glm-vision
Pi extension that gives non-vision GLM models (z.ai) image understanding via GLM-4.6V
$ pi install npm:glm-visionPackage Catalog
Extensions, skills, prompt templates, and themes published to npm. Install with pi install npm:<package>. See the package docs for details.
Recently published
pi-readseekPi extension for readseek-backed hash-anchored read/edit/grep, structural code maps, structural search, and file exploration14m agopi-codex-tokenpi provider plugin: use gpt-5.5 on the OpenAI Codex backend via a personal access token (PAT), non-interactively.15m agopi-namespaceNamespace tools and skills in pi — group tools by extension with configurable prefix rewriting17m ago@nitra/cursorCLI для завантаження cursor-правил (префікс n-) у локальний репозиторій19m agopi-shazamPi coding agent native codebase awareness toolkit — 14 structural analysis tools. Also supports MCP (Cursor, Claude Desktop, Windsurf, etc.)23m agopiscordLightweight Discord gateway for pi coding agent27m ago@pi-vault/pi-subagentsPi extension for delegating tasks to isolated and specialized subagents31m ago@gotgenes/pi-subagentsA pi extension that brings Claude Code-style autonomous sub-agents to pi. Friendly fork of @tintinweb/pi-subagents.1h ago
All packages
1-8 / 8 (of 3977)
pi-accurate-vision
Accurate spatial reasoning over images — vision model extracts bounding boxes, LLM calculates exact distances
$ pi install npm:pi-accurate-vision@dtmirizzi/pi-openrouter-multimodal
OpenRouter multimodal tools for Pi — search, fetch, image gen, vision, video, PDF, TTS, STT
$ pi install npm:@dtmirizzi/pi-openrouter-multimodalpi-multimodal-proxy
Automatic image, video and audio description for any model in Pi. Routes media to a multimodal model and injects descriptions into context.
$ pi install npm:pi-multimodal-proxypi-inspect-image
Pi extension that registers an inspect_image tool — analyzes local image files using a configurable vision-capable model via OpenAI-compatible API
$ pi install npm:pi-inspect-image@zhushanwen/pi-vision
Image analysis tool using multimodal vision models with memory sessions.
$ pi install npm:@zhushanwen/pi-vision@lokiyou/modelscope-vision
Simple image understanding for Pi Coding Agent. Install it, set your API key, and ask normal questions about images.
$ pi install npm:@lokiyou/modelscope-visionpi-vision-tool
Pi Agent extension that adds a describe_image tool, letting non-multimodal models delegate image analysis to a vision-capable model (like Qwen VL)
$ pi install npm:pi-vision-tool