Vision

A persistent, policy-guarded Playwright browser for AI agents with network controls, trusted credential filling, proof screenshots, and CAPTCHA helpers.

Pi extension for image generation via OpenAI gpt-image, Google Nano Banana (Gemini), Alibaba Qwen-Image, OpenRouter, and custom providers.

Hound web research for Pi agent - keyless search, anti-bot fetch, deep crawl, screenshot, Internet Archive dead-link recovery. Free, MIT, no API key.

Run AI coding agents in pi TUI overlays with interactive, hands-free, and dispatch supervision

Capability-aware vision + paste extension for the pi coding agent. Delegates image analysis to a vision model only when the active primary model is text-only; passes images through natively for multimodal models (zero delegation).

Pi extension for staging browser images and attaching them to the next message.

Pi package that adds document_parse, document_search, document_screenshot, and a companion skill for local document understanding with LiteParse v2.

Give text-only pi models vision — describe images with a vision model you pick via an interactive picker, then hand off the text description to non-vision models

Browser control extension for pi — navigate, click, type, screenshot, and extract data from real Chrome via CDP

MCP vision bridge for text-only coding agents

Claude Code-style tool rows for pi with Ctrl+O image previews and consistent built-in, MCP, and custom tool rendering

Image generation for Pi using the ChatGPT Images 2.0 model.

Unofficial pi package that exposes Z.ai MCP server tools for web search, URL reading, repository reading, and vision workflows.

Typed Pi tools for browser automation, rendered-page context extraction, screenshots, and saved session state via agent-browser.

QwenCloud provider for pi — access Qwen3.8, DeepSeek V4, GLM-5.2, Wan image generation, and HappyHorse video generation through QwenCloud's OpenAI-compatible API

Image generation and image recognition tools for the Pi coding agent

Pi extension for AI video generation plus local video composition: lossless clip concat and mixed image/video timelines with overlays, TTS, soft or burned subtitles, source audio, BGM, and bundled LGPL/GPL FFmpeg runtimes.

A Pi coding-agent extension for a certain current execution stack, provisional future paths, and a multi-session local web hub viewer.

Temporary pasted-image cache with compact placeholders for the pi coding agent.

Pi extension that turns pasted image paths into first-class image attachments.

TypeScript port of the nano-banana-imagegen pi skill. Generate and edit images with Google Gemini image models via the @the-focus-ai/nano-banana CLI, with GEMINI_API_KEY resolution, output-path handling and batch generation. Exposed as a pi skill and the

Pi quality-of-life extension: compact statusline/π prompt, reliable multiline input, styled pasted-image chips, session naming/search/context import, scheduled prompts, handoff, permission prompts, notifications, custom compaction, and a collapsed-thinkin

Browser automation tool for pi — interactive browsing, screenshots with inline vision, and session cleanup via agent-browser CLI

DeepInfra provider for pi: dynamic model catalog, reasoning-effort thinking levels, vision, session usage + monthly billing footer

Terminal visual polish for pi coding agent: natural multi-level headings, tool-panel code blocks, user message accent bar, clipboard image chips

Pi extension that turns pasted image paths into first-class image attachments with automatic optimization.

Pi extension + skill for a ground→contract→mockup→test→fix→learn frontend design loop. Ships a live mockup server tool, a Playwright breakpoint-screenshot tool, and a design-contract scaffolder. Works in any React/Tailwind/shadcn project.

Pi extension: review and test JS frontends headlessly — open dev-server pages in Playwright Chromium, interact with them, capture screenshots the model can see, and collect console/network errors.

Strict Plan Mode for Pi with revdiff review, immutable revisions, and explicit lifecycle completion.

Generate or edit PNG images in Pi using a ChatGPT Plus/Pro Codex subscription.

ComfyUI image/video generation extension for pi coding agent

pi extension that registers your llama.cpp server as a provider and auto-discovers every model it exposes at /v1/models — context size, vision and thinking support included

Local-first macOS screenshot optimizer for AI coding agents.

Pi extension exposing a gpt-5.5+ image generation tool backed by gpt-image-2.

