Antseed Connect

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.

Glossary (mental model)

• Buyer proxy — the local server on localhost:8377 that accepts API calls from your tools and forwards them to AntSeed peers. It is the only thing your editor / agent / SDK ever talks to.

• Peer — someone selling inference. Each peer has a peerId (40-char hex), a display name, and a list of services. List with antseed network browse.

• Service — a single model id like claude-sonnet-4-6 or deepseek-v4-flash. This is what you pass as model in your tool's config. Each service has its own native protocol list and its own in / cachedIn / out pricing.

• Protocols (per service) — the wire formats a service accepts natively, advertised on each peer in providerServiceApiProtocols[provider].services[service]. Values are anthropic-messages, openai-chat-completions, openai-responses, openai-completions. This is the field to match your tool's wire format against. If your tool's wire format is in this list, the request passes through untouched; if not, the api-adapter translates on the fly.

• Cached input pricing — services charge a separate, much lower rate (typically 4–10×) for tokens that are reused across requests: system prompts, tool schemas, prior conversation turns, long files you keep referencing. The CLI exposes it as cachedInputUsdPerMillion. For long-running agents and chatbots, this is often the dominant cost line.

• Pin — telling the buyer proxy "route requests to this peer." In the default manual flow, there is no peer auto-selection; you must choose a peer, send a per-request pin header, or start the proxy with a router plugin that performs selection. Common explicit routes:

  • Session pin: antseed buyer connection set --peer <peerId>. Persists in ~/.antseed/buyer.state.json and applies to every request until you change it.
  • Per-request header: x-antseed-pin-peer: <peerId> on each call. Overrides the session pin for that request, and works without any session pin at all.
  • Model prefix: set model to <peerId>@<service>. The proxy uses the prefix as the peer pin and forwards only <service> to the seller.

  If both header and model-prefix pins are present, the header selects the peer; the model prefix is still stripped before routing. Until at least one of these is in effect, every request returns no_peer_pinned.

Universal setup (do this once)

Option A — VPR desktop app (easiest)

Download from https://antseed.com — it ships the buyer proxy, a wallet, and a peer browser in a GUI. While the app is open the proxy is reachable at http://localhost:8377.

Option B — CLI (headless / servers / agents)

# 1. Install
npm install -g @antseed/cli

# 2. Identity (an EVM private key — 64 hex chars). Save this somewhere safe;
#    you will reuse it across machines and it controls your USDC deposits.
export ANTSEED_IDENTITY_HEX=$(openssl rand -hex 32)
# SECURITY: never paste this key into chat, logs, GitHub issues, or a file
# committed to git. It controls the buyer identity and access to deposits.

# 3. Start the buyer proxy on :8377
antseed buyer start &

# 4. Browse the network and list every service (= model) each peer offers,
#    along with its native protocols and USD-per-1M-tokens pricing.
#    `service` is the model id you pass to your tool. `protocols` is the
#    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 \
  | jq '.peers | map({
      peerId, name: .displayName,
      services: [
        (.providerServiceApiProtocols | to_entries[]) as $p
        | ($p.value.services | to_entries[]) as $s
        | {
            service:  $s.key,
            protocols: $s.value,
            in:       (.providerPricing[$p.key].services[$s.key].inputUsdPerMillion       // .providerPricing[$p.key].defaults.inputUsdPerMillion),
            cachedIn: (.providerPricing[$p.key].services[$s.key].cachedInputUsdPerMillion // null),
            out:      (.providerPricing[$p.key].services[$s.key].outputUsdPerMillion      // .providerPricing[$p.key].defaults.outputUsdPerMillion)
          }
      ]
    })'

