ClawRouter

ClawRouter is a model router/gateway - The agent-native LLM router for autonomous agents. 55+ models (8 free), <1ms local routing, USDC payments on Base & Solana via x402.

Overview

Agents can't sign up for accounts. Agents can't enter credit cards. Agents can only sign transactions. ClawRouter is the only LLM router that lets agents operate independently. 8 models free, no crypto required. No signup. No API key. No credit card.

Every other LLM router was built for human developers — create an account, get an API key, pick a model from a dashboard, pay with a credit card.

• Starts at $0 — 8 NVIDIA models are free forever (incl. 675B Mistral Large 3, 262K-context Qwen3-Next 80B + a vision-capable Nemotron Omni) - No accounts — a wallet is generated locally, no signup - No API keys — your wallet signature IS authentication - No model selection — 15-dimension scoring picks the right model automatically - No credit cards — agents pay per-request with USDC via x402 - No trust required — runs locally, continue.dev — ~/.continue/config.yaml

To pin a specific model, replace 'blockrun/auto' with any model from blockrun.ai/models, e.g. 'anthropic/claude-opus-4.8', 'xai/grok-4.5'.

Both 'provider: openai' and 'provider: clawrouter' work — just make sure 'apiBase' ends with '/v1/'.

Set base URL to 'http://localhost:8402', API key to 'x402', model to 'blockrun/auto'.

**100% local routing. .mp4' so the asset survives past the upstream's temporary bucket.

ClawRouter is open-source, written primarily in TypeScript, with 6,660 GitHub stars under the MIT license. The latest release is v0.12.230 (2026-07-19).

Key capabilities

From the project's documentation:

• No accounts — a wallet is generated locally, no signup
• No API keys — your wallet signature IS authentication
• No model selection — 15-dimension scoring picks the right model automatically
• No credit cards — agents pay per-request with USDC via x402
• No trust required — runs locally, <1ms routing, zero external dependencies
• Base (EVM): Send USDC on Base to your EVM address

Install

A quick way to get started (always check the official docs for the latest):

npm install -g @blockrun/clawrouter

How it fits a local-AI stack

ClawRouter runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related model router/gateways in the directory:

• "AIClient2API"
• "litellm"
• "PhoneClaw"

Sources

• Source code & docs: BlockRunAI/ClawRouter

Stats from GitHub, 2026-07-20.