Browser automation and web research tools for pi — search, visit, screenshot, interact, and inspect console output

Vision agents for pi — forward images to a vision model (pimage) and YouTube/TikTok videos to a video analyst (pideo) from any non-vision model.

Pi Coding Agent extension for OmniRoute — view combos, browse providers, and sync models with enriched metadata (context windows, max tokens, reasoning, and vision) to the Ctrl+P picker

Pi extension that turns terminal-dropped image paths into inline image attachments

Browser automation skill for pi — drive your real Chrome via the browser-use CDP CLI (navigate, screenshot, coordinate-click, extract, tabs). Penetrates closed shadow-DOM & cross-origin iframes via compositor-level coordinate clicks where js selectors fai

Pi extension that gives non-vision GLM models (z.ai) image understanding via GLM-4.6V

Improve OpenAI in pi with fast mode, usage stats, realtime voice, image generation, and footer polish.

Pi extension: Zero-setup multi-backend OCR — MinerU (free cloud), Ollama (local GPU, LaTeX formulas), Pix2Text (local Python). Extract text, formulas, and tables from images and PDFs. Default: zero config, works out of the box.

Image analysis tool using multimodal vision models with memory sessions.

Pi Agent extension that adds a describe_image tool, letting non-multimodal models delegate image analysis to a vision-capable model (like Qwen VL)

Convert any document to Markdown with Microsoft's markitdown CLI — PDF, DOCX, PPTX, XLSX, images (OCR), audio (transcription), YouTube, HTML, CSV, JSON, XML, EPUB, ZIP

Socratic planning and shared-understanding sessions for pi.

Agents should invoke this skill for Docker Compose deployments, container updates, stack health checks, rollbacks, compose-file changes, image upgrades, failed deploys, or service restart planning. Provides safe deployment and rollback workflows.

Slack read tools for pi — messages, threads, channels, search, and file/image downloads with Effect-powered client

PDF manipulation, processing, and management toolkit for Pi coding agent — extract text/tables, merge/split, fill forms, create PDFs, OCR, watermark, encrypt/decrypt, and more

A cute, colorful pet companion for the pi coding agent. Use classic ASCII pets or Petdex image pets that live below your editor and react to tools, tests, commits, PRs, reviews, subagents, model swaps and more.

Code Reasoning tools for pi and MCP — reflective sequential thinking with branching and revision support

Standalone Pi extension for OpenAI fast mode and image generation/editing.

Pi TUI configuration and an on-demand Skill/CLI for image generation.

Agents should invoke this skill when checking CVEs or known vulnerabilities in installed packages, dependencies, Docker images, OS packages, exposed services, or software versions. Produces severity-rated scan reports.

Screenshot picker extension for pi coding agent - quickly select and attach screenshots to your prompts

Essential extensions for pi — auto session naming, compact header, clipboard images, image pruning, markdown viewer, screenshots, and subagents.

Deprecated Google Antigravity image generation extension for pi

Common pi-coding-agent extensions: web search (mmx) and MCP server bridge. NOTE: 0.3.0 removed spawn_subagent (→ @shog-lab/pi-subagent); 0.4.0 removed understand_image (models have native vision now); cron scheduling moved to @shog-lab/pi-bus; browser aut

Muted thinking blocks, framed editor, animated header, response time, rich footer, and clipboard image paste for pi

Pi extension that registers an inspect_image tool — analyzes local image files using a configurable vision-capable model via OpenAI-compatible API

Image-to-base64 tool for pi — lets image-capable models see local image files

Vega-Lite chart extension for pi coding agent - render data visualizations as inline images

pi extension: convert a written prompt into an image and send it to the chat model

Pi package for OpenAI/Codex image generation with a local browser studio.

Image preview extension for pi coding agent — renders inline image thumbnails above the editor using kitty graphics protocol with tmux support

Use Pi providers in Codex Desktop with seamless history switching, image input, and a local OpenAI-compatible proxy.