# 5. Inspect one peer in detail. Use `matchingServices[]` for pricing/tags and
#    `peer.providerServiceApiProtocols` for native protocol support.
#    `cachedIn` is typically 4–10× cheaper than `in` and often dominates the
#    cost line for long-running agents and chatbots — always include it when
#    comparing peers.
antseed network peer <peerId> --json \
  | jq '{
      peer: (.peer | { peerId, name: .displayName,
                       sessions: .onChainChannelCount,
                       ghosts:   .onChainGhostCount }),
      services: [
        (.peer.providerServiceApiProtocols | to_entries[]) as $p
        | ($p.value.services | to_entries[]) as $s
        | (.matchingServices[] | select(.provider == $p.key and .service == $s.key)) as $m
        | {
            provider: $p.key,
            service: $s.key,
            protocols: $s.value,
            in:       $m.inputUsdPerMillion,
            cachedIn: $m.cachedInputUsdPerMillion,
            out:      $m.outputUsdPerMillion,
            tags:     $m.tags
          }
      ]
    }'

# 6. Pin a peer (session-wide). Until you do, every request returns
#    `no_peer_pinned` UNLESS the request includes an `x-antseed-pin-peer`
#    header (see Per-request peer selection below).
antseed buyer connection set --peer <peerId>

# 7. Verify the proxy advertises the services you expect
curl -s http://localhost:8377/v1/models | jq '.data[].id'

# 8. (Optional) Deposit USDC on Base for paid services
antseed payments  # opens portal at 127.0.0.1:3118?token=<hex> — connect a wallet, deposit USDC

Security notes for agents and deploys

• Treat ANTSEED_IDENTITY_HEX / ~/.antseed/identity.key as a hot wallet key. Never print it, paste it into chat, commit it, or copy it off the buyer host.
• Keep the buyer proxy bound to 127.0.0.1 / localhost. Do not expose :8377 directly to the public internet; use SSH tunnels or a private network if another process must reach it remotely.
• Start with small USDC deposits and conservative reserve caps for autonomous agents. The funding wallet does not need to stay connected after depositing.
• If a tool requires an API key, use a non-secret placeholder such as antseed; the buyer proxy authenticates with the local identity key instead.

Endpoints exposed by the buyer proxy

All four protocols (including legacy openai-completions) are supported by @antseed/api-adapter for translation, but only the three endpoints above are exposed to callers. Translation is automatic: a request that arrives in one format and is routed to a peer whose service advertises a different protocols value is transformed both directions (request and streaming response).

No Authorization header is required by the buyer proxy. It authenticates and pays peers using the local node's identity key and on-chain USDC deposits.

Per-request peer selection (no session pin needed)

Two ways to tell the proxy which peer to use:

1. Session pin — antseed buyer connection set --peer <peerId>. Persists in ~/.antseed/buyer.state.json (pinnedPeerId) and applies to every request until you change it. Best for single-tenant setups (laptops, dedicated agents).
2. Per-request header — send x-antseed-pin-peer: <peerId> on each call. Overrides the session pin for that one request. You do not need to call antseed buyer connection set at all if every request includes this header — the proxy will accept and route them. Best for scripts, schedulers, and multi-tenant deployments that need to fan out to different peers per call.

Example (per-request, no session pin):

curl http://localhost:8377/v1/chat/completions \
  -H 'content-type: application/json' \
  -H 'x-antseed-pin-peer: 4668854ba3e8b094e6f48fbeb59cec1cfde162f2' \
  -d '{ "model": "minimax-m2.7", "messages": [{"role":"user","content":"hi"}] }'

Other optional headers:

• x-antseed-provider: <providerName> — when a peer exposes the same service through more than one seller-plugin (rare), force a specific one. Most tools never need this.

Files the CLI creates in ~/.antseed/

Knowing what lives in ~/.antseed/ matters for backups, container deploys, and debugging. The directory is created on first antseed buyer start (or first run of any antseed command that needs it).

config.json (commonly edited)

{
  "buyer": {
    "proxyPort": 8377,                  // change if 8377 conflicts on the host
    "minPeerReputation": 0,             // optional: raise to filter lower-reputation peers
    "maxPricing": {                     // refuse to route to peers above this rate
      "defaults": { "inputUsdPerMillion": 100, "outputUsdPerMillion": 100 }
    }
  },
  "payments": {
    "preferredMethod": "crypto",
    "crypto": { "chainId": "base-mainnet" }   // or "base-sepolia" for testnet
  },
  "network": { "bootstrapNodes": [] }   // empty = use built-in defaults
}

