Knowledge graphs for library docs

Built with graphify — query the graph instead of dumping whole docs. Up to 95% fewer tokens.

$uvx graflet react

Knowledge-graph catalog

more coming soon
LibraryVersionCommand
Loading catalog…
01 · MARKDOWN

Docs as Markdown

Every page of the official docs, downloaded as clean Markdown you can grep, feed, and version — pinned to the exact release you install.

02 · THE VALUE

Knowledge graph

A pre-built graph of concepts, APIs, and how they connect — as an interactive view and a machine-readable graph.json. This is the context your AI actually needs.

Build cost saved
vs building the graph yourself
Build time done
pre-computed, not on your machine
GraphScore
coverage × structure quality
Docs distilled
of source docs, condensed into one graph

Live from the catalog · — until the first graph is measured

How it works

01

Run one command

uvx graflet react — no config, no account to start.

02

Sign in with GitHub

One click, and only to download the graph. Install, browse and copy stay free.

03

We fetch both

Docs pulled from the upstream project, the knowledge graph from our backend.

04

Land locally, aligned

docs/*.md and graph.json on disk, pinned to the same release.

react — graflet · example output
$ uvx graflet react
 Resolved 19.1.0 a3f21c8 · docs and graph aligned
 Downloaded docs → 312 files (18 MB)
 Fetched graph → 1,204 nodes · 3,880 edges

Done in 24s
Saved ~6h 12m of local build · ~$0.94 in API cost

  ./react/
WHY A KNOWLEDGE GRAPH

Raw docs are flat. A graph knows how things connect.

The graph encodes relationships — which API calls which, what depends on what, which concepts connect — so your AI retrieves the right context instead of dumping whole pages. Cheaper prompts, sharper answers, fewer hallucinations.

Support the project

Free and open source, and nothing is paywalled. A star is the whole ask — or fund the work with an optional supporter licence, which unlocks nothing because there is nothing to unlock.