MiniMax MCP tools for pi - Web search and image understanding via MiniMax's Model Context Protocol

GLSL fragment shader viewer for Pi Agent — live WebGL preview, Tweakpane uniform controls, presets, probe sheets & video export

OpenCode-grade clipboard paste for pi on Windows: instant Ctrl+V image attachments, Explorer file drops as collapsible blocks, large-text collapsing, persistent clipboard helper

Pi extension: Z.AI GLM-4.6V vision tools — image analysis, OCR, error diagnosis, diagram reading, UI diff, UI-to-code, video analysis

Pi extension: open files in $EDITOR via herdr, with per-extension openers (pdf, images, …)

pi-web plugin that browses and previews screenshots saved by pi-web into .pi-web/paste/ — gallery panel, lightbox, and chat-inline previews for folder-mode attachments.

Pi extension that renders LaTeX formulas as terminal images while preserving original LLM context.

Pi package that exposes Z.AI Web Search, Web Reader, Zread, and Vision MCP tools.

Pi-first QA pack: scans real codebases, infers test surfaces, ranks risk, runs evidence-based checks, captures screenshots, and writes .qa/* reports.

Restart llama-server with different model configurations. For single-model setups where models need different flags (context size, vision projector, sampling params).

Pi extension that exposes an inspect_image tool backed by a configurable VLM.

Headless browser for Pi — browse the web with DOM + OCR text maps. No image tokens, 10-50x cheaper than screenshot-based browsing.

Pi image generation tool powered by Together AI (Flux, Ideogram, and more)

Pi image generation tool powered by OpenAI (GPT Image, DALL-E)

Curated Pi skills for lookfor.cc image generation and Tavily search guidance

JSON-first CLI for Linear. Wraps every authenticated Linear MCP tool: projects, issues, comments, attachments, cycles, documents, milestones, teams, users, labels, statuses, images, and docs search.

MiniMax image understanding — pi extension and standalone CLI

OCR image-to-text tool for Pi — extracts text from screenshots, terminal output, and code images using Tesseract + ImageMagick

Accurate spatial reasoning over images — vision model extracts bounding boxes, LLM calculates exact distances

Pi image generation tool powered by xAI (Grok Imagine / Aurora)

Read GitHub issues, PRs, diffs, checks & code from inside Pi — via the gh CLI. Chronological markdown, image extraction, PR review workflows.

Provider-agnostic image generation for Pi coding agent

Pi image generation tool that auto-detects available API keys

Pi image generation tool powered by Replicate (Flux, SD, and more)

GitHub tool extension for Pi: format threads, list issues/PRs, and inspect PR diffs/images.

Screenshot skill and inline screenshot extension for pi

Umans provider extension for pi coding agent. (No extra tools, no vision proxy, just the provider.)

Pi image generation tool powered by Recraft (V3, V4)

Pi extension that gives non-vision models the ability to analyze images via a vision-capable subagent

Simple image understanding for Pi Coding Agent. Install it, set your API key, and ask normal questions about images.

Fallback image understanding for models without native vision support - provides understand_image tool via MiniMax API

CHOICES.md management — clarify project vision, mission, UX, operations, architectural decisions with cascading impact review. Includes replan skill for gap analysis and PLAN.md generation.

Display images from inside the pi coding agent: imgcat-style inline rendering in supported terminals, and one-click open in the system browser.

Screenshot picker for pi — browse, select, and attach screenshots to your prompts

Pi extension for xAI image, video, and vision workflows

Pi extension that resizes oversize images at Read-time so they fit model byte and pixel ceilings.

Pi package that exposes Codex-style image_generation and view_image tools with dynamic model routing.

Linux desktop-control MCP server: AT-SPI accessibility trees, Wayland/X11 input, screenshots, and compositor window targeting.

Pi extension that resizes oversize images at Read-time so they fit model byte and pixel ceilings.

Pi skill — a mechanical, countable anti-slop checklist for AI-generated frontend. Catches the specific tells an undirected model defaults to (AI-purple, Inter-everywhere, em-dashes, div-based fake screenshots, eyebrow-per-section, Jane Doe / Acme data). A

Synthetic (synthetic.new) model provider for pi - Dynamic model fetching with reasoning, vision, and tools support

Minimal Codex/OpenAI native tools for Pi: Codex image_generation, view_image, apply_patch

Image attachment and rendering extension for Pi TUI

Graphviz chart extension for pi coding agent - render DOT diagrams as inline images

Local hybrid RAG pipeline for the Pi coding agent. SQLite FTS5 + sqlite-vec, ONNX embeddings via Transformers.js, PDF/DOCX/HTML extraction (with OCR fallback), per-project storage, auto-injection. Zero cloud dependency.

Automatic image, video and audio description for any model in Pi. Routes media to a multimodal model and injects descriptions into context.

MiniMax Coding Plan extension for pi coding agent - provides web_search and understand_image tools

Pi extension package for direct HTTP GET plus web_search, web_fetch, and web_image via Firecrawl, Exa, Tavily, and Brave.

Pi-native ralph loop — autonomous coding iterations with mid-turn supervision

Expose Codex subscription image, search, Fast, and usage APIs as native Pi tools and commands

pi package adding a describe_image tool that lets non-multimodal models delegate image analysis to a vision model

Metabase CLI with full read/write access: cards, dashboards, databases, tables, queries, collections, search, and revisions from the terminal. Token-efficient JSON output.

Pi skill for browser automation via Chrome DevTools Protocol — navigate, evaluate JS, screenshot, pick elements, dismiss cookies, and monitor console/network logs.

Pi extension: load a Simocracy sim into your chat — see its pixel-art sprite render inline in the terminal and roleplay with it.

MiniMax web_search and understand_image tools for pi

OpenRouter multimodal tools for Pi — search, fetch, image gen, vision, video, PDF, TTS, STT

Generate, edit, and analyze images in pi using Google Nano Banana (image gen) and Gemini Vision (analysis). Inline terminal preview, reference-image editing, auto-save.

Local RapidOCR tools and slash commands for Pi, with a configurable backend adapter layer.

MiniMax MCP tools for pi - Web search and image understanding via MiniMax's Model Context Protocol

Run anything long-lived under babysit — one supervision substrate for processes and pi subagents, surfaced to the agent as babysit_run/check/send/wait/kill.

Connect pi to 9Router — multi-provider chat models plus image, speech, search, and fetch tools

Pi package for agent-assisted electronics/PCB image inventory with Cloudflare Workers AI vision and datasheet enrichment.

Render LaTeX as terminal images in Pi's TUI.

Pi extension that generates images via 9router's Codex image_generation tool (gpt-image-2).

[Alt+V] WSL image paste support for pi using the Windows clipboard

Pi image generation tool backed by local CLI providers: Codex or Agy.

Isolate and cache images so repeated payloads stay out of pi's main LLM context.

Clipboard image paste for pi-archimedes

Radius Google Workspace and image generation extensions for Pi

Pi extension that gives text-only models media understanding — describes images, transcribes local audio, routes local videos through native understanding for what-questions or frames+local ASR for when-questions, then feeds text to the active model

Cynos universal search, vision, and browser tools for the pi coding agent.

Pi extension: [image n] placeholders + SIXEL thumbnails for paste and tool screenshots (Windows Terminal + zentui). Supports agent_browser / agent-browser / Playwright. Switches: wrap/thumbs.

Log in to the airpx LLM proxy (https://airpx.cc) with an sk-proxy API key and auto-import its model catalog (prices, context windows, reasoning, vision) into the pi coding agent.

Minimal Ctrl+V image attachments with atomic [Image #01] placeholders for Pi.

Layout-aware PDF parsing, search, and screenshots using vision models already authenticated in Pi.

Pi image recognition tool: lets text-only models see images via local CLI providers (Codex or Agy).

Give text-only Pi and OMP models vision by handing images to a vision-capable model and returning text descriptions

Local vision (describe images), STT (speech-to-text), and TTS (text-to-speech). macOS uses MLX (Apple Silicon GPU). Windows/Linux use whisper, edge-tts, and transformers.

Pi extension — describe images via vision model when your active model cannot see images directly

Pi image generation tool powered by Google (Nano Banana, Imagen)

Pi extension that powers native Pi @file picking with background television-style search

Flicker-free inline images for Pi on Wayland + Ghostty, using Kitty Unicode placeholders.