Edit, then restart the buyer proxy. Do not hardcode contract addresses — the chain preset (base-mainnet / base-sepolia) resolves Deposits, Channels, USDC, and the RPC URL automatically.

buyer.state.json (read-only in practice)

Top-level fields that an agent might want to inspect:

• pinnedPeerId — the currently pinned peer (or null).
• pid / port — the running proxy. If pid is non-null but the process is gone, antseed buyer start will detect the stale lockfile and clean up.
• discoveredPeers — cached peer list from the last DHT browse. Refreshed on antseed network browse.
• peersUpdatedAt, onChainStatsRefreshedAt — cache timestamps (epoch millis).

To force a clean reset of pin + caches without losing your wallet:

antseed buyer stop || true
rm ~/.antseed/buyer.state.json
antseed buyer start &

How to integrate

Below is every integration we currently document. Find your tool, copy the config block, done. If your tool is not listed but accepts a custom OpenAI or Anthropic base URL, follow the closest example (or look at the curl / Raw HTTP entry — the contract is stable).

Claude Code

Anthropic's official CLI agent - launch through AntSeed with antseed claude.

• Category: Coding agents
• Wire format: Anthropic Messages
• Setup time: ~2 min
• Page: https://antseed.com/integrations/claude-code

TL;DR for agents: Prefer antseed claude --model <service-id>. It sets ANTHROPIC_BASE_URL and ANTHROPIC_API_KEY for Claude Code. Manual equivalent: set ANTHROPIC_BASE_URL=http://localhost:8377 and ANTHROPIC_API_KEY=antseed, then run claude --model <service-id>.

Claude Code is the official CLI coding agent from Anthropic. It speaks the Anthropic Messages API natively, so it slots into AntSeed through the antseed claude wrapper or by pointing ANTHROPIC_BASE_URL at your local proxy.

antseed claude resolves the active buyer proxy, sets the placeholder Anthropic API key for the child process, and forwards the rest of your Claude Code flags unchanged. Manual environment variables still work if you want to run claude directly.

No real Anthropic API key is needed - the AntSeed proxy authenticates each request with your local identity (ANTSEED_IDENTITY_HEX) and settles payments on-chain. The ANTHROPIC_API_KEY value is required by the Anthropic SDK only as a non-empty placeholder.

When Claude Code calls the Messages API, the proxy forwards the request to the peer you pinned in step 3 of the setup above. Whichever service ids that peer advertises (visible in antseed network peer <peerId>) become the valid --model values.

Install

• Install Claude Code globally

  npm install -g @anthropic-ai/claude-code
  

• Verify it runs

  claude --version
  

  Example output:

  1.4.2 (Claude Code)
  

Configure

antseed claude --model claude-sonnet-4-6

Recommended: the wrapper reads the active buyer proxy from buyer.state.json or config, sets ANTHROPIC_BASE_URL and ANTHROPIC_API_KEY for Claude Code, and forwards extra Claude args. Add --antseed-base-url http://host:port only when your proxy is somewhere else.

export ANTHROPIC_BASE_URL="http://localhost:8377"
export ANTHROPIC_API_KEY="antseed"

Manual equivalent if you want to run claude directly instead of through antseed claude.

Suggested models: claude-sonnet-4-6, claude-opus-4-7, deepseek-v4-flash

antseed claude --model <service-id> passes the value to Claude Code unchanged. The valid set is whatever your pinned peer advertises - see the discovery commands below.

Test it

• See which models your pinned peer offers

  curl -s http://localhost:8377/v1/models | jq '.data[].id'
  

  Example response:

  "claude-opus-4-7"
  "claude-sonnet-4-6"
  "deepseek-v4-flash"
  "gpt-oss-120b"
  

  These are the only ids that work with --model. To switch peers, run antseed network browse, then antseed buyer connection set --peer <peerId> and re-check this list.

• Start a Claude Code session through the wrapper

  antseed claude --model claude-sonnet-4-6
  

  Manual equivalent after exporting the env vars above: claude --model claude-sonnet-4-6.

