omniroute

data-ai MCP Server

Never stop coding. Free AI gateway: one endpoint, 231+ providers (50+ free), connect Claude Code, Codex, Cursor, Cline & Copilot to FREE Claude/GPT/Gemini. RTK+Caveman stacked compression saves 15-95% tokens, smart auto-fallback, MCP/A2A, multimodal APIs, Desktop/PWA.

Verified
data-aidata-ai
15 views73,712 stars10,588 forksv3.8.49MIT

Why This Matters

Discovered via mcp and last synced 2mo ago.

Verified
Source
mcp
Stars
73,712
Last synced
2mo ago
Install
Check source

Install

Install instructions not detected yet

Check the source repository for the latest setup steps.

View source instructions
107
Tools
0
Resources
0
Prompts
Standard I/O
Transport

Available Tools (107)

Layer

Scope

Default

Purpose

Translator

![Translator](docs/screenshots/05-translator.png)

Platform

Install

6

**Caveman**

PORT

`20128`

7

**LLMLingua-2**

REQUIRE_API_KEY

`false`

Mode

Savings

unsupported_country_region_territory

Configure proxy in Settings → Proxy

Page

Screenshot

Step

Action

1

**Session-Dedup**

3

**RTK**

4

Declarative shell-output reduction over MCP — validated our declarative bash-output compaction.

5

**Relevance**

Command

Action

omniroute

Start server (`PORT=20128`, API and dashboard on same port)

REQUEST_TIMEOUT_MS

`600000`

STREAM_IDLE_TIMEOUT_MS

inherits `REQUEST_TIMEOUT_MS`

API_BRIDGE_SERVER_REQUEST_TIMEOUT_MS

`max(API_BRIDGE_PROXY_TIMEOUT_MS, 300000)`

Groq

**FREE** (30 RPM)

Qwen

**$0**

Prefix

Rate Limit

Variable

Default

API_BRIDGE_SERVER_HEADERS_TIMEOUT_MS

`60000`

None

Reasoning flagship from xAI

Kiro

**$0**

qwen3-coder-flash

`qw/`

openai

`pol/`

Provider

Prefix

FETCH_TIMEOUT_MS

inherits `REQUEST_TIMEOUT_MS`

API_BRIDGE_SERVER_KEEPALIVE_TIMEOUT_MS

`5000`

Model

Prefix

qwen3-coder-next

`qw/`

gemini

`pol/`

Feature

OmniRoute

Strategy

What it does

FETCH_HEADERS_TIMEOUT_MS

inherits `FETCH_TIMEOUT_MS`

API_BRIDGE_SERVER_SOCKET_TIMEOUT_MS

`0`

vision-model

`qw/`

LongCat-Flash-Lite

50M tokens/day 🔥

deepseek

`pol/`

exact

Output must match exactly

FETCH_BODY_TIMEOUT_MS

inherits `FETCH_TIMEOUT_MS`

Image

Tag

Mistral

Free trial + paid

kimi-k2-thinking

`if/`

LongCat-Flash-Chat

`lc/`

llama

`pol/`

contains

Output must contain substring (case-insensitive)

FETCH_CONNECT_TIMEOUT_MS

`30000`

latest

~250MB

OpenRouter

Pay-per-use

qwen3-coder-plus

`qw/`

gemini-3-flash-preview

`gc/`

LongCat-Flash-Thinking

`lc/`

mistral

`pol/`

regex

Output must match regex pattern

FETCH_KEEPALIVE_TIMEOUT_MS

`4000`

Tier

Example

Pay-per-use

None

deepseek-r1

`if/`

LongCat-Flash-Thinking-2601

`lc/`

custom

Custom JS function returns true/false

TLS_CLIENT_TIMEOUT_MS

inherits `FETCH_TIMEOUT_MS`

Monthly

GitHub users

kimi-k2

`if/`

LongCat-Flash-Omni-2603

`lc/`

Document

Description

API_BRIDGE_PROXY_TIMEOUT_MS

inherits `REQUEST_TIMEOUT_MS` or `30000`

Cerebras

**FREE** (1M tok/day)

Qoder

**$0**

Free

**1M tokens**

Multimodal

> 100% free while in public beta. Sign up at [longcat.chat](https://longcat.chat) with email or phone. Resets daily 00:00 UTC. ### 🟢 POLLINATIONS AI (No API Key Required) 🆕

