more-pi

OpenClaw-flavored wrapper for pi. It launches @earendil-works/pi-coding-agent with an extension that registers OpenClaw Codex, Gemini CLI, and Ollama Cloud providers.

Usage

more-pi --provider openclaw-codex --model gpt-5.5
more-pi --provider ollama-cloud --model qwen3.5:397b-cloud

The OpenClaw Codex provider reads credentials from:

~/.openclaw/agents/main/agent/auth-profiles.json

Override the path with:

OPENCLAW_AUTH_PROFILES_PATH=/path/to/auth-profiles.json more-pi

Ollama Cloud

Ollama Cloud connects directly to https://ollama.com/v1 (no local Ollama server required).

Setup

1. Get an API key from ollama.com
2. Configure via one of:
   • /login in Pi → API key → Ollama Cloud
   • export OLLAMA_API_KEY="your-key"
   • Multiple keys with automatic rotation:

export OLLAMA_API_KEYS="key-one,key-two,key-three"

• ~/.pi/agent/auth.json (comma-separated keys also work in the key field):

{
  "ollama-cloud": {
    "type": "api_key",
    "key": "your-key"
  }
}

3. Refresh models (optional — baked-in list ships with the extension):

/ollama-cloud-refresh

Pi TUI

more-pi --provider ollama-cloud --model <model-id>

Use /model or Ctrl+L to pick any Ollama Cloud model under the ollama-cloud provider.

OpenAI-compatible endpoint

Start a universal OpenAI-compatible HTTP server that routes to Codex, Gemini CLI, Ollama Cloud, and Pi built-in providers (OpenRouter, Groq, DeepSeek, etc.):

# Core OpenAI-compatible mode
more-pi --mode endpoint --port 8888

# VS Code Copilot custom endpoint mode (optimized streaming)
more-pi --mode vscode --port 8888

# Ollama-compatible mode — auto model discovery in VS Code (recommended)
more-pi --ollama

--ollama listens on port 11434 by default (Ollama's default). Stop a local Ollama server first, or use --port 11435 and set VS Code's Ollama endpoint accordingly.

Ollama mode endpoints (VS Code auto-discovery)

Route	Method	Description
/api/version	GET	Ollama version check (VS Code requires ≥ 0.6.4)
/api/tags	GET	Native Ollama model list
/api/show	POST	Model capabilities (tools, vision, context length)
/v1/chat/completions	POST	OpenAI-compatible chat
/v1/models	GET	OpenAI-compatible model list
/health	GET	Health check

Endpoints (core / vscode modes)

Route	Method	Description
/v1/chat/completions	POST	Chat completions for any available model
/v1/models	GET	List all available models across providers
/health	GET	Health check

API key detection

Provider credentials are resolved per backend:

Provider	Env var	auth.json key
Ollama Cloud	OLLAMA_API_KEY or OLLAMA_API_KEYS	ollama-cloud
OpenRouter	OPENROUTER_API_KEY or OPENROUTER_API_KEYS	openrouter
OpenAI	OPENAI_API_KEY	openai
Other Pi providers	See pi-ai env map	provider id

All providers also accept Authorization: Bearer <key> from the client (used by VS Code).

Multi-key rotation (Ollama Cloud + OpenRouter)

When you configure multiple API keys, more-pi automatically rotates to the next key when one hits a rate limit. There is no usage API for these providers, so limits are tracked heuristically:

Provider	Tracked windows	Default cooldown
Ollama Cloud	5-hour session + weekly	5 hours / 7 days
OpenRouter	Daily (UTC)	Until next UTC midnight

export OLLAMA_API_KEYS="key1,key2,key3"
export OPENROUTER_API_KEYS="key1,key2"
more-pi --mode endpoint --port 8888

On HTTP 429 / rate-limit errors (before any response content is sent), the server marks that key as cooling down and retries with the next key. State is persisted in ~/.pi/agent/cache/api-key-pool.json across restarts.

Optional tuning:

export MORE_PI_OLLAMA_SESSION_WINDOW_MS=18000000   # 5 hours
export MORE_PI_OLLAMA_WEEKLY_WINDOW_MS=604800000   # 7 days

Ollama Cloud models appear in /v1/models when their credentials are configured, or when a Bearer token is sent with the request. On server start, each Ollama Cloud model is probed with a minimal API request; models that return a subscription-required error are hidden from the model list.

VS Code setup (recommended: Ollama mode)

VS Code's built-in Ollama provider auto-discovers models via /api/tags and /api/show. Use --ollama instead of Custom Endpoint:

1. Stop local Ollama if it is using port 11434 (or pick another port with --port)
2. Configure provider keys (OLLAMA_API_KEY, auth.json, etc.)
3. Run:

more-pi --ollama

4. In VS Code: Chat: Manage Language Models → Add Models → Ollama
5. Endpoint: http://localhost:11434 (or your host/port)
6. All configured models appear automatically — no chatLanguageModels.json editing

pi-coding-agent setup (another Pi instance via Ollama endpoint)

When a second pi-coding-agent instance connects to more-pi --ollama, it must declare vision support in ~/.pi/agent/models.json. Pi defaults custom models to text-only (input: ["text"]), which causes the agent to reject images with "model does not support images" before the request reaches more-pi.

Generate a ready-to-use config (includes "input": ["text", "image"] for vision-capable models and "reasoning": true with thinkingLevelMap for thinking models):

more-pi --pi-models-config --host http://localhost:11434 > ~/.pi/agent/models.json

Without this, pi defaults custom models to text-only and non-reasoning, so images and thinking levels are rejected before requests reach more-pi.

Set provider keys (OPENCLAW_API_KEY, OLLAMA_API_KEY, auth.json, etc.) before generating so all backends appear. Re-run after adding providers.

VS Code setup (Custom Endpoint — manual model list)

VS Code's Custom Endpoint provider (vendor: "customendpoint") does not auto-fetch models from GET /v1/models. That is a VS Code limitation: each model must be listed manually in chatLanguageModels.json with toolCalling, vision, and token limits. more-pi already serves /v1/models, but VS Code ignores it for custom endpoints.

1. Run more-pi --mode vscode --port 8888
2. Generate a VS Code config from your configured providers:

more-pi --vscode-config --host http://192.168.8.3:8888 > chatLanguageModels.json

Set OLLAMA_API_KEY (and other provider keys in auth.json or env) before running --vscode-config so Ollama Cloud and other backends appear in the output. Re-run after adding providers or refreshing models.

3. Copy the generated JSON into VS Code's chatLanguageModels.json (opened via Chat: Manage Language Models), set apiKey if needed, and reload the window.
4. Pick a model from the model picker.

Important: Use per-model url values pointing at http://<host>:<port>/v1/chat/completions. Do not rely on a provider-level url alone — VS Code will not discover models from more-pi's /v1/models endpoint for customendpoint.

Models need "toolCalling": true to appear in the VS Code model picker.

Package behavior

• Does not patch @earendil-works/pi-ai or @earendil-works/pi-coding-agent.
• Reuses pi's built-in openai-codex-responses and openai-completions transports.
• Mirrors the installed pi-ai openai-codex model list into openclaw-codex at extension load time.
• Ships a baked-in Ollama Cloud model list; run /ollama-cloud-refresh for the latest catalog.
• Can also be installed as a pi package; its pi.extensions manifest points at dist/extension.js.

Development

pnpm run build
pnpm publish