{"id":44494301,"url":"https://github.com/BlockRunAI/ClawRouter","last_synced_at":"2026-02-16T13:00:21.043Z","repository":{"id":336356659,"uuid":"1149071982","full_name":"BlockRunAI/ClawRouter","owner":"BlockRunAI","description":"Smart LLM router — save 78% on inference costs. 30+ models, one wallet, x402 micropayments.","archived":false,"fork":false,"pushed_at":"2026-02-11T13:59:34.000Z","size":2677,"stargazers_count":2181,"open_issues_count":6,"forks_count":221,"subscribers_count":81,"default_branch":"main","last_synced_at":"2026-02-11T14:48:11.369Z","etag":null,"topics":["ai","ai-agents","anthropic","cost-optimization","crypto","deepseek","gemini","llm","llm-router","micropayments","openai","openclaw","smart-routing","usdc","x402"],"latest_commit_sha":null,"homepage":null,"language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/BlockRunAI.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-02-03T17:32:00.000Z","updated_at":"2026-02-11T14:41:30.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/BlockRunAI/ClawRouter","commit_stats":null,"previous_names":["blockrunai/clawrouter"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/BlockRunAI/ClawRouter","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BlockRunAI%2FClawRouter","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BlockRunAI%2FClawRouter/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BlockRunAI%2FClawRouter/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BlockRunAI%2FClawRouter/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/BlockRunAI","download_url":"https://codeload.github.com/BlockRunAI/ClawRouter/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BlockRunAI%2FClawRouter/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29412720,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-13T06:24:03.484Z","status":"ssl_error","status_checked_at":"2026-02-13T06:23:12.830Z","response_time":78,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","ai-agents","anthropic","cost-optimization","crypto","deepseek","gemini","llm","llm-router","micropayments","openai","openclaw","smart-routing","usdc","x402"],"created_at":"2026-02-13T05:00:20.134Z","updated_at":"2026-02-16T13:00:21.036Z","avatar_url":"https://github.com/BlockRunAI.png","language":"TypeScript","funding_links":[],"categories":["Web4 The Money Loop 🔄","AI Agent Frameworks \u0026 SDKs","Skills \u0026 Plugins","🔌 Infrastructure","Self-Hosting","Ecosystem","8. Inference Engines","Deployment und Betrieb","MCP Tools","TypeScript","🔌 Plugins \u0026 Channel Integrations"],"sub_categories":["Multi-Agent Collaboration Systems","Notable Skills \u0026 Plugins","Reverse Proxy \u0026 Networking","Server / Production","Self-Hosted Deployment und Infrastruktur","ClawRouter — Cost Optimizer for Existing API Key Users"],"readme":"![ClawRouter Banner](assets/banner.png)\n\n\u003cdiv align=\"center\"\u003e\n\nRoute every request to the cheapest model that can handle it.\nOne wallet, 30+ models, zero API keys.\n\n[![npm](https://img.shields.io/npm/v/@blockrun/clawrouter.svg)](https://npmjs.com/package/@blockrun/clawrouter)\n[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)\n[![TypeScript](https://img.shields.io/badge/TypeScript-5.7-blue.svg)](https://typescriptlang.org)\n[![Node](https://img.shields.io/badge/node-%E2%89%A520-brightgreen.svg)](https://nodejs.org)\n[![USDC Hackathon Winner](https://img.shields.io/badge/🏆_USDC_Hackathon-Agentic_Commerce_Winner-gold)](https://x.com/USDC/status/2021625822294216977)\n\n[Docs](https://blockrun.ai/docs) \u0026middot; [Models](https://blockrun.ai/models) \u0026middot; [vs OpenRouter](docs/vs-openrouter.md) \u0026middot; [Configuration](docs/configuration.md) \u0026middot; [Features](docs/features.md) \u0026middot; [Troubleshooting](docs/troubleshooting.md) \u0026middot; [Telegram](https://t.me/blockrunAI) \u0026middot; [X](https://x.com/BlockRunAI)\n\n**Winner — Agentic Commerce Track** at the [USDC AI Agent Hackathon](https://x.com/USDC/status/2021625822294216977)\u003cbr\u003e\n_The world's first hackathon run entirely by AI agents, powered by USDC_\n\n\u003c/div\u003e\n\n---\n\n```\n\"What is 2+2?