Category

Planned Features

Goal

Strategy / combo

Engine

What it does

9

**Aggressive**

Problem

Quick fix

Analytics

![Analytics](docs/screenshots/03-analytics.png)

Protocol

Endpoint

8

**Lite**

DATA_DIR

`~/.omniroute`

auto

🎯 Balanced default (LKGP — sticks to your last good provider)

Providers

![Providers](docs/screenshots/01-providers.png)

10

**Ultra**

11

`reset-window`

12

`reset-aware`

13

`context-relay`

14

First inspired our tabular compaction stage; now its zero-dependency, lossless generic-profile encoder is **vendored directly** as the Headroom codec (MIT, SPDX-marked), current with GCF spec v3.2.

15

`lkgp`

16

PT-BR token compression — powers our pt-BR language pack: pleonasm reduction and filler removal tuned for Brazilian-Portuguese grammar.

17

`fusion`

18

`pipeline`

Knob

What it controls

bifrost

auto`) so `/v1/relay` stays the stable surface while choosing the fastest backend internally, **Bifrost** (Go AI-gateway) and **Mux** (agent-orchestration daemon) promoted to first-class embedded/supervised services alongside 9Router/CLIProxyAPI, **Webshare** added as a paid fourth source in the free-proxy provider framework, and **shorthand proxy formats + protocol header mode** for bulk proxy import. → [Embedded Services](docs/frameworks/EMBEDDED-SERVICES.md) <br/> <div align="center"> # 🤖 Compatible CLIs & Coding Agents > One config — `http://localhost:20128/v1` — and **every** AI IDE or CLI runs on free & low-cost models. <div align="center"> <table> <tr> <td align="center" width="120"><a href="https://github.com/anthropics/claude-code"><img src="./public/providers/claude.svg" width="52" alt="Claude Code"/><br/><b>Claude Code</b></a></td> <td align="center" width="120"><a href="https://github.com/openai/codex"><img src="./public/providers/codex.svg" width="52" alt="Codex CLI"/><br/><b>Codex CLI</b></a></td> <td align="center" width="120"><img src="./public/providers/cursor.png" width="52" alt="Cursor"/><br/><b>Cursor</b></td> <td align="center" width="120"><img src="./public/providers/copilot.png" width="52" alt="Copilot"/><br/><b>Copilot</b></td> <td align="center" width="120"><img src="./public/providers/continue.png" width="52" alt="Continue"/><br/><b>Continue</b></td> </tr> <tr> <td align="center" width="120"><a href="https://github.com/anomalyco/opencode"><img src="./public/providers/opencode.svg" width="52" alt="OpenCode"/><br/><b>OpenCode</b></a></td> <td align="center" width="120"><a href="https://github.com/Kilo-Org/kilocode"><img src="./public/providers/kilocode.svg" width="52" alt="Kilo Code"/><br/><b>Kilo Code</b></a></td> <td align="center" width="120"><img src="./public/providers/droid.svg" width="52" alt="Droid"/><br/><b>Droid</b></td> <td align="center" width="120"><img src="./public/providers/openclaw.png" width="52" alt="OpenClaw"/><br/><b>OpenClaw</b></td> <td align="center" width="120"><img src="./public/providers/kiro.svg" width="52" alt="Kiro"/><br/><b>Kiro</b></td> <td align="center" width="120"><img src="./public/providers/command-code.svg" width="52" alt="Command Code"/><br/><b>Command</b></td> </tr> </table> </div> <div align="center"> <b>+ also works with</b> · Cline · Antigravity · Windsurf · AMP · Hermes · Qwen CLI · Roo · Continue · <b>any OpenAI-compatible tool</b> </div> <sub>📖 Per-tool setup for all 24+ tools → [`docs/reference/CLI-TOOLS.md`](docs/reference/CLI-TOOLS.md) · 🧩 OpenCode plugin → [`@omniroute/opencode-provider`](https://www.npmjs.com/package/@omniroute/opencode-provider)</sub> </div> <br/> <div align="center"> # 🌐 250 AI Providers — 90+ Free </div> > The most complete catalog of any open-source router: **250 providers**, **90+ with a free tier**, **11 free forever**. <div align="center"> ### 🏢 Every major lab — through one endpoint <table> <tr> <td align="center" width="92"><picture><source media="(prefers-color-scheme:dark)" srcset="https://cdn.jsdelivr.net/npm/@lobehub/[email protected]/dark/openai.png"/><img src="https://cdn.jsdelivr.net/npm/@lobehub/[email protected]/icons/openai.svg" width="40" alt="OpenAI"/></picture><br/><sub>OpenAI</sub></td> <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/[email protected]/icons/claude-color.svg" width="40" alt="Anthropic"/><br/><sub>Anthropic</sub></td> <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/[email protected]/icons/gemini-color.svg" width="40" alt="Gemini"/><br/><sub>Gemini</sub></td> <td align="center" width="92"><picture><source media="(prefers-color-scheme:dark)" srcset="https://cdn.jsdelivr.net/npm/@lobehub/[email protected]/dark/grok.png"/><img src="https://cdn.jsdelivr.net/npm/@lobehub/[email protected]/icons/grok.svg" width="40" alt="xAI Grok"/></picture><br/><sub>xAI Grok</sub></td> <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/[email protected]/icons/deepseek-color.svg" width="40" alt="DeepSeek"/><br/><sub>DeepSeek</sub></td> <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/[email protected]/icons/mistral-color.svg" width="40" alt="Mistral"/><br/><sub>Mistral</sub></td> </tr> <tr> <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/[email protected]/icons/qwen-color.svg" width="40" alt="Qwen"/><br/><sub>Qwen</sub></td> <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/[email protected]/icons/meta-color.svg" width="40" alt="Meta Llama"/><br/><sub>Meta Llama</sub></td> <td align="center" width="92"><picture><source media="(prefers-color-scheme:dark)" srcset="https://cdn.jsdelivr.net/npm/@lobehub/[email protected]/dark/groq.png"/><img src="https://cdn.jsdelivr.net/npm/@lobehub/[email protected]/icons/groq.svg" width="40" alt="Groq"/></picture><br/><sub>Groq</sub></td> <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/[email protected]/icons/nvidia-color.svg" width="40" alt="NVIDIA"/><br/><sub>NVIDIA</sub></td> <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/[email protected]/icons/minimax-color.svg" width="40" alt="MiniMax"/><br/><sub>MiniMax</sub></td> <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/[email protected]/icons/cohere-color.svg" width="40" alt="Cohere"/><br/><sub>Cohere</sub></td> </tr> <tr> <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/[email protected]/icons/perplexity-color.svg" width="40" alt="Perplexity"/><br/><sub>Perplexity</sub></td> <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/[email protected]/icons/huggingface-color.svg" width="40" alt="Hugging Face"/><br/><sub>HuggingFace</sub></td> <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/[email protected]/icons/together-color.svg" width="40" alt="Together"/><br/><sub>Together</sub></td> <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/[email protected]/icons/fireworks-color.svg" width="40" alt="Fireworks"/><br/><sub>Fireworks</sub></td> <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/[email protected]/icons/cloudflare-color.svg" width="40" alt="Cloudflare"/><br/><sub>Cloudflare</sub></td> <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/[email protected]/icons/baidu-color.svg" width="40" alt="Baidu"/><br/><sub>Baidu</sub></td> </tr> </table> <sub>…and 220+ more — every icon resolves live from the dashboard's provider catalog. 