# decolua/9router

Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Auto-fallback, RTK -40% tokens, never hit limits.

Repository: https://github.com/decolua/9router
Canonical: https://ross.abutalabs.com/products/9router
Homepage: https://9router.com
Language: JavaScript
License: MIT
License Family: permissive
Topics: claude-code, cursor, ai-agents, ai-gateway, anthropic, chatgpt, claude, cline, codex, copilot, deepseek, free-ai, gemini, gemini-cli, llm, llm-gateway, openai, openai-proxy, qwen, token-saver
Last push: 2026-08-14T10:08:34+00:00

## Health v2 (maintenance only)
Score: 75/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 97, release rhythm 81, longevity 17
- inputs: {"age_days": 240, "days_push": 19, "days_rel": 48, "gap_med": 1.0, "n_releases_24m": 73}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 26418, forks 4773 (observed 2026-08-28T04:11:46.916165+00:00)

## What it is
9Router is a self-hosted AI gateway/router that connects AI coding tools like Claude Code, Cursor, Codex, and Cline to 60+ LLM providers through a single OpenAI-compatible endpoint. It provides 3-tier auto-fallback routing (subscription → cheap → free), token compression to save 20-40% on tokens, quota tracking, and multi-account round-robin.

## Use cases
- route claude code to free ai providers
- avoid hitting rate limits while coding with ai
- save tokens on ai coding assistant requests
- use one endpoint for multiple llm providers
- automatically fall back to cheaper models when quota runs out
- connect cursor and cline to gemini or deepseek for free
- reduce tool output token costs in ai coding sessions

## When to choose
- you hit subscription rate limits mid-coding and want automatic fallback
- you want to use free or cheap providers with your existing AI coding tools
- you want to cut token usage from tool outputs like git diffs
- you juggle multiple provider accounts and want round-robin load balancing

## When to avoid
- you need a fully managed cloud service with no local setup
- you only use a single provider and never hit limits
- you require enterprise SLAs or vendor support

## Facets
- artifact type: service
- maturity: active
- function: llm-inference, api-gateway, proxy, middleware, prompt-engineering
- domain: large-language-models, developer-tools, apis
- platform: cli, cross-platform, self-hosted
- tags: ai-gateway, llm-router, token-saver, claude-code, cursor, openai-compatible, auto-fallback, free-ai-providers, quota-tracking, ai-agents, nodejs, docker

## Member repositories
- decolua/9router (main) score 75

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:46.916165+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:55:52.540340+00:00, confidence not recorded.
  - readme: https://github.com/decolua/9router (fetched 2026-08-28T04:11:46.916165+00:00, sha 7ba097c86a97)
  - homepage: https://9router.com (fetched 2026-08-29T07:52:29.693997+00:00, sha 2038a674d30f)
- Data as of 2026-08-30T08:39:29.467469+00:00.