\"            → NVIDIA Kimi     $0.001/M   saved ~100%\n\"Summarize this article\"  → Grok Code Fast  $1.50/M    saved 94%\n\"Build a React component\" → Gemini 2.5 Pro  $10.00/M   best balance\n\"Prove this theorem\"      → Grok 4.1 Fast   $0.50/M    reasoning\n\"Run 50 parallel searches\"→ Kimi K2.5       $2.40/M    agentic swarm\n```\n\n## Why ClawRouter?\n\n- **4 routing profiles** — auto (balanced), eco (95.9-100% savings), premium (best quality), free (zero cost)\n- **100% local routing** — 15-dimension weighted scoring runs on your machine in \u003c1ms\n- **Zero external calls** — no API calls for routing decisions, ever\n- **30+ models** — OpenAI, Anthropic, Google, DeepSeek, xAI, Moonshot through one wallet\n- **x402 micropayments** — pay per request with USDC on Base, no API keys\n- **Open source** — MIT licensed, fully inspectable routing logic\n\n### Ask Your OpenClaw How ClawRouter Saves You Money\n\n\u003cimg src=\"docs/clawrouter-savings.png\" alt=\"ClawRouter savings explanation\" width=\"600\"\u003e\n\n---\n\n## Quick Start (2 mins)\n\n**Inspired by Andreas** — we've updated our installation script:\n\n```bash\n# 1. Install with smart routing enabled by default\ncurl -fsSL https://blockrun.ai/ClawRouter-update | bash\nopenclaw gateway restart\n\n# 2. Fund your wallet with USDC on Base (address printed on install)\n# $5 is enough for thousands of requests\n```\n\nDone! Smart routing (`blockrun/auto`) is now your default model.\n\n### Routing Profiles\n\nChoose your routing strategy with `/model \u003cprofile\u003e`:\n\n| Profile          | Strategy           | Savings   | Use Case                |\n| ---------------- | ------------------ | --------- | ----------------------- |\n| `/model auto`    | Balanced (default) | 74-100%   | Best overall balance    |\n| `/model eco`     | Cost optimized     | 95.9-100% | Maximum savings         |\n| `/model premium` | Quality focused    | 0%        | Best quality (Opus 4.5) |\n| `/model free`    | Free tier only     | 100%      | Zero cost               |\n\n**Other shortcuts:**\n\n- **Model aliases:** `/model br-sonnet`, `/model grok`, `/model gpt5`, `/model o3`\n- **Specific models:** `blockrun/openai/gpt-4o` or `blockrun/anthropic/claude-sonnet-4`\n- **Bring your wallet:** `export BLOCKRUN_WALLET_KEY=0x...`\n\n---\n\n## See It In Action\n\n\u003cdiv align=\"center\"\u003e\n\u003cimg src=\"assets/telegram-demo.png\" alt=\"ClawRouter in action via Telegram\" width=\"500\"/\u003e\n\u003c/div\u003e\n\n**The flow:**\n\n1. **Wallet auto-generated** on Base (L2) — saved securely at `~/.openclaw/blockrun/wallet.key`\n2. **Fund with $1 USDC** — enough for hundreds of requests\n3. **Request any model** — \"help me call Grok to check @hosseeb's opinion on AI agents\"\n4. **ClawRouter routes it** — spawns a Grok sub-agent via `xai/grok-3`, pays per-request\n\nNo API keys. No accounts. Just fund and go.\n\n---\n\n## How Routing Works\n\n**100% local, \u003c1ms, zero API calls.**\n\n```\nRequest → Weighted Scorer (15 dimensions)\n              │\n              ├── High confidence → Pick model from tier → Done\n              │\n              └── Low confidence → Default to MEDIUM tier → Done\n```\n\nNo external classifier calls. Ambiguous queries default to the MEDIUM tier (Grok Code Fast) — fast, cheap, and good enough for most tasks.