, code decides, every step leaves a receipt.

TypeScript
Stars
39
Forks
12

Why it is listed

An independent community research-stage proposal-review contract: an LLM proposes an action, Jev answers narrow questions, and the host retains execution and authorization. Its offline benchmark uses scripted mock results, not measurements of Jev; it is not an official TypeSafe SDK or a production agent runtime.

Related projects

  • dsh-jev-interceptor

    ⚡ Millisecond System-1 judgement for every tool call in DeepSeek Harness — Jev-powered risk classification & evidence-gated auto-approval. Fail-closed by construction. dsh 生态第一个 System-1 决策插件

    Shared topics: agent-harness, ai-agents, ai-safety

  • agent-fastpath

    Jev MCP server: a decision layer for coding agents, built on TypeSafe Jev (System One model). Ship gates, risk checks, file triage that keeps files out of context, and a safe headless browser, with calibrated confidence. For Claude Code, Codex, Cursor.

    Shared topics: ai-agents, coding-agent

  • openharness

    Follow your curiosity. Build across disciplines. Open-source software and hardware for polymaths in the making.

    Shared topics: agent-harness, ai-agents