@juicesharp/rpiv-web-tools
Pi extension. Web search and fetch for the model with pluggable providers (Brave, Tavily, Serper, Exa, You.com, Jina, Firecrawl, Perplexity, SearXNG, Ollama).
$ pi install npm:@juicesharp/rpiv-web-toolsPackage Catalog
Extensions, skills, prompt templates, and themes published to npm. Install with pi install npm:<package>. See the package docs for details.
Recently published
@narumitw/pi-goalPi extension for autonomous single-objective /goal completion.14m agopi-browser-harnessBrowser control extension for pi — navigate, click, type, screenshot, and extract data from real Chrome via CDP15m ago@workit-dev/piWorkit native extension for Pi — tools, method skills, and session continuity16m agodesign-compareDesign comparison MCP server and Pi extension with structural, perceptual, strict, and iPad layout-integrity modes26m ago@nathan33/nao-skillnao 多角色 AI 开发舰队（仅 pi）：角色卡 / 技能 / 协作协议 / 工具链，一键接入项目28m agopi-tidyTool folding for the pi agent — a reply's tool calls collapse to one clickable line; failures, edit diffs and running jobs stay visible31m ago@piagent/platformGuardrails and managed team harness for AI coding agents, with isolated tools, scoped approvals, and a local dashboard.34m agopi-workbuddy-hubWorkBuddy（CodeBuddy）一体化中枢：内置 provider（国内/国际双区域）+ 多账号签到、切换、限流自动换号42m ago
All packages
1-44 / 44 (of 5444)
@ollama/pi-web-search
Web search and fetch tools for Pi agent - uses Ollama's web search and fetch APIs
$ pi install npm:@ollama/pi-web-search@chankov/agent-fleet
Subagent orchestration for the pi coding agent — a thin dispatcher runs parallel subagents under a verification contract, keeping their output out of its context window. Multi-agent fleets, 15 personas, skills, herdr panes, peer coms, Hermes desktop.
$ pi install npm:@chankov/agent-fleetpi-ollama-cloud
An [Ollama Cloud](https://ollama.com) provider extension for the [Pi](https://pi.dev) coding agent. It connects directly to Ollama Cloud, so no local Ollama server is required.
$ pi install npm:pi-ollama-cloudpi-multi-account
Automatic multi-account failover & rotation for Pi Agent across Anthropic (Claude), native OpenAI ChatGPT and legacy Codex, Kimi For Coding, Cursor, Qwen/Alibaba, and Ollama. Auto-discovers authenticated accounts, grows the rotation on login, and drops ac
$ pi install npm:pi-multi-accountpi-better-web-search
A better provider-native web_search tool for pi: raw results, automatic provider fallback, URL analysis, and native DeepSeek Search/Fetch.
$ pi install npm:pi-better-web-searchpi-ghost-autocomplete
Inline ghost-text autocomplete extension for the Pi coding agent (pi.dev). Cloud and local LLM providers, zero-flicker rendering, no popup interference.
$ pi install npm:pi-ghost-autocompletepi-model-config
Add a Pi model endpoint from a URL and a key, then keep it in sync: context window, output limit, reasoning, vision and thinking levels are inferred from the endpoint itself, then models.dev, then the model name — then re-added, pruned or repaired on dema
$ pi install npm:pi-model-config@freibergergarcia/phone-a-friend
CLI relay that lets AI coding agents collaborate
$ pi install npm:@freibergergarcia/phone-a-friend@buyong/pi-ollama-cloud
Ollama Cloud provider, web search and fetch tools, and usage status for Pi.
$ pi install npm:@buyong/pi-ollama-cloud@indexyz/pi-custom-provider
A generic pi provider extension for OpenAI-compatible, Anthropic-compatible, OpenAI Responses, and Ollama chat endpoints
$ pi install npm:@indexyz/pi-custom-providerpi-ollama-cloud-link
Unified pi extension for the Ollama Cloud account: live model discovery with capability/pricing metadata, web search/fetch agent tools with a disk cache, a live /ollama-setup account management TUI (balance meter, purchased credits, 30-day spend history,
$ pi install npm:pi-ollama-cloud-linkbetter-custom-provider
Custom provider wizard for pi: add, probe, edit and sync custom LLM providers in its own store
$ pi install npm:better-custom-providerpi-localllm-provider
Wizard-based provider setup for local OpenAI-compatible LLM servers (vLLM, Ollama, LM Studio, llama.cpp, …)
$ pi install npm:pi-localllm-providerpi-modelctl
Pi extension for self-hosted models: finds the models on your inference servers, caps thinking with pi's own budgets, and sets compaction and the summary's thinking level per model.
