antseed-connect
Connect coding agents, AI SDKs, and LLM tools to the AntSeed buyer proxy. Use when configuring Claude Code, Codex, OpenCode, Pi, OpenClaw, Hermes, GenLayer Studio, Vercel AI SDK, LangChain, or raw HTTP to route inference through AntSeed at localhost:8377.
Profile →npx skills add internet-court/internet-court-skill --skill antseed-connect --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
The skill explains how to wire a variety of AI tools and coding agents to the AntSeed buyer proxy at localhost:8377. It treats AntSeed as the local endpoint that translates and routes requests to peers on the network, enabling usage through multiple protocols and services.
How it works
- Describes AntSeed as a peer-to-peer marketplace with a local buyer proxy exposing endpoints at http://localhost:8377 for Anthropic Messages, OpenAI Chat Completions, and OpenAI Responses. It notes translation via @antseed/api-adapter when needed.
- Defines the role of the buyer proxy, peers, services, and protocols, including how to match tool wire formats to service protocols.
- Provides commands and steps to install and run the AntSeed CLI, start the proxy, browse peers, inspect services, pin a peer, and verify models via /v1/models.
- Details per-request and session-based peer selection, including header x-antseed-pin-peer and model-prefix pinning.
- Lists CLI-created files under ~/.antseed/ and describes configuration options in config.json, including buyer.proxyPort and pricing defaults.
- Includes integration guidance for Claude Code with environment variable setup (ANTHROPIC_BASE_URL, ANTHROPIC_API_KEY) and the antseed claude wrapper.
When to use it
Use when configuring any supported coding agents or SDKs to route inference through AntSeed at localhost:8377, and when you need to map models, protocols, and pricing to the AntSeed network. Also used to set up authentication and daily operation through the local buyer proxy.
What it can touch
- Tools and scripts listed under integration sections (e.g., Claude Code via antseed claude). It references commands and environment variables like
antseed claude,CLAUDE-related model identifiers, andANTHROPIC_BASE_URL/ANTHROPIC_API_KEY. - Endpoints exposed by the buyer proxy: POST /v1/messages, POST /v1/chat/completions, POST /v1/responses.
Caveats
- Emphasizes local usage with localhost binding and advises against exposing the proxy publicly.
- Notes that payments use the local identity key and on-chain USDC deposits; keys must be kept secure.
- Contains extensive setup steps and example commands; no guarantees of specific outcomes beyond the described wiring and configuration.
# AntSeed — Integration Skill > This file is the agent-readable companion to https://antseed.com/integrations. > It tells any AI agent (Claude, Codex, OpenClaw, Hermes, custom) exactly > how to wire its tool of choice up to the AntSeed peer-to-peer inference network. ## What is AntSeed? AntSeed is a peer-to-peer marketplace for AI inference. Buyers run a small local daemon (the **buyer proxy**) that exposes an HTTP API at `http://localhost:8377` speaking the three caller-facing LLM API protocols: Anthropic Messages, OpenAI Chat Completions, and OpenAI Responses. Legacy OpenAI Completions is supported internally for adapter translation. The proxy discovers providers on a DHT, routes the request to a peer, translates between protocols when needed (via `@antseed/api-adapter`), and settles in USDC on Base. Important: AntSeed is for value-added AI services (specialized models, agents, TEEs, fine-tunes, managed workflows), not raw resale of API keys or subscription access. Providers must comply with upstream terms of service. From the perspective of any tool, SDK, or agent, **AntSeed is just a local OpenAI/Anthropic-compatible endpoint** — point a `base_url` at it and you are done. ## Gl
- What is AntSeed?
- Glossary (mental model)
- Universal setup (do this once)
- Option A — AntStation desktop app (easiest)
- Option B — CLI (headless / servers / agents)
- Security notes for agents and deploys
- Endpoints exposed by the buyer proxy
- Per-request peer selection (no session pin needed)
- Files the CLI creates in ~/.antseed/
- config.json (commonly edited)
- buyer.state.json (read-only in practice)
- How to integrate <your tool>
- Claude Code
- OpenAI Codex CLI
npm install -g @antseed/cli you will reuse it across machines and it controls your USDC deposits. export ANTSEED_IDENTITY_HEX=$(openssl rand -hex 32) committed to git. It controls the buyer identity and access to deposits. antseed buyer start & along with its native protocols and USD-per-1M-tokens pricing. wire format(s) the service accepts natively — match it against your tool. `in` / `cachedIn` / `out` are fresh-input / cached-input / output. antseed network browse --json --top 5 \ cost line for long-running agents and chatbots — always include it when
What does the antseed-connect skill do?
Connect coding agents, AI SDKs, and LLM tools to the AntSeed buyer proxy. Use when configuring Claude Code, Codex, OpenCode, Pi, OpenClaw, Hermes, GenLayer Studio, Vercel AI SDK, LangChain, or raw HTTP to route inference through AntSeed at localhost:8377.
How do I install it?
Run `npx skills add internet-court/internet-court-skill --skill antseed-connect --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From internet-court/internet-court-skill, a repository with 1,536 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.