Troubleshooting

• "invalid x-api-key" or 401 from Anthropic SDK — antseed claude sets ANTHROPIC_API_KEY=antseed for you. If you run claude directly, set the variable to any non-empty string; the proxy ignores the value.
• Hangs forever on first message — No peer is pinned. Run antseed network browse to see peers, then antseed buyer connection set --peer <peerId>.
• model_not_found for a model name you expected to work — The pinned peer doesn't advertise that service id. Check what it does offer with antseed network peer <peerId> (or curl http://localhost:8377/v1/models). Pin a different peer if needed.
• Want to confirm a request actually went through AntSeed (not Anthropic direct) — After the request completes, run antseed buyer metering - you'll see the channel for the peer Claude Code routed to, with token counts and the USDC settled. antseed buyer status shows the snapshot (pinned peer, active-channel count, deposits).

How Claude Code talks to AntSeed

• Wire format sent by Claude Code: Anthropic Messages (hits /v1/messages on the buyer proxy).
• Best-fit services: any service whose protocols array contains anthropic-messages — that is what the peer advertises as natively-supported, so traffic passes through with zero translation overhead.
• How to check a peer: run antseed network peer <peerId> --json and look at peer.providerServiceApiProtocols[provider].services[service] for each model. The browse command exposes the same field per peer.
• When protocols differ: AntSeed's @antseed/api-adapter translates between Anthropic Messages and the service's native protocol on the fly. So a request from Claude Code can still reach a service that only advertises a different protocol — just with a small transform step.
• Caveat: services whose only advertised protocol is openai-responses require streaming. If Claude Code sends a non-streaming request and the proxy routes it to one of those services, the call fails with HTTP 400: Stream must be set to true. Pick a service whose protocols includes anthropic-messages (or another non-responses protocol) to avoid this.

Links

• Claude Code docs
• AntSeed skill: join-buyer

OpenAI Codex CLI

OpenAI's official CLI coding agent - use antseed codex for per-run proxy config.

• Category: Coding agents
• Wire format: OpenAI Chat Completions
• Setup time: ~2 min
• Page: https://antseed.com/integrations/codex

TL;DR for agents: Prefer antseed codex --model <service-id>. It injects the AntSeed Codex provider for one run using base_url=http://localhost:8377/v1 and wire_api="responses". Manual alternative: create user-level ~/.codex/antseed.config.toml with top-level model/model_provider plus [model_providers.antseed], then run codex --profile antseed.

Codex is OpenAI's terminal coding agent. Recent versions ignore OPENAI_BASE_URL and instead read provider config from Codex settings.

antseed codex supplies that provider config for one run with Codex -c overrides, points it at the active buyer proxy, sets the placeholder API key, and leaves your real CODEX_HOME untouched.

If you prefer a persistent manual setup, create ~/.codex/antseed.config.toml and launch Codex with codex --profile antseed; the wrapper is still the shortest path for one-off sessions.

Install

• Install Codex globally

  npm install -g @openai/codex
  

• Verify it runs

  codex --version
  

Configure

antseed codex --model claude-sonnet-4-6

Recommended: the wrapper resolves the proxy URL, injects an AntSeed model provider with wire_api = "responses", sets ANTSEED_API_KEY=antseed, and forwards extra Codex args. Put child flags after -- when they look like wrapper flags.

# Loaded by: codex --profile antseed
# Set this to a service id returned by http://localhost:8377/v1/models
# after pinning an AntSeed peer.
model = "claude-sonnet-4-6"
model_provider = "antseed"

[model_providers.antseed]
name = "AntSeed"
base_url = "http://localhost:8377/v1"
wire_api = "responses"

Manual profile only: this must be your user-level ~/.codex/antseed.config.toml, then launch with codex --profile antseed. If your buyer proxy uses a non-default port, update base_url to match it. Project-local ./.codex/config.toml provider blocks are ignored by Codex.

GUI:

No real OpenAI key is needed. The AntSeed proxy authenticates with your local buyer identity; the wrapper and manual profile both point Codex at the local proxy instead of OpenAI.