📖 [Provider Reference](docs/reference/PROVIDER_REFERENCE.md)</sub> <br/> ### 🆓 Free Forever — $0, no card <table> <tr> <td align="center" width="150"><img src="./public/providers/agentrouter.png" width="44" alt="AgentRouter"/><br/><b>AgentRouter</b><br/><sub>GPT-5, Claude, Gemini<br/>$100 free credits</sub></td> <td align="center" width="150"><img src="https://cdn.jsdelivr.net/npm/@lobehub/[email protected]/icons/qoder-color.svg" width="44" alt="Qoder AI"/><br/><b>Qoder AI</b><br/><sub>Kimi-K2, DeepSeek-R1<br/>Unlimited FREE</sub></td> <td align="center" width="150"><picture><source media="(prefers-color-scheme:dark)" srcset="https://cdn.jsdelivr.net/npm/@lobehub/[email protected]/dark/pollinations.png"/><img src="https://cdn.jsdelivr.net/npm/@lobehub/[email protected]/icons/pollinations.svg" width="44" alt="Pollinations"/></picture><br/><b>Pollinations</b><br/><sub>GPT-5, Claude, Llama 4<br/>No key needed</sub></td> <td align="center" width="150"><img src="https://cdn.jsdelivr.net/npm/@lobehub/[email protected]/icons/longcat-color.svg" width="44" alt="LongCat"/><br/><b>LongCat</b><br/><sub>LongCat-2.0<br/>10M tokens one-time (KYC) 🔑</sub></td> </tr> <tr> <td align="center" width="150"><img src="https://cdn.jsdelivr.net/npm/@lobehub/[email protected]/icons/cloudflare-color.svg" width="44" alt="Cloudflare AI"/><br/><b>Cloudflare AI</b><br/><sub>50+ models<br/>10K neurons/day</sub></td> <td align="center" width="150"><img src="https://cdn.jsdelivr.net/npm/@lobehub/[email protected]/icons/nvidia-color.svg" width="44" alt="NVIDIA NIM"/><br/><b>NVIDIA NIM</b><br/><sub>129 models<br/>~40 RPM free</sub></td> <td align="center" width="150"><img src="https://cdn.jsdelivr.net/npm/@lobehub/[email protected]/icons/cerebras-color.svg" width="44" alt="Cerebras"/><br/><b>Cerebras</b><br/><sub>Qwen3 235B<br/>1M tokens/day</sub></td> </tr> </table> 📖 Full machine-readable catalog → [`docs/reference/PROVIDER_REFERENCE.md`](docs/reference/PROVIDER_REFERENCE.md) <br/> </div> <div align="center"> # 🖥️ Where OmniRoute Runs — Anywhere </div> > Same app, your machine, your rules. From a global npm install to **your phone** via Termux.

Install

Highlights

Project

How it composes with OmniRoute

28

The JS/ONNX port (MobileBERT / XLM-RoBERTa) used as the worker-thread backend for our LLMLingua engine.

421

Brotli/SQLite cache + per-session context-delta — inspired our `session-dedup` engine.

110

Content-aware, per-file-type output compression with failure-aware bail-out — validated our per-type dispatch and minimum-gain skip.

2

Rust columnar-JSON + content-addressed retrieve + cross-message dedup — validated our `headroom`/`ccr`/`session-dedup` engine design and the cache-stable "compressed form is position-independent" invariant.

89

MCP tool-schema/description compression — informed our MCP tool-manifest cardinality reduction.

181

Aider-style repo-map ranking — informed our repo-map / retrieval-ranking exploration.

48

MITM interception/analysis of coding-assistant ↔ LLM traffic — our Traffic Inspector ports its SSE merge, conversation normalization, host passthrough and secret masking (MIT).

708

A curated list of secure-by-default libraries that guides our security choices (Helmet.js, DOMPurify, ssrf-req-filter, safe-regex, Google Tink).