Integrations

Every agent harness and framework BlockRun plugs into — the setup for each, paid per call in USDC over x402 with no API keys.

• Claude Code

  Install the BlockRun MCP in Claude Code and it can call every frontier model, generate images and video and pull live data — no API keys, pay per call.

• Claude Desktop

  One entry in claude_desktop_config.json gives Claude Desktop every BlockRun model, media generation and live data — no API keys, priced before it runs.

• Cursor

  Point Cursor's mcp.json at the BlockRun MCP server and its agent can call any frontier model, generate media and pull live data — no keys, pay per call.

• OpenAI Codex

  clawrouter-codex translates Codex's Responses API onto BlockRun chat completions, so Codex runs on any model in the catalog — no OpenAI key, priced per call.

• OpenClaw

  ClawRouter is the open-source model router built for OpenClaw: install the plugin, run /model blockrun/auto and each request goes to the model that fits it.

• Nous Research Hermes

  hermes-plugin-clawrouter replaces one provider block per lab with one local endpoint: a Hermes agent reaches every BlockRun model — one wallet, no keys.

• DeepSeek Harness

  dsh-clawrouter wires DeepSeek's open-source harness to ClawRouter: every model from one endpoint, and a stronger model reviews flagged tool calls first.

• ElizaOS

  @blockrun/elizaos-plugin gives ElizaOS agents every BlockRun model through one plugin entry — no per-provider API keys, each call priced before it runs.

• LangChain

  Run the blockrun-litellm sidecar and point LangChain's ChatOpenAI at it: every catalog model with tools, streaming and async — no provider keys, pay per call.

• LiteLLM

  blockrun-litellm adds BlockRun as a LiteLLM provider and ships an OpenAI-compatible proxy: every model, one wallet, no provider keys, payment signed locally.

• OpenAI Agents SDK

  Point the OpenAI Agents SDK at the blockrun-litellm sidecar and its agents run on any catalog model — OpenAI's, Anthropic's, open-weight — with no OpenAI key.

• Vercel AI SDK

  Call every BlockRun model from a Vercel AI SDK app with the @blockrun/llm TypeScript client, or via an OpenAI-compatible provider pointed at a local sidecar.

• Coinbase AgentKit

  An AgentKit agent already holds on-chain assets; add the BlockRun Python SDK and every catalog model is one call away, paid from the same wallet, no keys.

• GOAT SDK

  Use GOAT SDK for cross-chain execution and the @blockrun/llm client for reasoning: every catalog model from one client, no provider keys, priced per call.

• Windsurf

  Add the BlockRun MCP server to Windsurf's mcp_config.json and Cascade can call any frontier model, generate media and read live data — no keys, pay per call.

• Cline

  Add BlockRun to Cline's MCP settings and the VS Code agent can call any frontier model, generate media and pull live data — no provider keys, pay per call.

• Aider

  Point aider's OpenAI base URL at the blockrun-litellm sidecar and it pair-programs on any catalog model — switch with one flag, no provider key, pay per call.

• Mastra

  Point an OpenAI-compatible AI SDK provider at the blockrun-litellm sidecar and a Mastra agent runs on any catalog model, with typed tools for images and search.

• CrewAI

  CrewAI's LLM class takes a base URL; point it at the blockrun-litellm sidecar and every agent in a crew picks its own model — no provider keys, pay per call.

• Continue

  Set Continue's OpenAI provider apiBase to the blockrun-litellm sidecar and chat, edit and autocomplete can use any catalog model — one YAML block each, no key.

• Zed

  Point Zed's OpenAI provider api_url at the blockrun-litellm sidecar and the assistant chats and edits with any catalog model — fast inline, frontier for agents.

• Claude Agent SDK

  Add the BlockRun MCP server to a Claude Agent SDK agent's options and it can call any catalog model, generate media and read live data — no keys, pay per call.

• n8n

  Point n8n's OpenAI credential base URL at BlockRun's API-key endpoint and every workflow can call any catalog model from one credential, on one invoice.

• Dify

  Set Dify's OpenAI-API-compatible provider to BlockRun's API-key endpoint and every app, agent and workflow in the workspace picks any model, one invoice.