Skip to main content
kRouter

One endpoint.
Build Everything.

The AI infrastructure layer beneath your favourite IDE. Route Claude Code, Cursor, and 89+ providers through a single OpenAI-compatible endpoint on your machine.

Get started — free foreverStar on GitHub
  • MIT licensed
  • Self-hosted
  • 12+ IDEs supported
  • 89+ providers
  • 12.5k+ monthly downloads
localhost:20128
01 · Your IDE
cc/
cur/
ag/
gh/
+8
02 · kRouter
kRouter:20128
~5s
latency
40%
savings
$0
cost
03 · Providers
Claude
OAuth · Pro/Max
T1
Codex
OAuth · Plus/Pro
T1
Vertex
$300 credits
T2
Kiro
Free · unlimited
T3
Catalog+ 85 more
OpenAI-compatibleMIT

How it works

One local endpoint.
Every provider behind it.

kRouter runs on your machine and exposes a single OpenAI-compatible endpoint at localhost:20128. Point any IDE at it. Behind the scenes it routes to your subscription first, falls back to free tiers, and only touches paid keys when nothing else works.

  • No proxy in the cloud. Your prompts stay on your machine.
  • Quota-aware. Switches providers automatically when one runs out.
  • Format translation. OpenAI ↔ Claude ↔ Gemini — any tool, any model.

Your IDE

  • Claude Code
  • Cursor
  • Antigravity
  • Copilot
  • Codex
  • Kiro

kRouter

:20128

89+ providers

  • Anthropic
  • OpenAI
  • Google
  • GitHub
  • Kiro
  • Mistral
  • Groq
  • +82 more

one OpenAI-compatible API · subscription → free → paid fallback · RTK compression · format translation

Install in 30 seconds

One command. Three ways.

Pick NPM if you just want it to work. Docker if you self-host. Git if you want to hack on the code.

$npm install -g @sifxprime/krouter
$krouter -t

Dashboard: http://localhost:20128/dashboard

Full guide →
Built for production

Real features from the repo — not marketing slides.

Every feature ships with audited unit tests, end-to-end verification, and visible-in-the-dashboard observability.

RTK Token Saver

Compresses tool_result content (git diff, grep, ls, tree) inline before sending. Saves 20–40% input tokens per request.

Caveman Mode

Optional terse-response prompt injection (Lite / Full / Wenyan) to cut output tokens up to 65% without losing technical substance.

3-Tier Fallback

Subscription → cheap → free. Combos auto-rotate when one quota hits zero. No more rate-limit interruptions.

Routing Strategies

Per-provider account selection: fill-first, round-robin (sticky), p2c, or random. Atomic backoff keeps concurrency safe.

Response Cache

In-memory cache for repeated non-streaming requests. Warmup probes and title generation skip redundant upstream calls.

Real-Time Quota

Live token counts, reset countdowns, and per-model spend. Quota tracker matches Google's own backend numbers.

MITM Mode

Intercept Antigravity, Kiro, Copilot, and Cursor IDE traffic locally. Bounds-checked frames, NGHTTP2 stream recovery.

Tunnel / Tailscale

Expose the dashboard over a public tunnel or Tailscale. Configurable access controls so it stays safe when shared.

Provider Ecosystem

OAuth, free credits, API key, and browser-cookie providers. Stack them into combos that auto-fall-through.

Format Translation

OpenAI ↔ Claude ↔ Gemini ↔ Cursor ↔ Kiro. Use any tool with any model. The translation layer handles the rest.

Auto Token Refresh

OAuth tokens refresh before expiration. Concurrent-safe — no stale-401 cascades when traffic spikes.

Zero Cost

MIT licensed, self-hosted, never charges. The dashboard 'cost' is a savings tracker — you only pay providers directly.

Works with your stack

89+ providers.
One endpoint.

OAuth subscription providers, genuinely-free tiers, and pay-per-token APIs. Stack them into combos so requests auto-fall-through.

Browse all providers
Kiro AI
kr/
OpenCode Free
oc/
OpenRouter
openrouter/
NVIDIA NIM
nvidia/
Vertex AI
vx/
Gemini
gemini/
BytePlus ModelArk
bpm/
Claude Code
cc/
Antigravity
ag/
OpenAI Codex
cx/
GitHub Copilot
gh/
Cursor IDE
cu/
xAI (Grok)
xai/
GLM Coding (Z.ai)
glm/
Kimi
kimi/
Minimax Coding
minimax/
OpenAI
openai/
Anthropic
anthropic/
DeepSeek
ds/
Groq
groq/
Mistral
mistral/
Perplexity
pplx/
Together AI
together/
Fireworks AI
fireworks/
How we compare

Honest, side-by-side.

All three projects share a common ancestor (CLIProxyAPI in Go). Each takes the idea in a different direction. Pick by fit, not loyalty.

See full 5-way comparison
ConcernkRouter9routerOmniRoute
Verify-your-account ban fixNumeric enums (matches binary)String enums (triggers ban)Permanent-ban classifier
Exhausted Claude quota displayAmber 'Exhausted • resets in X'Fake red 100%-used barSimilar to kRouter
Combo retry on busy IDE~5s with per-provider concurrency~25s flat 30s timeout cascadeTunable, similar
MITM stream error recoveryNGHTTP2 → HTTP/1.1 fallback"Truncated event message"Different MITM stack
Thinking config passthroughTranslates Claude/OpenAI shapeBlacklist strips, never runsTranslates at converter

The new floor for AI coding

Stop choosing tools.
Build Everything.

kRouter is the layer beneath your favourite IDE — Claude Code, Cursor, Antigravity, Copilot, Codex, Kiro. Connect any model. Switch providers on quota. Keep every prompt on your machine.

Install kRouterStar on GitHub

MIT licensed · v0.5.81 · Built in the open.

What you actually get

  • Local endpointOpenAI-compatible API at localhost:20128
  • Providers89+ — OAuth, free, and pay-per-token
  • IDEsClaude Code · Cursor · Antigravity · Copilot · Codex · Kiro · Cline · Roo · Aider · OpenCode · Kimi · Gemini CLI
  • Token savings20–40% via RTK compression
  • PrivacyPrompts never leave your machine
  • LicenseMIT — self-hosted forever