\n\n**Deep dive:** [15-dimension scoring weights](docs/configuration.md#scoring-weights) | [Architecture](docs/architecture.md)\n\n### Routing Profiles (NEW in v0.8.21)\n\nClawRouter now offers 4 routing profiles to match different priorities:\n\n| Profile            | Strategy                | Savings vs Opus 4.5 | When to Use                   |\n| ------------------ | ----------------------- | ------------------- | ----------------------------- |\n| **auto** (default) | Balanced quality + cost | 74-100%             | General use, best overall     |\n| **eco**            | Maximum cost savings    | 95.9-100%           | Budget-conscious, high volume |\n| **premium**        | Best quality only       | 0%                  | Mission-critical tasks        |\n| **free**           | Free tier only          | 100%                | Testing, empty wallet         |\n\nSwitch profiles anytime: `/model eco`, `/model premium`, `/model auto`\n\n**Example:**\n\n```\n/model eco                    # Switch to cost-optimized routing\n\"Write a React component\"     # Routes to DeepSeek ($0.28/$0.42)\n                              # vs Auto → Grok ($0.20/$1.50)\n                              # 98.3% savings vs Opus 4.5\n```\n\n### Tier → Model Mapping\n\n| Tier      | Primary Model           | Cost/M | Savings vs Opus |\n| --------- | ----------------------- | ------ | --------------- |\n| SIMPLE    | nvidia/kimi-k2.5        | $0.001 | **~100%**       |\n| MEDIUM    | grok-code-fast-1        | $1.50  | **94.0%**       |\n| COMPLEX   | gemini-2.5-pro          | $10.00 | **60.0%**       |\n| REASONING | grok-4-1-fast-reasoning | $0.50  | **98.0%**       |\n\nSpecial rule: 2+ reasoning markers → REASONING at 0.97 confidence.\n\n### Advanced Features\n\nClawRouter v0.5+ includes intelligent features that work automatically:\n\n- **Agentic auto-detect** — routes multi-step tasks to Kimi K2.5\n- **Tool detection** — auto-switches when `tools` array present\n- **Context-aware** — filters models that can't handle your context size\n- **Model aliases** — `/model free`, `/model br-sonnet`, `/model grok`\n- **Session persistence** — pins model for multi-turn conversations\n- **Free tier fallback** — keeps working when wallet is empty\n- **Auto-update check** — notifies you when a new version is available\n\n**Full details:** [docs/features.md](docs/features.md)\n\n### Cost Savings\n\n| Tier                | % of Traffic | Cost/M      |\n| ------------------- | ------------ | ----------- |\n| SIMPLE              | ~45%         | $0.001      |\n| MEDIUM              | ~35%         | $1.50       |\n| COMPLEX             | ~15%         | $10.00      |\n| REASONING           | ~5%          | $0.50       |\n| **Blended average** |              | **$2.05/M** |\n\nCompared to **$25/M** for Claude Opus = **92% savings** on a typical workload.\n\n---\n\n## Models\n\n30+ models across 6 providers, one wallet:\n\n| Model                 | Input $/M | Output $/M | Context | Reasoning |\n| --------------------- | --------- | ---------- | ------- | :-------: |\n| **OpenAI**            |           |            |         |           |\n| gpt-5.2               | $1.75     | $14.00     | 400K    |    \\*     |\n| gpt-4o                | $2.50     | $10.00     | 128K    |           |\n| gpt-4o-mini           | $0.15     | $0.60      | 128K    |           |\n| gpt-oss-120b          | **$0**    | **$0**     | 128K    |           |\n| o3                    | $2.00     | $8.00      | 200K    |    \\*     |\n| o3-mini               | $1.10     | $4.40      | 128K    |    \\*     |\n| **Anthropic**         |           |            |         |           |\n| claude-opus-4.5       | $5.00     | $25.00     | 200K    |    \\*     |\n| claude-sonnet-4       | $3.00     | $15.00     | 200K    |    \\*     |\n| claude-haiku-4.5      | $1.00     | $5.00      | 200K    |           |\n| **Google**            |           |            |         |           |\n| gemini-2.5-pro        | $1.25     | $10.00     | 1M      |    \\*     |\n| gemini-2.5-flash      | $0.15     | $0.60      | 1M      |           |\n| **DeepSeek**          |           |            |         |           |\n| deepseek-chat         | $0.14     | $0.28      | 128K    |           |\n| deepseek-reasoner     | $0.55     | $2.19      | 128K    |    \\*     |\n| **xAI**               |           |            |         |           |\n| grok-3                | $3.00     | $15.00     | 131K    |    \\*     |\n| grok-3-mini           | $0.30     | $0.50      | 131K    |           |\n| grok-4-fast-reasoning | $0.20     | $0.50      | 131K    |    \\*     |\n| grok-4-fast           | $0.20     | $0.50      | 131K    |           |\n| grok-code-fast-1      | $0.20     | $1.50      | 131K    |           |\n| **Moonshot**          |           |            |         |           |\n| kimi-k2.5             | $0.50     | $2.40      | 262K    |    \\*     |\n\n\u003e **Free tier:** `gpt-oss-120b` costs nothing and serves as automatic fallback when wallet is empty.\n\nFull list: [`src/models.ts`](src/models.ts)\n\n### Kimi K2.5: Agentic Workflows\n\n[Kimi K2.5](https://kimi.ai) from Moonshot AI is optimized for agent swarm and multi-step workflows:\n\n- **Agent Swarm** — Coordinates up to 100 parallel agents, 4.5x faster execution\n- **Extended Tool Chains** — Stable across 200-300 sequential tool calls without drift\n- **Vision-to-Code** — Generates production React from UI mockups and videos\n- **Cost Efficient** — 76% cheaper than Claude Opus on agentic benchmarks\n\nBest for: parallel web research, multi-agent orchestration, long-running automation tasks.\n\n---\n\n## Payment\n\nNo account. No API key. **Payment IS authentication** via [x402](https://x402.org).\n\n```\nRequest → 402 (price: $0.003) → wallet signs USDC → retry → response\n```\n\nUSDC stays in your wallet until spent — non-custodial. Price is visible in the 402 header before signing.\n\n**Fund your wallet:**\n\n- Coinbase: Buy USDC, send to Base\n- Bridge: Move USDC from any chain to Base\n- CEX: Withdraw USDC to Base network\n\n---\n\n## Wallet Configuration\n\nClawRouter auto-generates and saves a wallet at `~/.openclaw/blockrun/wallet.key`.\n\n```bash\n# Check wallet status\n/wallet\n\n# Use your own wallet\nexport BLOCKRUN_WALLET_KEY=0x...\n```\n\n**Full reference:** [Wallet configuration](docs/configuration.md#wallet-configuration) | [Backup \u0026 recovery](docs/configuration.md#wallet-backup--recovery)\n\n---\n\n## Architecture\n\n```\n┌─────────────────────────────────────────────────────────────┐\n│                     Your Application                         │\n└─────────────────────────────────────────────────────────────┘\n                              │\n                              ▼\n┌─────────────────────────────────────────────────────────────┐\n│                   ClawRouter (localhost)                     │\n│  ┌─────────────────┐  ┌─────────────────┐  ┌─────────────┐ │\n│  │ Weighted Scorer │→ │ Model Selector  │→ │ x402 Signer │ │\n│  │  (15 dimensions)│  │ (cheapest tier) │  │   (USDC)    │ │\n│  └─────────────────┘  └─────────────────┘  └─────────────┘ │\n└─────────────────────────────────────────────────────────────┘\n                              │\n                              ▼\n┌─────────────────────────────────────────────────────────────┐\n│                      BlockRun API                            │\n│    → OpenAI | Anthropic | Google | DeepSeek | xAI | Moonshot│\n└─────────────────────────────────────────────────────────────┘\n```\n\nRouting is **client-side** — open source and inspectable.