PI

An Ask HN reply asked what Herdr fills that pi and plain tmux scripts don't already cover. We compared all three against their own documentation - including the places where Herdr genuinely loses.

How a one-developer protest against bloated coding harnesses became a 95,000-star agent toolkit: pi's five-package architecture, branching JSONL session trees, four run modes, and the philosophy that refuses to build sub-agents, plan mode, or MCP.

The practical guide to earendil-works/pi: verified install and auth steps, all four run modes from TUI to SDK, JSONL session trees with branch, fork and resume, and the rough edges nobody advertises.

A decision-intent comparison of pi, Claude Code, OpenCode and Codex CLI as your main agentic coding harness in late 2026, with a verified capability matrix and pick-X-if verdicts.

Interactive UI to switch models and effort sliders mid-session.

Add gateway or custom models to the picker via environment variables.

Configure model, tools, MCP, skills, memory, and scoping.

Route specific MCP servers only to specific subagents.

Managed scheduling on Anthropic infrastructure with API and GitHub triggers.

Deep comparison of the top AI agent frameworks - LangGraph, CrewAI, Mastra, CopilotKit, AutoGen, and Claude Code.

Install Claude Code, configure your first project, and start shipping code with AI in under 5 minutes.