How do I send a Jev decision through rotom?

POST to /v1/evaluations with a model such as typesafe-ai/jev, a state string and typed questions; the README shows a boolean question with true and false criteria.

Where do credentials come from?

From one-time rotom login flows: browser login for Codex and Grok, Kiro's portal for Kiro, or an AI Gateway API key for Vercel; each provider is stored separately and all run behind one local address.

How do I run rotom as a background service?

rotom daemon install --bind 127.0.0.1:14550 --api-key ... followed by rotom daemon start; it uses a macOS LaunchAgent or a Linux systemd user unit, and on Windows you use WSL.

How do I expose rotom beyond localhost?

--bind accepts a comma-separated list and CIDR selectors, for example 127.0.0.1:14550,192.168.1.0/24:14550, and the daemon keeps the API key in ~/.rotom/config.json rather than the service definition.

What happens to an unknown Claude model id?

Unknown Anthropic ids like claude-sonnet-* are rewritten to a fallback, default gpt-5.5, which you can change with --model-fallback or ROTOM_MODEL_FALLBACK.

What license is rotom under?

It is LGPL-3.0 only and an unofficial compatibility tool unaffiliated with the providers; its disclaimer warns that personal OAuth access should not be shared, resold or exposed as a multi-user service.

Which API shapes does rotom speak?

It proxies OpenAI chat, responses and image endpoints, Anthropic messages, token counting and message batches, Vercel AI Gateway evaluations, and Grok-native text-to-speech over REST and WebSocket.

CommunityJev Integrations & Adapters

Rotom

Local OpenAI- and Anthropic-compatible API gateway in Rust that reuses Codex, Grok, Kiro or Vercel AI Gateway logins. It carries Jev through its model catalog and evaluation path, exposing typesafe-ai/jev via POST /v1/evaluations with state and typed questions.

See highlights

Open github.com

Stars: 6
Language: Rust
License: LGPL-3.0
Published by: Community
Last verified: Oct 2026

RyanKung/rotom

User repository on GitHub

View on GitHub

Local OpenAI- and Anthropic-compatible API gateway backed by Codex OAuth.

Forks: 3
Last pushed: Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.

About this project

Use your Codex, Grok, Kiro, or Vercel AI Gateway credentials from any tool that speaks the OpenAI or Anthropic API. rotom is a small local gateway. You log in once, run rotom serve, and point Claude Code, the OpenAI/Anthropic SDKs, or any compatible client at the local address. Claude Code running through Grok and GPT: Point Claude Code (or any Anthropic-compatible client) at the gateway: rotom login lists the providers and runs the chosen flow. Skip the prompt with a flag:

Quoted from the project's README. Read the full README.

Tagscommunity gateway rust local-ai

Works forJev for Evaluation

Used inJev for Software & DevTools

Languages: Rust
Platforms: CLI Vercel AI Gateway
Capabilities: Open sourceSelf-hostedRuns locallyRequires API key

Highlights

Run `rotom serve --bind 127.0.0.1:14550 --api-key ...` and point ANTHROPIC_BASE_URL at the server root.
Proxies OpenAI and Anthropic endpoints including /v1/messages, /v1/chat/completions and message batches.
Jev arrives via Vercel AI Gateway evaluations as typesafe-ai/jev, alongside ids like openai/gpt-6-astra.
Runs as a background daemon via LaunchAgent or systemd; credentials stored per provider in ~/.rotom/auth.json.

Watch out

LGPL-3.0 only. It is an unofficial compatibility tool unaffiliated with the providers, and its disclaimer warns that personal OAuth access should not be shared, resold or exposed as a multi-user service.

Questions about this entry

Short answers drawn from the linked project or page.

Reactions & coverage

Posts, threads, and videos about this entry from around the web.

X: Jev lands on the Vercel AI Gateway

X: Jev as an LLM guardrail inside Agentgateway

YouTube: Greg Isenberg and Ryan Vogel on the businesses Jev unlocks, and a path in through the Vercel AI Gateway.

Related terms

Glossary definitions related to this entry.

AI gateway

More Jev resources like this

Holon

159

Rust agent workbench for ongoing work that keeps branch decisions in their own crate and backend notes in the adapter. Its first decision backend is Cloudflare's Clef, borrowing Clef's System One-shaped state and questions request instead of reinventing the interface.

Jev Integrations & Adapters#community#agent-runtime#rust

Community

holon-run/holonRust

Minutes

1.5k

An MIT-licensed, local-first conversation memory app that transcribes meetings, calls and voice memos on-device into Markdown you own. Its live voice path runs evaluations through Jev, and 34 MCP tools plus a 58-command CLI let coding agents query the history you choose to share.

Jev Integrations & Adapters#community#mcp#transcription

Community

silverstein/minutesRust

OpenViking

39.6k

Volcengine's agent context database that unifies memory, knowledge RAG and skills under a viking:// virtual filesystem; it ships a Jev rerank client that scores candidate documents against api.typesafe.ai and treats the probability as relevance.

Jev Integrations & Adapters#community#agent-memory#rag

Community

volcengine/OpenVikingPython

jcode

20.4k

Rust coding-agent harness (MIT, ~20k stars) whose crates/jcode-base/src/jev.rs is a typed TypeSafe Jev decision transport, used for memory pruning (memory_jev.rs), browser navigation (browser_jev.rs), and voice routing (voice_intent.rs) with separate provider selectors per purpose.

Jev Tools & CLIs#community#rust#coding-agent

Community

1jehuang/jcodeRust

Inbox Zero

12.4k

Open-source AI email assistant (Next.js, Postgres, 12k+ stars) with a decision-model layer that can run on openrouter:typesafe/jev-1.13: Jev-backed questions cover rule selection, cold-email detection, thread status, recurring patterns, unsubscribe pages, and sender categorization, each with evals.

Jev Integrations & Adapters#community#email#gmail

Community