\n\n**Deep dive:** [docs/architecture.md](docs/architecture.md) — request flow, payment system, optimizations\n\n---\n\n## Configuration\n\nFor basic usage, no configuration needed. For advanced options:\n\n| Setting               | Default | Description           |\n| --------------------- | ------- | --------------------- |\n| `CLAWROUTER_DISABLED` | `false` | Disable smart routing |\n| `BLOCKRUN_PROXY_PORT` | `8402`  | Proxy port            |\n| `BLOCKRUN_WALLET_KEY` | auto    | Wallet private key    |\n\n**Full reference:** [docs/configuration.md](docs/configuration.md)\n\n---\n\n## Programmatic Usage\n\nUse ClawRouter directly in your code:\n\n```typescript\nimport { startProxy, route } from \"@blockrun/clawrouter\";\n\n// Start proxy server\nconst proxy = await startProxy({ walletKey: \"0x...\" });\n\n// Or use router directly (no proxy)\nconst decision = route(\"Prove sqrt(2) is irrational\", ...);\n```\n\n**Full examples:** [docs/configuration.md#programmatic-usage](docs/configuration.md#programmatic-usage)\n\n---\n\n## Performance Optimizations (v0.3+)\n\n- **SSE heartbeat**: Sends headers + heartbeat immediately, preventing upstream timeouts\n- **Response dedup**: SHA-256 hash → 30s cache, prevents double-charge on retries\n- **Payment pre-auth**: Caches 402 params, pre-signs USDC, skips 402 round trip (~200ms saved)\n- **Response cache**: LLM response caching with 10-minute TTL, saves cost on repeated queries\n\n---\n\n## Cost Tracking\n\nTrack your savings with `/stats` in any OpenClaw conversation.\n\n**Full details:** [docs/features.md#cost-tracking-with-stats](docs/features.md#cost-tracking-with-stats)\n\n---\n\n## Why Not OpenRouter / LiteLLM?\n\nThey're built for developers. ClawRouter is built for **agents**.\n\n|                 | OpenRouter / LiteLLM        | ClawRouter                       |\n| --------------- | --------------------------- | -------------------------------- |\n| **Setup**       | Human creates account       | Agent generates wallet           |\n| **Auth**        | API key (shared secret)     | Wallet signature (cryptographic) |\n| **Payment**     | Prepaid balance (custodial) | Per-request (non-custodial)      |\n| **Routing**     | Proprietary / closed        | Open source, client-side         |\n| **Rate limits** | Per-key quotas              | None (your wallet, your limits)  |\n| **Cost**        | $25/M (Opus equivalent)     | $2.05/M blended average          |\n\nAgents shouldn't need a human to paste API keys. They should generate a wallet, receive funds, and pay per request — programmatically.\n\n### Real Problems with OpenRouter\n\nBased on [50+ OpenClaw issues](https://github.com/openclaw/openclaw/issues?q=openrouter):\n\n| Issue                                                       | Problem                             | ClawRouter                 |\n| ----------------------------------------------------------- | ----------------------------------- | -------------------------- |\n| [#11202](https://github.com/openclaw/openclaw/issues/11202) | API keys leaked in every LLM prompt | No API keys to leak        |\n| [#2373](https://github.com/openclaw/openclaw/issues/2373)   | `openrouter/auto` path broken       | `blockrun/auto` just works |\n| [#8615](https://github.com/openclaw/openclaw/issues/8615)   | Single API key rate limit hell      | Non-custodial, no limits   |\n| [#2963](https://github.com/openclaw/openclaw/issues/2963)   | Tool calling fails silently         | Full tool support          |\n| [#10687](https://github.com/openclaw/openclaw/issues/10687) | \"Unknown model\" errors              | 30+ models, auto-update    |\n\n**[Full comparison →](docs/vs-openrouter.md)**\n\n---\n\n## Why did we build this\n\n- **Agents need to pay and get paid — without humans in the loop.