Untested on omp

Pi extension for Shipd checks, behavioral test-gap analysis, and opt-in CoreWeave-backed agent_prompt.md humanization.

Isolated AI-powered code and plan reviews from the command line

Pi extension to quickly save, manage, and paste reusable prompts without retyping.

System One decisions for Pi. Plug in TypeSafe Jev, Reflex, or your own provider.

Keiyaku is an agent-facing contract workflow.

Vim-style modal editing for Pi's TUI editor

Optional model-powered ghost-text prompt suggestions

Free OpenAI-compatible model provider for pi via OpenCode Zen and KiloCode gateway

Multimodal perception for Pi — image/audio/video/document understanding, transcription & image generation via Gemini (gemini_api or local antigravity CLI).

herdr integration for the pi coding agent — spawn, drive, wait for, and harvest AI agent panes running in herdr.

Invisible session continuation for pi — resume the agentic loop without sending ANY prompt the LLM can see

Tokens-per-second tracker for pi — see your LLM generation speed after every agent turn

Public web pages, web search sources, and focused Context7 docs

Local FTS5 search over past Pi sessions plus a skill for turning recurring work into deterministic automation.

Clean up your Pi terminal status bar — formats extension badges with crisp presets (Stream, Powerline, Matrix, Glow), folds idle items on narrow screens, and adds live spinners.

Pi terminal UI extension with session management, context inspection, Tool/MCP usage tracking, sidebar panels, and a compact footer

Pi extension for goosedump session search, durable memory, session management, and compaction

Pi extension for goal tracking with background-aware continuation.

Production-ready agentic SDLC framework for Pi and coding agents — orchestrator, builder/validator teams, lifecycle state, and specialist reuse

Long-running iterative development loops for Pi coding agent

Persistent autonomous goals for pi — /goal loops until complete, paused, or budget-limited

Sub-Sub: a research assistant that works from your own Zotero library, in the browser or the terminal, built on pi

Guardian extension for pi — security guards that block accidental secret exposure, enforce command policies, protect .env files, and sandbox bash commands

nao 多角色 AI 开发舰队：角色卡 / 技能 / 协作协议 / 工具链，一键接入项目（pi / Claude / 任意 Agent）

Pi extension: subagent dispatch with admission, durable tickets, workspaces, and steering

Scene switcher for pi: bundle extensions, skills, and prompt templates into a common layer + per-scene layers. /scene hot-switches with live reload (project-scoped, zero settings residue); scene-scoped workflow templates arrive via resources_discover with

Pi extension. Native Warp terminal notifications, dispatched via OSC 777 on Pi lifecycle events.

Ask Pi users one interactive question with choices or a custom answer.

Minimal Antigravity provider for Pi Coding Agent

Pi extension for exploring a remote HPC/SSH host (via plink) with ls/read/grep tools, gated per-project by /hpc:on and /hpc:off.

Adaptive multi-harness orchestration with six roles, runtime-autonomous AI-first execution routes, and external provider boundaries.

Local document extraction: text, tables, metadata, images from 107 formats with optional OCR.

Pi coding agent extension: operator cockpit with a live powerline status bar, idea queue, skill search, sticky Bash, hooks, policy guardrails, and TUI session UX.

Shared logging helper for Pi extensions — two-channel routing (audit appendEntry / debug file log; the third AI-realtime channel stays with pi native) (shared library, not a Pi extension - no install.mjs needed)

Local Pi session analytics for token usage, cost, models, tools, subagents, skills, and history

Playwright browser automation skill package for pi

Reusable prompts and skills for CLI LLM tools, with native pi package support.

Subagent extension for Pi coding agent. Delegate tasks to specialized agents.

Semantic tool routing and typed System One decisions for the Pi coding agent using TypeSafe Jev

Shared memory, a curated-note editor, and optional main-session watchers for Pi, with a persistent side conversation, searchable history, optional archive encryption, native MCP, and explicit tool/bridge controls.

Project mental-model wiki for pi, maintained by agent insights and Jev decisions

Inline adaptive ask_user tool for Pi — single/multi-question structured input with split-pane preview and an inline free-text editor.

Delegate Pi work to focused child agents: code review, scouting, implementation, parallel audits, saved chains, and background jobs.

Session capability controls, prompt stash, shortcuts, and activity indicators

Same-provider multi-account pooling, OAuth storage, and safe in-stream auth failover for Pi

Inspect prompt-cache history and investigate regressions

Two-pane browser workspace for pi with prompt/response editing, annotations, critiques, active quiz, prompt/response history, live previews, and tmux-backed REPL/literate REPL workflows

Fusion CLI: HTTP API server, daemon, dashboard launcher, and task tooling for the Fusion AI coding agent.

Shiki-powered diff rendering for pi-archimedes

Pi extension: analyze and probe the pi-permission-auto-review classifier. Dry-run or call the model to validate additionalPolicy rules and inspect prompt construction.