Suggested models: claude-sonnet-4-6, deepseek-v3.1, kimi-k2.5, qwen-3-coder-480b

Pass the peer service id to antseed codex --model <service-id>. For a manual profile, set top-level model = "<service-id>" in ~/.codex/antseed.config.toml or override with codex --profile antseed --model <service-id>.

Test it

• See which service ids your pinned peer exposes

  curl -s http://localhost:8377/v1/models | jq '.data[].id'
  

  Example response:

  "claude-opus-4-7"
  "claude-sonnet-4-6"
  "deepseek-v4-flash"
  "gpt-oss-120b"
  

  Whatever appears here is a valid value for top-level model = ... in ~/.codex/antseed.config.toml (or for codex --profile antseed --model <id>).

• Run Codex through the wrapper

  antseed codex --model deepseek-v4-flash
  

  Manual profile equivalent: codex --profile antseed --model deepseek-v4-flash.

• Verify inference is actually paid through AntSeed

  open http://localhost:3118   # or: antseed buyer status
  

  What to look for after one real prompt:

  Deposits available: 4.289391 USDC → 3.289391 USDC
  Deposits reserved:           0 USDC → 1 USDC
  

  The buyer dashboard at http://localhost:3118 is the authoritative real-time signal: a non-zero Reserved (channel opened) and/or a drop in Available (settled spend) after a real prompt confirms AntSeed served the request. The antseed buyer status CLI output is cached and may lag the dashboard - refresh the web view for confirmation. Do not rely on lsof -i | grep codex or ~/.codex/log/codex-tui.log: Codex keeps persistent TCP connections to Cloudflare/ChatGPT IPs (e.g. 172.64.0.0/13) for non-inference purposes (the cause was not isolated during testing), and the provider=OpenAI lines in the TUI log are not a reliable indicator that inference went to OpenAI - the on-chain numbers can show AntSeed served the request despite that log line.

Troubleshooting

• OPENAI_BASE_URL / OPENAI_API_KEY are being ignored — Expected on recent Codex builds. Use antseed codex --model <service-id> so the wrapper injects the provider config for the current run, or use the manual ~/.codex/antseed.config.toml profile above.
• How can I tell if Codex is actually routing through AntSeed? — Check the buyer dashboard at http://localhost:3118 (or antseed buyer status) after sending a test prompt. Reserved going from $0 to a non-zero value (a channel was opened) and/or Available dropping (spend settled) confirms AntSeed served the request. If both stay flat after a real prompt, the profile is not being applied. Do not trust lsof connections to Cloudflare IPs or provider=OpenAI lines in ~/.codex/log/codex-tui.log - neither is a reliable routing signal.
• Codex prints Ignored unsupported project-local config keys … model_provider, model_providers — Provider settings must live in your user-level Codex profile file. For this manual flow, put the top-level model, model_provider, and [model_providers.antseed] block in ~/.codex/antseed.config.toml, then relaunch with codex --profile antseed. Codex silently rejects provider blocks in project-local ./.codex/config.toml and falls back to its default provider.
• Hand-written Codex -c provider overrides behave inconsistently — Use antseed codex --model <service-id> so AntSeed supplies the complete provider block (base_url, wire_api, and model_provider) for the current run. If managing config yourself, keep the full provider/profile in user-level ~/.codex/antseed.config.toml.
• Streaming stops after the first chunk with a manual profile — Use antseed codex, or set wire_api = "responses" in the manual [model_providers.antseed] block.
• unknown profile: antseed — Codex caches profile config on launch. Make sure you saved ~/.codex/antseed.config.toml, then start a fresh codex --profile antseed session.
• Hangs forever on first message — No peer is pinned. Run antseed network browse, then antseed buyer connection set --peer <peerId>.