$ pi install npm:pi-modelctl@ask-llm/plugin
Ask LLM review, comparison, brainstorming, image, verification, and pairing workflows for Claude Code, Cursor Agent, and Pi
$ pi install npm:@ask-llm/pluginpi-webveil
Pi extension: web_search and web_fetch tools backed by webveil. A drop-in, anonymity-capable replacement for Ollama's web_search/web_fetch.
$ pi install npm:pi-webveilpi-model-scout
Pi provider extension: automatic model discovery for OpenAI-compatible endpoints (vLLM, LM Studio, Ollama, LiteLLM, etc.), including Unsloth Studio connected services.
$ pi install npm:pi-model-scout@tian.zuo/pi-web-search
Web search and fetch with configurable fallback order across OpenAI, DeepSeek, Exa, Tavily, Firecrawl, Monid, Brave, Parallel, TinyFish, Ollama, and direct HTTP.
$ pi install npm:@tian.zuo/pi-web-searchpi-s1-compact
Pi extension for classifier-driven context compaction and tool-output pruning, with persistent settings and original evidence retrieval
$ pi install npm:pi-s1-compactpi-provider-lemonade
Pi model provider that auto-discovers models from a Lemonade Server and integrates them into Pi via the server's OpenAI-compatible API
$ pi install npm:pi-provider-lemonadepi-protokoll
Pi extension: a running per-turn protocol replaces summarizing compaction – fast, bounded compaction for very long sessions with local models
$ pi install npm:pi-protokoll@latentminds/pi-quotas
Quota monitoring for Pi. Shows remaining usage and rate limits for Anthropic, OpenAI Codex, GitHub Copilot, OpenRouter, Synthetic, Grok, Z.ai, OpenCode Go, Kimi Code, and Ollama Cloud — directly in your Pi session.
$ pi install npm:@latentminds/pi-quotaspi-ollama-custom-tool
Temporary package placeholder for staged publishing
$ pi install npm:pi-ollama-custom-toolbetter-custom
Pi and Oh My Pi extension for managing custom providers through an interactive wizard.
$ pi install npm:better-custom@jamesjfoong/pi-ollama
Auto-discover and register Ollama models in pi. No more manual models.json editing.
$ pi install npm:@jamesjfoong/pi-ollamapi-ollama-usage
Pi extension that shows Ollama Cloud quota usage (monthly) in the footer status line
$ pi install npm:pi-ollama-usage@kylebrodeur/pi-model-discovery
Auto-discover local model providers (Ollama) and register their models with Pi on startup. Per-model context windows and capabilities, no /reload required.
$ pi install npm:@kylebrodeur/pi-model-discoverypi-setup-custom-providers
Interactive wizard to manage custom LLM providers and models for pi coding agent
$ pi install npm:pi-setup-custom-providerspi-model-dock
pi-model-dock: an interactive custom provider manager for Pi and Oh My Pi.
$ pi install npm:pi-model-dock@nbafrank/pi-tks
Live tokens-per-second (TPS) + time-to-first-token (TTFT) meter for pi, tuned for local models (footer status line + /tps command).
$ pi install npm:@nbafrank/pi-tkspi-ollama-provider
Native Ollama provider for Pi: local and Ollama Cloud through the Ollama API
$ pi install npm:pi-ollama-provider@0xkobold/pi-ollama
Ollama extension for pi-coding-agent. Unified local + cloud Ollama support with model management
$ pi install npm:@0xkobold/pi-ollamapi-cloud-quota
Subscription quota & pay-as-you-go balance in the pi status bar — Ark, Kimi, Ollama, OpenAI Codex, GitHub Copilot, Claude, GLM/z.ai, MiniMax, OpenRouter, new-api gateways and more
$ pi install npm:pi-cloud-quotapi-lm-providers
Ollama (local + Ollama Cloud) and LM Studio providers for the pi coding agent - live model discovery with real capabilities (tools/vision/thinking) and context windows.
$ pi install npm:pi-lm-providerspi-ollama-cloud-provider
Ollama Cloud provider extension for pi coding agent with dynamic model discovery
$ pi install npm:pi-ollama-cloud-providerpi-custom-endpoint
Pi and Oh My Pi extension for managing custom providers through an interactive wizard.
$ pi install npm:pi-custom-endpointpi-voice-refine
Local voice-to-English dictation for the Pi coding agent: faithful sentence-by-sentence translation with disfluency removal. SenseVoice ASR + Ollama refine, fully offline.
$ pi install npm:pi-voice-refine@hypabolic/crossbar
Connect the Pi coding agent to local & self-hosted LLMs — Ollama, LM Studio, llama.cpp, llama-swap, vLLM, and any OpenAI-compatible server. Auto-discovery, model switching, and zero-JSON in-TUI onboarding.
$ pi install npm:@hypabolic/crossbar