** Today's AI infra requires accounts, API keys, manual billing. But an agent spawning 50 sub-agents shouldn't need a human to provision 50 keys. An agent completing a bounty shouldn't wait for someone to invoice and collect.\n\n- **Payment IS authentication.** A wallet signature proves you can pay — no shared secrets that leak into prompts, no accounts to create, no keys to rotate.\n\n- **Agents should control their own money.** Non-custodial means the agent holds the keys. No platform can freeze funds or change terms overnight.\n\n- **Cost optimization should be automatic.** Agents shouldn't overpay $25/M for \"what is 2+2\". Smart routing to the cheapest capable model saves 92% on typical workloads.\n\nThe result: an agent can generate a wallet, receive funds, call any model, pay per-request, and earn money — all programmatically. **This is agentic commerce.**\n\n---\n\n## Troubleshooting\n\nQuick checklist:\n\n```bash\n# Check version (should be 0.8.21+)\ncat ~/.openclaw/extensions/clawrouter/package.json | grep version\n\n# Check proxy running\ncurl http://localhost:8402/health\n\n# Update to latest version\ncurl -fsSL https://blockrun.ai/ClawRouter-update | bash\nopenclaw gateway restart\n```\n\nClawRouter automatically checks for updates on startup and shows a notification if a newer version is available.\n\n**Full guide:** [docs/troubleshooting.md](docs/troubleshooting.md)\n\n---\n\n## Development\n\n```bash\ngit clone https://github.com/BlockRunAI/ClawRouter.git\ncd ClawRouter\nnpm install\nnpm run build\nnpm run typecheck\n\n# End-to-end tests (requires funded wallet)\nBLOCKRUN_WALLET_KEY=0x... npx tsx test-e2e.ts\n```\n\n---\n\n## Uninstall\n\n```bash\nopenclaw plugins uninstall clawrouter\nopenclaw gateway restart\n```\n\nYour wallet key remains at `~/.openclaw/blockrun/wallet.key` — back it up before deleting if you have funds.\n\n---\n\n## Roadmap\n\n- [x] Smart routing — 15-dimension weighted scoring, 4-tier model selection\n- [x] x402 payments — per-request USDC micropayments, non-custodial\n- [x] Response dedup — prevents double-charge on retries\n- [x] Payment pre-auth — skips 402 round trip\n- [x] SSE heartbeat — prevents upstream timeouts\n- [x] Agentic auto-detect — auto-switch to agentic models for multi-step tasks\n- [x] Tool detection — auto-switch to agentic mode when tools array present\n- [x] Context-aware routing — filter out models that can't handle context size\n- [x] Session persistence — pin model for multi-turn conversations\n- [x] Cost tracking — /stats command with savings dashboard\n- [x] Model aliases — `/model free`, `/model br-sonnet`, `/model grok`, etc.\n- [x] Free tier — gpt-oss-120b for $0 when wallet is empty\n- [x] Auto-update — startup version check with one-command update\n- [x] Response cache — LiteLLM-inspired caching for repeated requests\n- [ ] Cascade routing — try cheap model first, escalate on low quality\n- [ ] Spend controls — daily/monthly budgets\n- [ ] Remote analytics — cost tracking at blockrun.ai\n\n---\n\n## Support / talk with founders\n\n- [Schedule Demo 👋](https://calendly.com/vickyfu9/30min)\n- [Community Telegram 💭](https://t.me/blockrunAI)\n- [X / Twitter 🐦](https://x.com/BlockRunAI)\n- Telegram 📱 [@bc1max](https://t.me/bc1max)\n- Our email ✉️ vicky@blockrun.ai\n\n---\n\n## License\n\nMIT\n\n---\n\n\u003cdiv align=\"center\"\u003e\n\n**[BlockRun](https://blockrun.ai)** — Pay-per-request AI infrastructure\n\nIf ClawRouter saves you money, consider starring the repo.\n\n\u003c/div\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FBlockRunAI%2FClawRouter","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FBlockRunAI%2FClawRouter","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FBlockRunAI%2FClawRouter/lists"}