pi-package

📚 Sync skills, agents, MCP, plugins to all AI CLI tools with one command and simplify team sharing.

54 rigorous skills for Codex, OpenCode, and Pi: code review, security audit, feature development, frontend design, MCP tools, Hugging Face ML/training, and more.

Universal mobile devtool for Agents & Humans - control iOS Simulators, Android Emulators, and real devices from a single dashboard and CLI

Pi extension package for Anthropic OAuth compatibility

Run Cursor's agent loop inside the pi coding agent via local Cursor SDK agents, with native model selection, thinking controls, fast/plan modes, image input, and MCP-bridged pi tools.

A programmable tool and agent runtime for Pi

OS-level sandboxing for pi with interactive permission prompts

Posthorse: fresh context, same journey. No-summary context rollover for the Pi coding agent (official Pi 1.0+ or the fitchmultz/pi fork), with durable notes and history recovery.

Unified algorithmic compaction + observational memory for Pi. Merges pi-vcc and pi-observational-memory with fallback chains, cooldowns, and per-worker model config.

pi extension that exposes agent-browser as a native tool for browser automation

A pi extension that brings Claude Code-style task tracking and coordination to pi. Track multi-step work with structured tasks, dependency management, and a persistent visual widget.

GitNexus knowledge graph integration for the Pi coding agent

pi custom provider for the Command Code API — 18 models including Claude, GPT, DeepSeek, Kimi, GLM, MiniMax, and Qwen

Codex-style goal tracking and continuation for pi.

Think Claude Code's auto mode but for pi (and oh-my-pi). Selectable model, sensible defaults.

Run the pi coding agent as a self-hosted service: jobs from cron, the CLI, or GitHub, GitLab, Forgejo and Azure DevOps events, each in a locked down Docker or Podman container, with a durable queue, spend caps checked before anything is spent, and a live admin panel.

Pi extension: rewrite rough prompts into precise technical prompts before send

Asynchronous Pi subagents and agent fleet orchestration for parallel coding agents with nested delegation, background work, and supervision in herdr.

Guardrails for Pi that steer instead of interrupt: enforces your project rules on every write, holds only hard-to-undo actions (3 per 1,000 calls, measured on real sessions), catches unverified "done" claims and stuck loops, and trims tool output. Built on pi-typesafe.

TypeSafe Jev as a decision layer for the Pi coding agent: a measured tool-call gate plus jev_ask for typed, calibrated answers