How OpenAI Codex CLI talks to AntSeed

• Wire format sent by OpenAI Codex CLI: OpenAI Chat Completions (hits /v1/chat/completions on the buyer proxy).
• Best-fit services: any service whose protocols array contains openai-chat-completions — that is what the peer advertises as natively-supported, so traffic passes through with zero translation overhead.
• How to check a peer: run antseed network peer <peerId> --json and look at peer.providerServiceApiProtocols[provider].services[service] for each model. The browse command exposes the same field per peer.
• When protocols differ: AntSeed's @antseed/api-adapter translates between OpenAI Chat Completions and the service's native protocol on the fly. So a request from OpenAI Codex CLI can still reach a service that only advertises a different protocol — just with a small transform step.
• Caveat: services whose only advertised protocol is openai-responses require streaming. If OpenAI Codex CLI sends a non-streaming request and the proxy routes it to one of those services, the call fails with HTTP 400: Stream must be set to true. Pick a service whose protocols includes openai-chat-completions (or another non-responses protocol) to avoid this.

Links

• Codex repo
• Codex sample config

OpenCode

Open-source AI coding agent - launch through AntSeed with antseed opencode.

• Category: Coding agents
• Wire format: OpenAI Chat Completions
• Setup time: ~2 min
• Page: https://antseed.com/integrations/opencode

TL;DR for agents: Prefer antseed opencode --model <service-id>. It creates a temporary OpenCode provider config using npm="@ai-sdk/openai-compatible", baseURL="http://localhost:8377/v1", apiKey="antseed", and one model entry. Manual alternative: put the same provider in opencode.json and run opencode.

OpenCode is an MIT-licensed terminal coding agent built on the Vercel AI SDK. It supports 75+ providers out of the box and lets you register custom ones via opencode.json.

antseed opencode creates that custom provider config in a temporary opencode.json, points OpenCode at it for the child process, and deletes it when the session exits. Manual project or global config still works if you want OpenCode to remember AntSeed outside the wrapper.

AntSeed plugs in as a custom provider using the @ai-sdk/openai-compatible adapter - the same one OpenCode recommends for any OpenAI-compatible endpoint (LM Studio, llama.cpp, Atomic Chat, etc.). No ANTHROPIC_BASE_URL: OpenCode reads provider config from JSON.

Each model you want to use must be listed under models. The id has to match what the buyer proxy returns from GET /v1/models - i.e. a service id advertised by your currently-pinned peer.

Install

• Install OpenCode

  npm install -g opencode-ai
  

• Verify it runs

  opencode --version
  

Configure

antseed opencode --model gpt-oss-120b

Recommended: the wrapper resolves the proxy URL, writes a temporary OpenCode config with one AntSeed model, sets OPENCODE_CONFIG for the child process, and forwards extra OpenCode args.

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "antseed": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "AntSeed (peer-to-peer)",
      "options": {
        "baseURL": "http://localhost:8377/v1",
        "apiKey": "antseed"
      },
      "models": {
        "claude-sonnet-4-6":  { "name": "Claude Sonnet 4.6 (via AntSeed)" },
        "deepseek-v4-flash":  { "name": "DeepSeek v4 Flash (via AntSeed)" },
        "gpt-oss-120b":       { "name": "gpt-oss 120B (via AntSeed)" }
      }
    }
  }
}

Manual equivalent if you want OpenCode to keep AntSeed in its normal project or global config.

Suggested models: claude-sonnet-4-6, claude-opus-4-7, deepseek-v4-flash, gpt-oss-120b

antseed opencode --model <service-id> generates a temporary config for that one id. In manual config, the keys under models must exactly match service ids returned by curl http://localhost:8377/v1/models.

Test it

• Confirm the proxy lists the same ids your config references

  curl -s http://localhost:8377/v1/models | jq '.data[].id'
  

  Example response:

  "claude-opus-4-7"
  "claude-sonnet-4-6"
  "deepseek-v4-flash"
  "gpt-oss-120b"
  

  Add or remove entries under models in opencode.json so they match this list.

• Launch OpenCode through the wrapper

  antseed opencode --model gpt-oss-120b
  

  Extra OpenCode args are forwarded, so antseed opencode --model gpt-oss-120b run works too. Manual config equivalent: run opencode, then pick one of the AntSeed entries from /models.

