jan launch

Usage

jan launch [PROGRAM] [OPTIONS] [-- PROGRAM_ARGS...]

Start a local model, then launch an AI agent or program with environment variables automatically set to use the local model.

Arguments

string

Agent or program to run after the model is ready.Supported agents:

claude — Claude Code (Anthropic’s AI coding agent)
codex — Codex CLI (OpenAI’s coding agent)
openclaw — OpenClaw (open-source autonomous AI agent)

Omit to pick interactively from the list above.

jan launch claude
jan launch openclaw
jan launch  # Pick interactively

array

Arguments forwarded to the program. Use -- to separate them from jan options.

jan launch claude -- --help
jan launch openclaw -- tui --debug

Options

Model Selection

string

Model ID to load. Omit to pick interactively from installed models.

jan launch claude --model qwen3.5-35b-a3b

Can be:

A model ID from jan models list (e.g. qwen3.5-35b-a3b)
A HuggingFace repo ID (e.g. Qwen/Qwen2.5-35B-Instruct-GGUF) — will auto-download

string

Path to the inference binary. Auto-discovered from Jan data folder when omitted.

jan launch claude --model qwen3.5-35b --bin /usr/local/bin/llama-server

Server Configuration

number

default:"6767"

Port the model server listens on.

jan launch claude --model qwen3.5-35b --port 8080

string

default:"jan"

API key for the model server. Exported as OPENAI_API_KEY and ANTHROPIC_AUTH_TOKEN.

jan launch claude --model qwen3.5-35b --api-key my-secret-key

Performance Configuration

number

default:"-1"

GPU layers to offload.

-1: All layers (full GPU acceleration)
0: CPU only
> 0: Specific number of layers to offload

jan launch claude --model qwen3.5-35b --n-gpu-layers 35

number

default:"4096"

Context window size in tokens.

jan launch claude --model qwen3.5-35b --ctx-size 8192

Setting --ctx-size explicitly disables auto-fit. Omit this option when launching Claude to enable auto-fit by default.

boolean

Auto-fit context to available VRAM.

jan launch claude --model qwen3.5-35b --fit

Default behavior:

When launching claude: --fit defaults to true (unless --ctx-size is set explicitly)
When launching other programs: --fit defaults to false

Output Control

boolean

default:"false"

Print full server logs (llama.cpp / mlx output) instead of the loading spinner.

jan launch claude --model qwen3.5-35b --verbose
jan launch claude --model qwen3.5-35b -v

Examples

# Pick agent and model interactively
jan launch

# Launch Claude Code with a specific model
jan launch claude --model qwen3.5-35b-a3b

# Launch OpenClaw
jan launch openclaw --model qwen3.5-35b-a3b

# Pass arguments to the launched program
jan launch claude -- --help
jan launch openclaw -- tui --debug

# Custom port and API key
jan launch claude --model qwen3.5-35b --port 8080 --api-key secret

# Maximize context window
jan launch claude --model qwen3.5-35b --fit

# CPU only
jan launch claude --model qwen3.5-35b --n-gpu-layers 0

# Download and launch with a HuggingFace model
jan launch claude --model Qwen/Qwen2.5-35B-Instruct-GGUF

Environment Variables

Depending on the launched agent, Jan sets different environment variables:

For Claude Code & Codex

OPENAI_BASE_URL=http://127.0.0.1:6767/v1
OPENAI_API_KEY=jan
OPENAI_MODEL=qwen3.5-35b-a3b
ANTHROPIC_BASE_URL=http://127.0.0.1:6767
ANTHROPIC_AUTH_TOKEN=jan  # or ANTHROPIC_API_KEY for non-Claude agents
ANTHROPIC_DEFAULT_OPUS_MODEL=qwen3.5-35b-a3b
ANTHROPIC_DEFAULT_SONNET_MODEL=qwen3.5-35b-a3b
ANTHROPIC_DEFAULT_HAIKU_MODEL=qwen3.5-35b-a3b

For OpenClaw

Jan configures OpenClaw via ~/.openclaw/openclaw.json instead of environment variables:

{
  "models": {
    "providers": {
      "jan": {
        "baseUrl": "http://127.0.0.1:6767/v1",
        "apiKey": "jan",
        "api": "openai-completions",
        "models": [
          {
            "id": "qwen3.5-35b-a3b",
            "name": "qwen3.5-35b-a3b",
            "input": ["text"],
            "reasoning": false,
            "contextWindow": 131072,
            "maxTokens": 16384,
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            }
          }
        ]
      }
    }
  },
  "agents": {
    "defaults": {
      "model": {
        "primary": "jan/qwen3.5-35b-a3b"
      }
    }
  }
}

Provider API keys are cleared to prevent overrides:

OPENAI_API_KEY, OPENAI_BASE_URL
ANTHROPIC_API_KEY, ANTHROPIC_AUTH_TOKEN, ANTHROPIC_OAUTH_TOKEN
GEMINI_API_KEY, MISTRAL_API_KEY, GROQ_API_KEY
XAI_API_KEY, OPENROUTER_API_KEY

Output

Loading

✓ qwen3.5-35b-a3b ready · http://127.0.0.1:6767

  OPENAI_BASE_URL=http://127.0.0.1:6767/v1
  OPENAI_API_KEY=jan
  OPENAI_MODEL=qwen3.5-35b-a3b
  ANTHROPIC_BASE_URL=http://127.0.0.1:6767
  ANTHROPIC_AUTH_TOKEN=jan
  ANTHROPIC_DEFAULT_OPUS_MODEL=qwen3.5-35b-a3b
  ANTHROPIC_DEFAULT_SONNET_MODEL=qwen3.5-35b-a3b
  ANTHROPIC_DEFAULT_HAIKU_MODEL=qwen3.5-35b-a3b

  → Launching: claude

Then Claude Code (or your chosen agent) starts with the local model pre-configured.

