Organization repository on GitHub
The model router for AI agents.
- Forks
- 11
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.Homepage
Jev directory
CommunityJev Integrations & Adapters
AutoJev (ThinkAny router)
A Tauri desktop model router for AI agents: one local gateway at 127.0.0.1:9527 that manages providers and routing rules, converts between OpenAI and Anthropic protocols, and uses OpenRouter Jev to pick the model for each request.
- Stars
- 100
- Language
- Rust
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- thinkany-ai
- Last verified
- Oct 2026
This is one of several Jev listings for the same project. The canonical entry is AutoJev — denis-pplx.
Works forJev for Routing
Used inJev for Software & DevTools
- Languages
- RustTypeScript
- Platforms
- OpenRouterAPI
- Capabilities
- Open sourceRuns locally
Highlights
- One local gateway for AI agents: route every request to the right model through http://127.0.0.1:9527/v1.
- Decision model: use OpenRouter Jev to select a candidate model, with local routing as the fallback when Jev is unavailable.
- Routing: intelligent selection or load balancing with speed, cost, quality or balanced preferences, plus session affinity, failover and cooldowns.
- Converts between OpenAI Responses, Chat Completions and Anthropic Messages protocols, including streaming and function tool calls.
- Built with Tauri, React and Rust; it connects Codex, Claude Code and Hermes, and the README says it is in early development.
Watch out
README reviewed 2026-10-17; the excerpt is truncated inside the architecture diagram and shows no install command or platform matrix, so supported operating systems and setup steps come only from the linked GitHub Releases page.
Questions about this entry
Short answers drawn from the linked project or page.
A desktop model router for AI agents: a Tauri, React and Rust app that manages providers, models and routing rules in one place and exposes a single local endpoint for agents such as Codex, Claude Code and Hermes.
Its decision model feature uses OpenRouter Jev to select a candidate model for a request, with local routing as the fallback when Jev is unavailable, according to the README feature list.
Agents point at the local gateway on http://127.0.0.1:9527/v1, and AutoJev forwards to OpenRouter, DeepSeek or custom providers after intelligent selection, load balancing or failover.
OpenAI Responses, Chat Completions and Anthropic Messages, including streaming and function tool calls; the README links a protocol compatibility document for the limitations.
Intelligent selection or load balancing optimised for speed, cost, quality or a balance of them, with session affinity, failover and cooldowns; image support and context lengths are informational settings only.
Installers are published on GitHub Releases, and the digest excerpt does not include install commands. The README warns the app is in early development, so check the releases page for supported platforms.
No. This repository, thinkany-ai/autojev, is a router app that ships no model weights of its own; it uses OpenRouter Jev to choose among the models you configure, with local routing as a fallback.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Jev 1.14 is now on OpenRouter
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.
More Jev resources like this
Zero-dependency Node adapter that exposes OpenCode Zen's eleven free-tier models to 9Router as one OpenAI-compatible provider, and documents jev-1.13-free as the SystemOne-protocol model it deliberately does not proxy.
Jev Integrations & Adapters#community#github#javascript
A host-agnostic routing layer that sits between a coding harness and its models, choosing capacity per round from trajectory evidence like tool calls, failures and context pressure, running as a user-scoped daemon and local OpenAI-compatible proxy.
Jev Integrations & Adapters#community#catalog-import#logicrw
Community
vizuh/sabiTypeScript
vizuh/sabiTypeScriptOpen-source TypeScript agentic operating system: a core runtime, app for web and mobile, CLI, cloud services and first-party plugins. The directory's curated summary reports it integrates TypeSafe System One decision services for sub-100ms intent classification, action dispatching and confidence-gated tool execution.
Jev Integrations & Adapters#community#agents#framework
Community
elizaOS/elizaTypeScript
elizaOS/elizaTypeScriptRust 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
holon-run/holonRustLocal 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.
Jev Integrations & Adapters#community#gateway#rust
Community
RyanKung/rotomRust
RyanKung/rotomRustAn open-source LLM router: a small router model, Laya or Jev, reads each prompt and decides which LLM, specialist agent or direct answer it gets, then serves everything through one OpenAI-compatible endpoint. Routing rules are described in plain language in a GUI.
Jev Integrations & Adapters#community#github#llm-router
Community
pooyaphoenix/RoutapsePython
pooyaphoenix/RoutapsePythonFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.