# buchidonggua/dg-ai-notes

Repository: https://github.com/buchidonggua/dg-ai-notes
Canonical: https://ross.abutalabs.com/products/dg-ai-notes
Homepage: https://dg-ai-notes.pages.dev/
Language: MDX
License: MIT
License Family: permissive
Topics: ai-agent, learning-notes, pi-agent, python, tutorial, typescript
Last push: 2026-08-23T11:39:49+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 60, longevity 4
- inputs: {"age_days": 59, "days_push": 10, "days_rel": 59, "gap_med": null, "n_releases_24m": 1}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2333, forks 179 (observed 2026-08-28T04:06:37.708643+00:00)

## What it is
An open-source bilingual (TypeScript/Python) tutorial book that dissects the Pi-Agent SDK's source code across 10 chapters and provides a 7-chapter hands-on guide for building a production-ready vertical AI Agent. It also ships a companion 'dg-piagent' skill that lets AI coding assistants answer pi-agent SDK questions and generate working code.

## Use cases
- learn how a production agent SDK is designed by reading annotated source code
- build and deploy a vertical AI agent on top of pi-agent
- understand agent loop, tool system, and session management internals
- install a skill so Claude Code or Codex can write pi-agent code for me
- connect an internal enterprise LLM to the pi-agent runtime
- study context engineering and context compression techniques for agents

## When to choose
- you want a deep, structured walkthrough of a real agent SDK's architecture
- you are building an agent product on pi-agent or a similar runtime
- you prefer dual TypeScript/Python explanations with runnable notebooks and code samples

## When to avoid
- you need official documentation or guaranteed API accuracy for production work
- you use a different agent framework like LangChain or AutoGen
- you want a general AI/ML course rather than agent SDK specifics

## Facets
- artifact type: learning-resource
- maturity: active
- function: agent-framework, llm-inference, developer-tools, documentation
- domain: artificial-intelligence, large-language-models, tutorials, developer-tools
- platform: python, cross-platform
- tags: ai-agent, pi-agent, source-code-analysis, tutorial, mdx, ebook, skill, typescript, python, ai-agents, web-server, nodejs

## Member repositories
- buchidonggua/dg-ai-notes (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:37.708643+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:37:55.093240+00:00, confidence not recorded.
  - readme: https://github.com/buchidonggua/dg-ai-notes (fetched 2026-08-28T04:06:37.708643+00:00, sha 3df5de1c09df)
  - homepage: https://dg-ai-notes.pages.dev/ (fetched 2026-08-29T10:18:30.758712+00:00, sha 41a2729b44f3)
- Data as of 2026-08-30T08:39:29.467469+00:00.