Clawrouter

ClawRouter (Hermes)

Quick Start (Hermes plugin)

Recommended:

curl -fsSL https://raw.githubusercontent.com/BlockRunAI/ClawRouter-Hermes/main/scripts/install.sh | bash

Manual install, if you know Hermes' Python venv path:

~/.hermes/hermes-agent/venv/bin/python -m pip install -U hermes-plugin-clawrouter
hermes plugins enable clawrouter
hermes clawrouter setup       # installs the model-provider plugin + verifies your rail (wallet or API key)
hermes clawrouter doctor      # green = ready

If plain pip install hermes-plugin-clawrouter fails with Debian/Ubuntu's externally-managed-environment, do not use --break-system-packages; install into Hermes' venv or use the one-command installer. The installer also checks for Python, pip/venv support, pipx, and Node/npm/npx, and installs missing basics through common OS package managers when available.

Then in a Hermes chat session:

• Pick model blockrun/auto for smart routing across 78 models.
• /clawrouter account — which rail you're paying on (wallet or API key)
• /clawrouter wallet — show address + USDC balance (Solana and Base)
• /clawrouter stats — proxy usage
• /clawrouter status — proxy health
• /clawrouter route <eco|auto|premium> — switch routing profile
• /clawrouter logout — drop the API key, go back to the wallet
• Tools: clawrouter_image_generate, clawrouter_video_generate, clawrouter_web_search

Two ways to pay

Same catalog and same model ids either way — what differs is the credential and the host.

hermes-clawrouter login brk_live_...   # bill account credit
hermes-clawrouter account              # what's live right now
hermes-clawrouter logout               # back to the x402 wallet

A key wins over a wallet whenever both are present, and nothing is deleted — logout reverses it. Needs @blockrun/clawrouter >= 0.12.268; older proxies ignore the key and spend the wallet instead. Key resolution order: BLOCKRUN_API_KEY env → ~/.blockrun/.api-key → ~/.openclaw/blockrun/api-key. Type keys in a terminal, never in a chat — /clawrouter login refuses for that reason.

Wallet lives at ~/.openclaw/blockrun/mnemonic (shared with the upstream TS CLI — fund once, use everywhere). Override with BLOCKRUN_WALLET_KEY env for headless setups. Set CLAWROUTER_PROXY_URL to point at an externally-managed proxy.

Hosted-gateway LLM router that saves 84% on inference costs by forwarding each request to the blockrun.ai gateway, which picks the cheapest model capable of handling it across 78 models from 12 providers (6 free models). Billing flows through one credential — a local USDC wallet, or one BlockRun API key from https://user.blockrun.ai. Either way you do not hold provider API keys.

This is not a local-inference tool. ClawRouter is a thin local proxy. Your prompts are sent over HTTPS to the blockrun.ai gateway for model execution. If your workload requires inference that never leaves your machine, use a local runtime like Ollama — ClawRouter is not the right tool for that use case.

Source: https://github.com/BlockRunAI/ClawRouter · npm: https://www.npmjs.com/package/@blockrun/clawrouter · License: MIT.

Data Flow

Your app → localhost proxy (ClawRouter) → https://sol.blockrun.ai/api  (wallet, Solana)
                                        → https://blockrun.ai/api      (wallet, Base)
                                        → https://api.blockrun.ai      (API key)
                                              ↓
                                        OpenAI / Anthropic / Google / etc.
                                              ↓
                                        Response → back through proxy → your app

Sent to the gateway on every request: the model name, the full prompt/messages body, sampling params (temperature, max_tokens, tools, etc.), and one credential — either an X-PAYMENT header containing a signed x402 USDC micropayment (wallet rail), or an Authorization: Bearer brk_… header (API-key rail). Never both: an x402 header on an API-key request is a payment nobody asked for, and the proxy strips it.

Not sent: your wallet private key (only the detached payment signature is sent), any other local files, environment variables, or OpenClaw config beyond what's needed for this request.

Blockrun's privacy stance: https://blockrun.ai/privacy. Treat prompts the same way you'd treat prompts sent to any hosted LLM API (OpenAI, Anthropic, etc.) — do not send data you would not share with a third-party API provider.

Credentials & Local Key Storage

ClawRouter does not collect or forward third-party provider API keys. You do not supply OpenAI, Anthropic, Google, DeepSeek, xAI, or NVIDIA credentials — the blockrun.ai gateway owns those relationships.

There is exactly one optional BlockRun credential: a brk_… API key, stored 0600 at ~/.blockrun/.api-key (or supplied via BLOCKRUN_API_KEY) and sent as a bearer token to exactly one host, api.blockrun.ai. It is never logged in full — status output masks it to head-and-tail. It is optional: with no key configured, ClawRouter signs x402 payments from the local wallet instead and contacts no account service.

