Ross ROSS = Recommend OSS · open-source software intelligence for agents

SaladDay/pi-from-scratch resource

600 行 TypeScript 写成的超级迷你版 pi,让你轻松从 0 写出属于你的 pi-agent observed · 2026-08-28

github.com/SaladDay/pi-from-scratch · homepage · TypeScript · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

57/100

  • Activity 98
  • Release rhythm 35
  • Longevity 1

Flags: no_releases young

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 24
  • days_rel: n/a
  • days_push: 15
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

1131 stars · 82 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A tutorial project that walks through building a minimal 600-line TypeScript coding agent (nano-pi) modeled on the production-grade pi agent. It pairs an article with an interactive website showing source code and execution traces, covering the LLM streaming layer, agent loop, and file/bash tools.

Use cases

  • learn how to build an AI coding agent from scratch
  • understand agent loops and tool calling in TypeScript
  • study how the pi agent architecture works
  • build a minimal LLM agent that reads files and runs bash
  • teach myself LLM streaming and SSE parsing
  • follow a step-by-step coding agent tutorial

When to choose

  • you want to understand agent internals rather than use a production tool
  • you prefer learning by building a tiny implementation
  • you want a readable TypeScript codebase for agent loops and tool calling

When to avoid

  • you need a production-ready coding agent with multi-provider support
  • you need extensions, session branching, or token compaction features
  • you want a framework to build applications on rather than a teaching resource

Facets

learning-resource · maturity active

agent-framework llm-inference developer-tools sdk artificial-intelligence large-language-models developer-tools tutorials cli coding-agent agent-loop tool-calling tutorial educational pi-agent nano-pi ai-agents nodejs typescript web

2 sources

Member repositories

RepositoryRoleHealth v2
SaladDay/pi-from-scratchmain57

For agents

markdown · JSON · MCP: product_card(name="SaladDay/pi-from-scratch")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem