typesafe-docs
Markdown export of TypeSafe's documentation (110 pages) for feeding to LLMs and agents.
This repository is mostly documentation or write-up rather than runnable code.
Overview
This repository contains TypeSafe AI's documentation extracted from docs.typesafe.ai into Markdown, preserving the original order across 110 documents. It covers the introduction, quick start, System One concepts, state, the Choice, Score and Noul primitives, confidence, patterns such as speculative fan-out, confidence-gated routing, composite scoring and intent routing, demos, client SDKs and the API reference.
The stated purpose is to provide the docs in a form that LLMs can read or be trained on. The README says the content was extracted before removal from the site, so it may be a snapshot of an earlier docs version. It is documentation only, with no code. Because it reflects the docs at one moment, it is best used as context for agents or for comparing with the current official documentation rather than as the authoritative reference.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Other | None; documentation export.(inferred) | — |
How it works
- Docs are scraped from docs.typesafe.ai.
- Pages are saved as numbered Markdown files.
- Users feed them to LLMs or agents as context.
Strengths
- Offline, LLM-friendly copy of the docs.
Caveats
- A snapshot that may be outdated.
- Third-party copy of official content.
At a glance
- Type
- Project
- Has code
- no
- Has tests
- no
Use cases and integrations
How curated lists describe it
System One Models & Jev documentation. typesafe.ai documentation extracted in .md format for LLMs. Used to train LLMs.
hellogumbo/awesome-jev
Frequently asked questions
What is in it?
110 Markdown pages extracted from TypeSafe's documentation.
Is it current?
It is a snapshot taken before some content was removed from the site.
What is it for?
Giving LLMs and agents the docs as context.
Related projects
- Building with Jev★ 155
Agent skill for writing and improving programs that call Jev: question design, state structure, thresholds and diagnosing wrong answers.
Agent skillproduction Server behind api.typesafe.pro, a free anonymous System One-compatible endpoint that forwards to TypeSafe on the operator's key.
ServiceproductionPortable Agent Skill teaching coding agents to use Jev as a bounded judgment layer, plus an optional MCP bridge.
MCP serverbetaTypeScriptIndependent agent skill that makes a coding agent design, build, test and tune a bounded Jev decision layer with a contract first.
Agent skillbetaAgent skill that guides you in finding, designing and testing Jev decision loops, including when to keep logic in code.
Agent skillbetaBrowser form for building Jev requests from pasted text without hand-writing JSON, then rerunning to see how steady the answers are.
ProjectbetaJavaScript