For OpenClaw

✓ qwen3.5-35b-a3b ready · http://127.0.0.1:6767

  ~/.openclaw/openclaw.json → jan provider configured
  agents.defaults.model.primary = jan/qwen3.5-35b-a3b

  → Launching: openclaw tui

Workflow

When you run jan launch:

Model Selection: Pick a model (interactively or via --model)
Model Loading: Start the model server with optimized settings
Environment Setup:
- For Claude/Codex: Set environment variables
- For OpenClaw: Write ~/.openclaw/openclaw.json
Agent Launch: Execute the chosen program with the local model pre-wired
Cleanup: When the agent exits, stop the model server

Supported Agents

Claude Code

jan launch claude --model qwen3.5-35b-a3b

Launches Anthropic’s Claude Code agent with:

ANTHROPIC_AUTH_TOKEN set to your API key (default: jan)
ANTHROPIC_BASE_URL pointing to local model
All Anthropic model defaults (OPUS, SONNET, HAIKU) set to your local model
Auto-fit enabled by default for maximum context window

Codex CLI

jan launch codex --model qwen3.5-35b-a3b

Launches OpenAI’s Codex CLI with:

OPENAI_API_KEY set to your API key (default: jan)
OPENAI_BASE_URL pointing to local model
OPENAI_MODEL set to your local model ID

OpenClaw

jan launch openclaw --model qwen3.5-35b-a3b

Launches the open-source OpenClaw agent with:

~/.openclaw/openclaw.json configured with Jan provider
Default model set to jan/<model_id>
OpenClaw’s TUI automatically started (unless you pass custom args)

Performance Tips

Maximize Context for Claude Code

jan launch claude --model qwen3.5-35b

Auto-fit is enabled by default when launching Claude, maximizing the context window based on available VRAM.

Custom Context Size

jan launch claude --model qwen3.5-35b --ctx-size 8192

Setting --ctx-size explicitly disables auto-fit and uses your specified size.

CPU-Only Mode

jan launch claude --model qwen3.5-35b --n-gpu-layers 0

HuggingFace Auto-Download

Download and launch with a HuggingFace model:

jan launch claude --model Qwen/Qwen2.5-35B-Instruct-GGUF

Jan will:

Fetch available GGUF files
Let you pick a quantization
Download the model
Start the model server
Launch Claude Code

For private/gated models:

export HF_TOKEN="your_token_here"
jan launch claude --model meta-llama/Llama-3.3-70B-Instruct-GGUF

Troubleshooting

Agent Not Found

Error launching 'claude': No such file or directory

Solution: Ensure the agent is installed and available in your PATH.

# For Claude Code
which claude

# For OpenClaw
which openclaw

Model Not Found

Error: model not found in data folder

Solution: Download the model using the Jan desktop app, or use a HuggingFace repo ID to auto-download.

Binary Not Found

✗ llama-server binary not found

Solution: Install a backend from Jan’s settings, or specify the binary path with --bin.

OpenClaw Config Override

If OpenClaw still uses a cloud provider instead of Jan: Solution: Check for environment variables that override the config:

env | grep -E '(OPENAI|ANTHROPIC|GEMINI|MISTRAL|GROQ|XAI|OPENROUTER)'

Jan clears these automatically, but they may be set in your shell config (.bashrc, .zshrc, etc.).

Serve Command

Run models without launching an agent

Commands Reference

Complete reference for all CLI commands

CLI

Extensions

API Reference

Core Library

jan launch

Usage

Arguments

Options

Model Selection

Server Configuration

Performance Configuration

Output Control

Examples

Environment Variables

For Claude Code & Codex

For OpenClaw

Output

Loading

For OpenClaw

Workflow

Supported Agents

Claude Code

Codex CLI

OpenClaw

Performance Tips

Maximize Context for Claude Code

Custom Context Size

CPU-Only Mode

HuggingFace Auto-Download

Troubleshooting

Agent Not Found

Model Not Found

Binary Not Found

OpenClaw Config Override

See Also

Serve Command

Commands Reference

​Usage

​Arguments

​Options

​Model Selection

​Server Configuration

​Performance Configuration

​Output Control

​Examples

​Environment Variables

​For Claude Code & Codex

​For OpenClaw

​Output

​Loading

​For OpenClaw

​Workflow

​Supported Agents

​Claude Code

​Codex CLI

​OpenClaw

​Performance Tips

​Maximize Context for Claude Code

​Custom Context Size

​CPU-Only Mode

​HuggingFace Auto-Download

​Troubleshooting

​Agent Not Found

​Model Not Found

​Binary Not Found

​OpenClaw Config Override

​See Also

Serve Command

Commands Reference

Usage

Arguments

Options

Model Selection

Server Configuration

Performance Configuration

Output Control

Examples

Environment Variables

For Claude Code & Codex

For OpenClaw

Output

Loading

For OpenClaw

Workflow

Supported Agents

Claude Code

Codex CLI

OpenClaw

Performance Tips

Maximize Context for Claude Code

Custom Context Size

CPU-Only Mode

HuggingFace Auto-Download

Troubleshooting

Agent Not Found

Model Not Found

Binary Not Found

OpenClaw Config Override

See Also