What models.providers.blockrun stores (fully enumerated):

How and where keys are stored:

• Keys live in the OpenClaw user config file — typically ~/.config/openclaw/config.json on Linux, ~/Library/Application Support/openclaw/config.json on macOS, %APPDATA%\openclaw\config.json on Windows — under the models.providers.blockrun path.
• Written by OpenClaw's standard config writer with 0600 permissions on POSIX systems (owner read/write only).
• Stored in plaintext, the same way every OpenClaw provider's API key is stored. ClawRouter does not add an extra encryption layer; your filesystem permissions are the security boundary. If you require an encrypted keystore, run OpenClaw on an encrypted volume (FileVault, LUKS, BitLocker) or use a dedicated burner wallet funded only with what you intend to spend.
• Auto-generation uses @scure/bip39 to produce a 24-word mnemonic, then BIP-44 derivation for both chains. Source: src/wallet.ts.

Operational guidance: treat the wallet as a spending account with a small top-up, not a long-term store of value. Fund it with what you expect to spend on LLM calls. If the host machine is compromised, the wallet key is compromised — rotate and refund.

Supply-Chain Integrity

• Every release is tagged on GitHub: https://github.com/BlockRunAI/ClawRouter/releases
• Every release publishes to npm with a matching version: https://www.npmjs.com/package/@blockrun/clawrouter?activeTab=versions
• The skills/release/SKILL.md mandatory checklist enforces: same version in package.json, matching git tag, matching GitHub release, and matching npm publish.
• To verify locally: npm pack @blockrun/clawrouter@<version> and compare the tarball contents to the tagged commit.

Install

openclaw plugins install @blockrun/clawrouter

The structured install block above tells OpenClaw to install the auditable npm package @blockrun/clawrouter. Source for every version is on GitHub; every release is tagged.

Setup

# Enable smart routing (auto-picks cheapest model per request)
openclaw models set blockrun/auto

# Or pin a specific model
openclaw models set openai/gpt-4o

How Routing Works

ClawRouter classifies each request into one of four tiers:

• SIMPLE — factual lookups, greetings, translations → gemini-2.5-flash ($0.30/$2.50)
• MEDIUM — summaries, explanations, data extraction → kimi-k2.7 ($0.95/$4.00)
• COMPLEX — code generation, multi-step analysis → gemini-3.1-pro ($2/$12)
• REASONING — proofs, formal logic, multi-step math → grok-4-1-fast-reasoning ($0.20/$0.50)

Prices are per 1M input/output tokens, on the default auto profile. Per-tier savings percentages are deliberately not quoted: the published figure is blended across a stated workload mix, and a per-tier number invites comparison against a baseline nobody wrote down. See savings-mix.json.

Rules handle 80% of requests in <1ms. Only ambiguous queries hit the LLM classifier ($0.00003 per classification).

Available Models

Built-in Agent Tools

In addition to LLM routing, ClawRouter exposes BlockRun's paid data APIs as ready-to-use OpenClaw tools. Every tool bills the rail you are already on — x402 USDC from the local wallet, or account credit when a brk_… key is configured — with no extra setup and no provider API keys. The only genuinely wallet-only surfaces are phone-number ownership and Polymarket trading.

Market Data

Realtime prices and historical OHLC across every asset class. The agent should call these directly instead of scraping finance sites.

Image & Video Generation

Prediction Markets (Predexon)

Full prediction-market toolbox spanning Polymarket, Kalshi, Limitless, Opinion, Predict.Fun, dFlow + Binance for crypto candles. 57 endpoints (Predexon v2) exposed as 9 agent tools (8 named ergonomic wrappers + 1 catch-all):

• Markets & trading — events, markets list per venue, cross-venue search (markets/search), orderbooks, candlesticks (per-market and per-token), trades, positions, volume charts.
• Leaderboard & smart money — global + per-market leaderboards, smart-money positioning, top holders, smart-activity feed.
• Wallet analytics — full wallet profile, P&L time series, per-market breakdown, similar-wallet discovery, batch profiles, AND/OR filters.
• UMA oracle + wallet identity — UMA optimistic-oracle resolution status (uma/markets, uma/market/{conditionId}); wallet identity labels (ENS / Lens / exchange / risk tags), bulk identity, on-chain cluster discovery.

Pricing: $0.001 per market-data call, $0.005 per analytics / search / wallet call. See the predexon skill for the full endpoint reference.

Example Output

[ClawRouter] google/gemini-2.5-flash (SIMPLE, rules, confidence=0.92)
             Cost: $0.0025 | Baseline: $0.308 | Saved: 99.2%