Troubleshooting

• AntSeed doesn't appear in /connect or /models — With antseed opencode, pass the service id via --model; the wrapper supplies a temporary config. With manual config, make sure opencode.json is in your project root (or ~/.config/opencode/opencode.json) and that the JSON is valid - a stray comma silently disables the whole provider.
• Model is listed but every call returns model_not_found — The pinned peer doesn't advertise that service id. Run antseed network peer <peerId> to see what it actually offers, or pin a different peer.
• OpenCode prompts for an API key — The proxy ignores auth, but the AI SDK sometimes asks anyway. Either skip the prompt (press enter on empty input) or set "apiKey": "antseed" inside options in opencode.json.

How OpenCode talks to AntSeed

• Wire format sent by OpenCode: OpenAI Chat Completions (hits /v1/chat/completions on the buyer proxy).
• Best-fit services: any service whose protocols array contains openai-chat-completions — that is what the peer advertises as natively-supported, so traffic passes through with zero translation overhead.
• How to check a peer: run antseed network peer <peerId> --json and look at peer.providerServiceApiProtocols[provider].services[service] for each model. The browse command exposes the same field per peer.
• When protocols differ: AntSeed's @antseed/api-adapter translates between OpenAI Chat Completions and the service's native protocol on the fly. So a request from OpenCode can still reach a service that only advertises a different protocol — just with a small transform step.
• Caveat: services whose only advertised protocol is openai-responses require streaming. If OpenCode sends a non-streaming request and the proxy routes it to one of those services, the call fails with HTTP 400: Stream must be set to true. Pick a service whose protocols includes openai-chat-completions (or another non-responses protocol) to avoid this.

Links

• OpenCode docs → Custom provider
• OpenCode repo

Pi

Open-source terminal coding agent with a first-class AntSeed extension.

• Category: Coding agents
• Wire format: OpenAI Responses
• Setup time: ~3 min
• Page: https://antseed.com/integrations/pi

TL;DR for agents: Install Pi: npm install -g @mariozechner/pi-coding-agent. Install the AntSeed extension: pi install git:github.com/AntSeed/pi-antseed. Restart or /reload. The extension calls pi.registerProvider("antseed", { api: "openai-responses", baseUrl: "http://localhost:8377/v1" }) and auto-discovers models from the pinned peer via GET /v1/models. Switch with /model antseed/<service-id>. Override base URL with ANTSEED_BASE_URL env var; auth with ANTSEED_API_KEY.

What Pi is. Pi (@mariozechner/pi-coding-agent) is a minimal, hackable terminal coding agent by Mario Zechner - the same lineage as pi-mono. It ships with four default tools (read, write, edit, bash) and lets you extend everything else - commands, providers, themes, even the editor UI - through TypeScript extensions, skills, and prompt templates. No fork required.

What the AntSeed extension does. pi-antseed is a Pi extension that registers the local buyer proxy as a Pi provider named antseed. Once installed, every service your pinned peer advertises shows up under antseed/<id> in Pi's model picker (Ctrl+L or /model) - you switch with /model antseed/minimax-m2.7 just like any built-in.

Why an extension instead of env vars. Pi already speaks dozens of provider protocols natively. The extension calls pi.registerProvider("antseed", { api: "openai-responses", authHeader: true, baseUrl: "http://localhost:8377/v1" }) - Pi then handles auth headers, streaming, retries, and tool-calling. The Responses API path preserves reasoning items across turns for reasoning-capable models, while the extension still auto-refreshes the model list from GET /v1/models so the menu reflects what your pinned peer can serve.

Install

• Install Pi itself (the coding agent CLI)

  npm install -g @mariozechner/pi-coding-agent
  

  Pi requires Node.js 20+. The binary is pi. Verify with pi --version. Without any extensions, Pi can already talk to Claude / GPT / Gemini / Groq / etc. via API key or OAuth - the AntSeed extension below is what teaches it to route through your local buyer proxy.

• Install the AntSeed extension into Pi

  pi install git:github.com/AntSeed/pi-antseed
  

  Pi extensions install from a git URL or a local path. Alternatives: pi -e git:github.com/AntSeed/pi-antseed runs the extension once without installing, useful for trying it out. pi install ./pi-antseed works from a local clone.

