#pi
MCP servers, skills and plugins tagged “pi” on GitHub.
55 entries · real GitHub data
- #34codeArbiter
Open-source governance and hard gates for AI coding agents across Claude Code, Codex CLI, and Pi.
Local-first MCP App for scientific figures. Import, review, and publish a global library on disk; reuse exact templates in Pi, DeepSeek Harness (dsh), Claude, Codex, Cursor,…
- #36Bough
Claude Code, Codex and Pi write down everything you do. bough draws it and prices it: a day, the work inside it, every prompt, and what each piece cost. One Go binary, runs on…
- #38Rigup.Nix
AI agents and Nix: parametrable skills/instructions and tools, packaged together in a reproducible and modular fashion
Agentic game development taken to the next level: plan, build and test across major engines with any coding agent
- #40Tokdash
Agent Dashboard: Visualization and analytics for Sessions and Quota Usage. Track, analyze, and optimize token usage across providers with heatmaps, cost tracking, token…
- #41Dely
Multi-harness control protocol that turns requests into approved design contracts, orchestrating isolated worker sessions for sequential implementation and independent code…
Use Cursor CCE and bounded Cursor Agent execution from Codex, Claude Code, Grok Build, or Pi, with an independent Grok Build Supervisor.
- #43Manifest Dev
Skills for agentic coding CLIs: output you can ship with minimal review, on work you can tell was worth doing.
- #44Untether
Run your coding agents from Telegram. A bridge for Claude Code, Codex, OpenCode and Pi: send tasks by text or voice, watch them work and approve changes from your phone.
A zero-dependency Python module for inspecting and converting coding-agent session files (.jsonl) — Claude Code, Codex, and Pi — into the messages format expected by Hugging…
- #48Skillsbar
Claude Code, Codex, Pi, project skills, plugins, collections, and agents in the menu bar on macOS.
- #49Pi Goals
Persistent goal tracking for Pi with durable objectives, goal queues, budgets, reusable prompts, churn monitoring, and context-managed handoffs.
- #5010x
The engineering discipline that makes your AI developer 10x — hill-climbed through billions of tokens of autonomous experimentation.
Think first, then code. Where Claude Code and Codex jump straight to writing, this stays review-first: a code reviewer, security scanner, root-cause debugger, and code…
- #52Hivemind
Visibility for AI coding agents. Capture your agentic coding sessions so you can search, replay, and learn from them with your teammates.
- #53Eaon Desktop
The Eaon desktop app — an AI chat client that runs on your own API keys. Built with Electron, React and TypeScript; the interface follows the supplied design frames.
A single SKILL.md skill giving coding agents task-aware working modes (debug, fix, review, migrate, …) — works with Hermes, Claude Code, Codex, Cursor, and Pi
- #55Agent Flow
Guardrails for AI coding agents: run Claude Code, Codex, Gemini CLI, Cursor or Copilot unattended and come back to a reviewed pull request. Implement, review and QA agents, a…