@xiaomovps: Pi Runs in the Terminal — Manage It Anytime, Just Install These Three Pi itself is intentionally kept tiny. Multi-agent management, mobile remote access, and account connections are all left out of the core — but they're real must-haves for many people. So I'm recommending 3 tools to get everything sorted at once. 1. Herdr: The Layer for Managing Multiple Agents in the Terminal
Summary
Three companion tools for Pi (a terminal-based AI agent): Herdr for multi-agent terminal management, Collie as its self-hosted mobile PWA, and Executor as a unified entry point for accounts and MCP credentials. None of them modify Pi itself, and you can install each as needed.
View Cached Full Text
Cached at: 10/16/26, 10:48 PM
Pi runs in the terminal — manage it anytime. These three tools are all you need 🔥
Pi’s core is intentionally kept lightweight. Multi-agent management, mobile remote access, and account connections are all left out of the core — but these are real needs for many people. Here are three tools that will fill those gaps in one shot.
1. Herdr: the layer for managing multiple agents in the terminal
Each agent gets its own pane. Pi reports its status directly — idle, working, or blocked. Close your laptop and it keeps running.
Install:
curl -fsSL https://herdr.dev/install.sh | sh
2. Collie: the mobile companion for Herdr
Self-hosted PWA, open source (MIT). See which agent is waiting for input from your phone and reply directly. Push notifications when an agent gets stuck.
Install:
curl -fsSL https://colliepwa.dev/install.sh | sh
It uses Tailscale by default. It’s essentially a remote shell — don’t expose it directly to the public internet.
3. Executor: a unified entry point for accounts and MCP
Connect accounts like Gmail, GitHub, and Slack once, and all your agents can use them through a single MCP endpoint. Credentials never enter your chats or code.
There’s a hosted version on the official site, and you can also run it locally or deploy with Docker. Self-hosting is free.
https://executor.sh
None of these touch Pi’s core. Install them one at a time if needed. They also work with other agents, not just Pi.
Similar Articles
@realchendahuang: I've put together a comprehensive configuration scheme for Pi Agent, including 17 plugins, 18 global Skills, 2 MCP servers, with a one-click install script. Pi out of the box only has four functions: read and write files and run commands. This configuration is not simply stacking plugins; it's a complete design built around the actual coding process...
A practical complete configuration scheme for Pi Coding Agent, including 17 plugins, 18 global Skills, and 2 MCP servers, with a one-click install script, aimed at turning it into a powerful terminal coding agent.
@aehyok: I just started using Pi recently, and I really love its minimalism and high degree of freedom, which lets me assemble it however I like Since I'm just getting started, based on my initial experience and the docs I've gone through, I put together a quick overview of the most basic features Pi Agent provides 👇 1. First off, a complete Agent loop Calls the model, executes tools, hands results back to the model — looping until the task is done You can also chime in mid-loop to steer or correct, or just interrupt it 2. Only 4 tools enabled by default read: reads files and images bash: executes commands edit: makes precise file edits write: creates or overwrites files Don't let the small number fool you — it's more than enough, since grep, find, curl, etc. can all be run directly through bash 3. Plus 4 built-in tools, disabled by default grep, find, ls, and PowerShell on Windows You can turn them on with a single command: pi --tools +grep,+find,+ls You can also enable just read, grep, find, and ls to create a read-only Agent that only reads code and never modifies it 4. MCP is now built in No need to install any extra plugins — just use `pi mcp add` to add an MCP server and it works Note: Pi itself has no web search. If you want it to look things up online, you'll need to connect a search-type MCP or another tool yourself 5. Supports Skills Uses the same SKILL.md format as Claude Code — normally only the name and description are given to the model, and the full content is loaded only when needed, which saves a lot of context However, it doesn't read .claude/skills by default. You need to add a line in ~/.pi/agent/settings.json: "skills": ["~/.claude/skills"] 6. Can read CLAUDE.md It reads AGENTS.md or CLAUDE.md from the current directory and parent directories But if both exist in the same directory, only AGENTS.md is read It also doesn't read ~/.claude/CLAUDE.md — global instructions need to go under ~/.pi/agent/ I looked at the code, and CLAUDE.md isn't handled separately — it's just in the same filename list as AGENTS.md. So the @ references from Claude Code aren't supported either 7. Other basic capabilities are all there Switch models at any time Sessions can be forked and rolled back Context is automatically compressed when it's nearly full Supports CLI, RPC, and SDK invocation ⚠️ What's NOT included by default Sub-agents, plan mode, todo lists, permission confirmation — none of these are built in However, the official repo's examples directory has example extensions for each of these, so you can install them if you're interested, or just ask Pi to write one for you So I see Pi more as a clean Agent foundation — it has all the basics you need, and you build the rest on top to fit your own workflow That's exactly why I like it most: the more capable the model gets, the simpler I think the Harness should be — no need for all those flashy features
作者分享了刚上手 Pi Agent 的体验，梳理了它提供的基础功能：完整的 Agent 循环、read/bash/edit/write 四个默认工具、内置 grep/find/ls 等可选工具、内置 MCP 支持、兼容 Claude Code 的 SKILL.md 格式与 CLAUDE.md 读取，以及多模型切换、会话分叉、上下文压缩等能力，认为 Pi 是一个极简、高度自由的 Agent 底座。
After Pi is installed, the first thing recommended to add is not multiple agents, but internet connectivity. Recommended tool: pi-web-access. It can not only search the web but also: Search for latest materials, Read web pages and PDFs, Analyze GitHub repositories, Understand YouTube videos, Analyze local videos. Installation: pi …
This article recommends the pi-web-access tool to add internet capabilities to Pi, allowing it to search the web, read PDFs, analyze GitHub repositories, and more.
@oragnes: Recently discovered a hardcore open-source project from Harness: pi (recently moved under earendil-works from badlogic). It is an all-in-one AI Agent infrastructure suite plus a terminal programming assistant CLI designed to backstop developers. Stop reinventing the wheel: it provides a ready-made…
Pi is an open-source AI Agent infrastructure suite and terminal programming assistant CLI. It offers a unified API to bridge differences between multiple models, supports concurrent tool calling to reduce latency, and allows developers to control the thinking budget.
@9hills: After several weeks of exploration and various attempts, the configuration of pi agent is basically stable. I posted a list before without explanation, which wasn't very friendly. This time I'm posting a full version with comments. Warning: If you need an out-of-box Coding Agent, don't use Pi; Claude Code/Codex is more suitable…
The author shares the stable configuration of pi agent (full version with comments), and warns that if you need an out-of-box Coding Agent, Claude Code/Codex is more suitable.