# alejandrobalderas/claude-code-from-source

Architecture, patterns & internals of Anthropic's AI coding agent — reverse-engineered from source maps

Repository: https://github.com/alejandrobalderas/claude-code-from-source
Canonical: https://ross.abutalabs.com/products/claude-code-from-source
Language: TypeScript
License Family: other
Last push: 2026-04-04T00:00:48+00:00

## Health v2 (maintenance only)
Score: 48/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 75, release rhythm 35, longevity 11
- inputs: {"age_days": 154, "days_push": 152, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2773, forks 755 (observed 2026-08-28T04:07:19.103465+00:00)

## What it is
An educational technical book (18 chapters, ~400 pages) analyzing the architecture and design patterns of Anthropic's Claude Code AI coding agent, reverse-engineered from npm source maps. It contains no proprietary code—only original pseudocode illustrating how production AI agents are built.

## Use cases
- understand how production AI coding agents are architected
- learn agent loop and tool execution patterns for building my own AI agent
- study multi-agent orchestration design patterns
- evaluate agent architectures as a technical leader
- learn how permission systems and state management work in AI agents
- understand prompt caching, streaming, and API layer design for LLM tools

## When to choose
- you're a senior engineer building agentic systems and want transferable patterns
- you want a narrative deep-dive into Claude Code's internals without reading source
- you're evaluating architectures for AI agent products

## When to avoid
- you need runnable source code or a library to import
- you want official Anthropic documentation
- you need a general AI/LLM tutorial rather than agent architecture analysis

## Facets
- artifact type: learning-resource
- maturity: active
- function: documentation, agent-framework, developer-tools
- domain: artificial-intelligence, large-language-models, developer-tools, tutorials
- platform: -
- tags: ai-coding-agents, reverse-engineering-analysis, technical-book, claude-code, architecture-patterns, educational, ai-agents, nodejs, typescript, web

## Member repositories
- alejandrobalderas/claude-code-from-source (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:19.103465+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 2026-08-30T08:16:35.964872+00:00, confidence not recorded.
  - readme: https://github.com/alejandrobalderas/claude-code-from-source (fetched 2026-08-28T04:07:19.103465+00:00, sha a75922646e2e)
- Data as of 2026-08-30T08:39:29.467469+00:00.