nitro

Grok Build with TypeSafe Jev routing tool selection once per turn: 22 to 40% cheaper on the same tasks

How it uses Jev

Grok Build with TypeSafe Jev in front of tool selection. The command is nitro .

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

Keep exploring

Similar to nitro

Browse all
jev-routing project preview
Agent tooling
Go Jev harness for Claude Code, Codex, and Grok Build. No npx. Not an MCP server.
jev-workbench project preview
Agent tooling
Build versioned judgment functions on TypeSafe's Jev once, then call the same published version from your backend over HTTP and from coding agents over MCP. The vendor key stays on your machine.
jev-agent-hooks project preview
Agent tooling
TypeSafe Jev hooks for Claude Code, Codex and pi: per-turn skill suggestion and subagent model routing
hermes-jev-skills project preview
Browser & computer use
Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex)
dohnuts project preview
Applications
Dohnuts builds small multimodal models for direct decisions. -> System One model
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.
LitJev project preview
Benchmarks & research
A reproduction of Jev that turns any Qwen model into a fast decision model, serving the same /v1/systemone schema (Choice, Score, Noul) with no training and no generated answer text.
jev-browser (vlad-terin) project preview
Browser & computer use
Jev-powered element selection for your agent’s existing computer-use tools
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.