Merge pull request #436 from samfoy/add-pi-tools

Add pi coding agent and related tools

README.md

@@ -121,6 +121,7 @@ Autonomous CLI agents that generate code, execute shell commands, and manage mul
 - [Mini SWE-Agent](https://mini-swe-agent.com/latest/) — A minimal, hackable software engineering agent built for learning and experimentation. Lightweight implementation demonstrating core SWE-agent concepts with a focus on simplicity and extensibility.
 - [Micro Agent](https://www.builder.io/blog/micro-agent) — An AI agent that writes and fixes code for you.
 - [cmux](https://github.com/manaflow-ai/cmux) — A Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Features notification rings, in-app browser, SSH support, and Claude Code Teams integration.
+- [pi](https://pi.dev/) — Minimal, extensible terminal coding agent. TypeScript extensions, skills, prompt templates, and themes — all shareable as npm packages. Supports multiple LLM providers with a unified API.
 
 ### CLI Utilities
 
@@ -337,6 +338,7 @@ Platforms for running multiple AI coding agents in parallel with workspace isola
 - [Shep](https://github.com/shep-ai/cli) — Multi-session SDLC control center that orchestrates AI coding agents (Claude Code, Cursor CLI, Gemini) for autonomous feature development with configurable approval gates and a live web dashboard.
 - [Bernstein](https://github.com/chernistry/bernstein) — Deterministic multi-agent orchestrator that spawns parallel coding agents (Claude Code, Codex CLI, Gemini CLI) from a single goal, verifies with tests, and auto-commits. Zero LLM tokens on coordination.
 - [Kagan](https://github.com/kagan-sh/kagan) — Open-source AI orchestration board with a VS Code extension for planning, running, and reviewing coding agent tasks.
+- [pi-ralph](https://github.com/samfoy/pi-ralph) — Multi-agent orchestration loops for the pi coding agent. Runs autonomous implementation, review, and debugging cycles with configurable roles and loop chaining.
 
 ### Sandboxing & Isolation
 
@@ -367,6 +369,7 @@ Tools that manage and sync AI agent configurations, rules, and context across ed
 - [AgentsKB](https://agentskb.com) — Knowledge base with 39K+ researched technical Q&As accessible via MCP server, REST API, or web search. Integrates with Claude Code, Cursor, and Cline.
 - [rule-gen](https://github.com/nedcodes-ok/rule-gen) — CLI tool that generates AI coding rules from your actual codebase using Google Gemini. Feeds source files into Gemini's 1M token context window to produce project-specific rules for Cursor, Claude Code, Copilot, and Windsurf. Zero dependencies.
 - [Zenable](https://zenable.io/) — AI guardrails that learn your team's standards and ensure coding agents follow them, maximizing speed and quality.
+- [pi-steering-hooks](https://github.com/samfoy/pi-steering-hooks) — Deterministic before-tool-call guardrails for the pi coding agent. Enforces rules (no force push, conventional commits, etc.) via regex pattern matching on tool inputs — zero tokens, 100% reliable. Custom rules via JSON config with override escape hatch.
 - [Gestalt](https://github.com/dwgoldie/gestalt) — Model-agnostic thinking protocol (AGENTS.md) that shapes how AI coding agents reason. Less filler, more substance, honest about limits. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI.
 - [Agentify](https://github.com/koriyoshi2041/agentify) — CLI tool that transforms any OpenAPI spec into 9 agent interface formats (MCP server, AGENTS.md, CLAUDE.md, .cursorrules, Skills, llms.txt, GEMINI.md, A2A Card, CLI) with a single command. Tiered generation strategies for small to large APIs.