# devenjarvis/lathe

Generate hands-on, multi-part technical tutorials on demand, with LLM skills tuned to make content approachable. Then you work through them yourself, by hand ✋

Repository: https://github.com/devenjarvis/lathe
Canonical: https://ross.abutalabs.com/products/lathe
Language: Go
License: MIT
License Family: permissive
Last push: 2026-08-03T00:03:18+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 95, release rhythm 93, longevity 8
- inputs: {"age_days": 122, "days_push": 31, "days_rel": 44, "gap_med": 0, "n_releases_24m": 6}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1653, forks 46 (observed 2026-08-28T04:05:17.133632+00:00)

## What it is
Lathe is a Go CLI plus local web UI that generates hands-on, multi-part technical tutorials on demand using LLM skills run inside coding agents like Claude Code or Cursor. It stores, manages, and serves the tutorials in a purpose-built reading interface, encouraging you to work through them yourself by hand.

## Use cases
- generate a hands-on tutorial on any technical topic on demand
- create a multi-part tutorial series with an LLM coding agent
- read and work through tutorials in a local learning UI
- ask questions about a tutorial or have the LLM verify it
- extend an existing tutorial with an additional part
- search and manage a personal library of generated tutorials

## When to choose
- you want LLM-generated, approachable technical tutorials you complete yourself rather than having AI write code for you
- you already use a coding agent like Claude Code, Cursor, or Codex and want a tutorial workflow on top of it
- you prefer a self-contained local binary with a pleasant reading UI and no cloud service

## When to avoid
- you need fully automated course generation without an interactive coding agent session
- you want a hosted, multi-user learning platform with accounts and progress tracking
- you need offline tutorial generation - the LLM work runs in your agent, not the binary

## Facets
- artifact type: cli-tool
- maturity: active
- function: llm-inference, prompt-engineering, documentation, cli, http-server
- domain: education, developer-tools, large-language-models, documentation
- platform: cli, cross-platform, windows
- tags: llm-skills, coding-agents, tutorial-generator, learning-tool, local-web-ui, go, education, command-line, macos, linux, web-server

## Member repositories
- devenjarvis/lathe (main) score 77

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:17.133632+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 2026-08-30T03:44:57.843482+00:00, confidence not recorded.
  - readme: https://github.com/devenjarvis/lathe (fetched 2026-08-28T04:05:17.133632+00:00, sha 7c4f68f3bda9)
- Data as of 2026-08-30T08:39:29.467469+00:00.