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

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

MediaPipe Vision Tasks. See the privacy notice at https://goo.gle/mediapipe-privacy.

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

Bitmap-frame context compression for vision-capable LLMs

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

Pi session search, ask, handoff, messaging, auto-titling, and indexing tools

Google Cloud Vision API client for Node.js

Controllable background sub-agent threads for pi: specialized roles, capability-aware thinking, direct main-model fallback, auto-fix chains, and Git worktree isolation.

VisionCamera is the fastest and most powerful Camera for react-native.

Sanity plugin for running/debugging GROQ-queries against Sanity datasets

Coding agent CLI with read, bash, edit, write tools and session management

Maestria extension for the Oh My Pi coding agent

Web chat interface for the pi coding agent, powered by the pi SDK (@earendil-works/pi-coding-agent) — one-command run, Docker/systemd/launchd deployable

Maestria extension for the Pi coding agent

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. Includes direct clipboard paste (image-paste integration).

Pi extension that keeps Multica work agents bound to issue, PR, evidence, and handoff contracts.

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 that adds a Codex-like read-only /plan collaboration mode.

Maintained, extension-first Pi coding agent with built-in workflows, subagents, web research, questions, skills, and an enhanced terminal UI.