jev-harness-router

Per-turn router for agent harnesses: one 350ms Jev call picks the model tier, effort, tools and skill, behind a hard deadline with a regex fallback. Claude Agent SDK adapter included.

How it uses Jev

Before a harness spends a second on the real work, it has to answer four questions about the turn in front of it. This asks all four in a single Jev call, in about 350 ms, behind a deadline it is not allowed to miss.

Getting started

Describe your harness with defineCatalog as above and hand it to createRouter . The router is the only thing that needs the key; running the routed turn is your harness's job, on whatever provider it already talks to. createRouter() with no catalogue runs on the shipped example — fine to try it, wrong to ship.

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README · the project website.

Keep exploring

Similar to jev-harness-router

Browse all
jev-go project preview
SDKs & clients
Community Go SDK for TypeSafe AI Jev / System One
jcm-router project preview
Agent tooling
Local proxy that picks the Claude model and effort per message using TypeSafe Jev. Routes subagents, leaves your cached main chat alone.
codex-jev-router project preview
Agent tooling
Use Jev Choice and Noul decisions to select Codex subagent model and reasoning tiers, with local compatible backends and a Sol fallback.
Jev Auto Router project preview
Agent tooling
Per-call GPT model routing for Codex: Jev chooses model and effort, a local Responses proxy keeps the tool loop intact, then independent verification and Router Compass check whether the task still passed.
jev-kit project preview
Browser & computer use
Everything you need to run TypeSafe's Jev with Claude Code: a tool-call guard, tier guard, file search, browser agent, review, belay, compaction and installers.
Jevbridge project preview
Browser & computer use
ACP and MCP adapter that bridges TypeSafe Jev with any LLM — computer use and typed decisions alongside Codex, Claude, Grok, and OpenCode.
langchain-loadout project preview
Integrations
Per-turn skill selection for LangChain and deepagents agents: a fast judge picks the few skills a turn needs, so a catalog of hundreds stays out of the prompt.