ai-agent

Jan

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.
44,369 stars3,011 forksTypeScriptUpdated 9/4/2026100% free · open source
What it does

Jan lets you run a ChatGPT‑style large‑language‑model locally on your own computer, so you can generate text without any internet or API calls.

When to use it
  • You need AI‑generated copy, ideas, or code but can’t rely on external APIs for privacy or cost reasons.
  • Your team is working in a low‑bandwidth environment (e.g., on a ship, in a bunker) and still wants LLM assistance.
  • You want to prototype or demo an AI feature quickly without waiting for a paid cloud quota.
Ready-to-paste prompt
Write a 150‑word product description for a new AI‑powered project‑management tool aimed at remote teams.
Heads up: Jan requires a recent Node.js version (≥ 18) *and* a compatible CPU/GPU; if you run the default LLaMA‑7B GGML model you need at least 8 GB of RAM, otherwise the process will crash with an out‑of‑memory error.
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/jan && curl -fsSL https://workflowstacks.com/api/skills/jan/claude-skill -o ~/.claude/skills/jan/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Jan works
Codeflow
Free to inspect

Jan is a very large TypeScript project (~184k lines across 972 code files, plus 308 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Other license, has a test suite.

Size
Very large codebase
~184k lines · 972 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Node.js
No API keys detected
TypeScript 51%Rust 46%Swift 1%Python 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    autoqa/main.py
    Where the program starts running
  3. 3
    package.json
    Dependencies and the commands it exposes
  4. 4
    core/README.md
    Inside core/ — the main logic begins here
What's in each folder
core/Core code — the actual logic108 files
extensions/Sub-packages / plugins77 files
docs/Documentation720 files
web-app/Folder1099 files
src-tauri/Folder329 files
autoqa/Folder26 files
mlx-server/Folder11 files
scripts/Helper scripts7 files
READMEHas testsDocumentedCI checksOther licenseUpdated this month
Quick Actions
Details
Creator
janhq
Language
TypeScript
Category
ai-agent
Published
8/17/2023

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.