• Reload Pi so the new provider is picked up

  /reload
  

  Run this inside the Pi REPL (after typing pi to launch it). It re-scans extensions, skills, prompt templates, keybindings, and context files. A full restart works too.

Configure

export ANTSEED_BASE_URL="http://localhost:8377/v1"

GUI:

No GUI config needed in the common case - the extension reads ANTSEED_BASE_URL (default http://localhost:8377/v1) and discovers models from the pinned peer automatically. Only set ANTSEED_API_KEY if you front the buyer proxy with your own auth layer, or ANTSEED_MODELS="id1,id2" to skip discovery and register a fixed list.

Suggested models: minimax-m2.7, claude-sonnet-4-6, deepseek-v4-flash, qwen3-coder-480b

The extension auto-discovers from GET /v1/models after Pi loads, so anything your pinned peer advertises shows up under antseed/.... After re-pinning a different peer, run /reload in Pi to refresh the model list.

Test it

• Launch Pi

  pi
  

  You'll see Pi's startup header, which lists loaded extensions. Look for antseed (or pi-antseed) in that list - if it's there, the extension loaded successfully.

• Open the model picker and pick an AntSeed-routed model

  /model
  

  Or press Ctrl+L. The picker is fuzzy-searchable; type "antseed" to filter. You should see entries like antseed/claude-sonnet-4-6, antseed/deepseek-v4-flash, etc. - one for each service your pinned peer advertises.

• Or switch directly via slash command

  /model antseed/minimax-m2.7
  

  Replace minimax-m2.7 with any id from curl http://localhost:8377/v1/models. After this, every prompt routes through AntSeed → your pinned peer → the model.

Troubleshooting

• pi: command not found after install — Your global npm bin is not on PATH. Run npm prefix -g to find it, then add <that-path>/bin to PATH in your shell rc. Or use a Node version manager (nvm, fnm, volta) which handles this automatically.
• antseed doesn't appear in the model picker (/model or Ctrl+L) — The extension didn't load. Re-run pi install git:github.com/AntSeed/pi-antseed, restart Pi, and watch the startup header - it lists every loaded extension and surfaces load errors there.
• Picker only shows a few hard-coded antseed/... ids, not what my peer offers — Pi started before the buyer proxy was up, so the extension fell back to its built-in seed list. Make sure antseed buyer start is running and a peer is pinned, then run /reload inside Pi to refresh the model list.
• Empty /v1/models from the proxy — No peer is connected. Run antseed network browse to see options, then antseed buyer connection set --peer <peerId>. Or launch the proxy with antseed buyer start --router <name> for automatic peer selection.
• 5xx from the proxy mid-conversation — Usually means the pinned peer doesn't offer the model you asked for, or has just gone offline. Re-pin via antseed buyer connection set --peer <peerId> and /reload in Pi.
• Want to use a custom buyer proxy URL (remote host, custom port) — Set ANTSEED_BASE_URL=http://your-host:8377/v1 in the shell that launches pi. The extension reads this on startup. If your proxy is fronted by auth, also set ANTSEED_API_KEY=<token>.

How Pi talks to AntSeed

• Wire format sent by Pi: OpenAI Responses (hits /v1/responses on the buyer proxy).
• Best-fit services: any service whose protocols array contains openai-responses — that is what the peer advertises as natively-supported, so traffic passes through with zero translation overhead.
• How to check a peer: run antseed network peer <peerId> --json and look at peer.providerServiceApiProtocols[provider].services[service] for each model. The browse command exposes the same field per peer.
• When protocols differ: AntSeed's @antseed/api-adapter translates between OpenAI Responses and the service's native protocol on the fly. So a request from Pi can still reach a service that only advertises a different protocol — just with a small transform step.

Links

• Pi coding agent (npm)
• Pi source (badlogic/pi-mono)
• pi-antseed extension

OpenClaw

Open-source autonomous agent runtime - register AntSeed as a custom provider in openclaw.json.

• **Ca

…(truncated)