Where is Crush's config file?

The global config lives at `~/.config/crush/crushrc` (`%USERPROFILE%\.config\crush\crushrc` on Windows). It's a Bash script that Crush runs at startup. Project-level config can go in `./.crushrc` or `./crushrc` in the current directory, which takes priority over the global one. Note that the `crush.json` inside `~/.local/share/crush/` (`%LOCALAPPDATA%\crush\` on Windows) is machine-owned state — **don't edit it by hand**.

Tutorials tell me to edit crush.json — does that still work?

It still works, but it's officially **deprecated** — the maintainers state that new configuration options will only be added to the Bash config, and JSON won't receive new features. Use `crushrc` instead. If you already have a JSON config, start Crush and simply ask it in plain language to convert the config for you.

Does the Base URL need a `/v1` suffix?

The two types are opposites. For `--type anthropic`, enter `https://api.lmuai.com` (**no** `/v1` — Crush appends `/v1/messages` itself; adding it produces `/v1/v1/messages` and a 404). For `--type openai-compat`, enter `https://api.lmuai.com/v1` (**with** `/v1`).

I've configured it but LMU AI models don't show up under /models

Crush's built-in model list comes from the Catwalk database, which doesn't include LMU AI model IDs — you have to register them yourself with `model add / `. Restart Crush after registering, and they'll be selectable via `/models` in a session.

Can I put the API key directly in crushrc?

Yes — just pass the `sk-` key generated in the LMU AI console straight to `--api-key`; that's the common setup. Do note the official warning, though: both crushrc and crush.json are **trusted code** that runs with your shell privileges before the UI appears, so don't launch Crush in a directory whose config you haven't reviewed.

Crush

Connect the Crush terminal AI coding tool to the LMU AI API — add a custom provider in crushrc to use Claude, GPT and Chinese models.

Crush is a terminal AI coding tool from Charm, offering both a CLI and a TUI for code generation, debugging, conversation, file operations, and multitasking from the command line. It supports custom providers — this page covers connecting it to LMU AI.

Install Crush

Pick whichever method suits your system:

brew install charmbracelet/tap/crush

npm install -g @charmland/crush

winget install charmbracelet.crush

Or with Scoop:

scoop bucket add charm https://github.com/charmbracelet/scoop-bucket.git
scoop install crush

yay -S crush-bin

nix run github:numtide/nix-ai-tools#crush

Configure LMU AI

Crush is configured with a Bash script. Edit the global config file:

macOS / Linux: ~/.config/crush/crushrc
Windows: %USERPROFILE%\.config\crush\crushrc

There are two steps: add LMU AI as a provider with provider add, then register the models you want with model add. Choose the protocol that matches the models you plan to use:

Works for OpenAI models such as gpt-5.6-sol and gpt-5.5. Claude and Chinese models can also go through this protocol (the LMU AI backend handles the protocol conversion).

# Add LMU AI as a provider (OpenAI-compatible protocol)
provider add lmuai \
  --type openai-compat \
  --base-url "https://api.lmuai.com/v1" \
  --api-key "sk-your-lmu-ai-api-key"

# Register the models you want
model add lmuai/gpt-5.6-sol --name "GPT-5.6 Sol" --context-window 400000
model add lmuai/claude-opus-5 --name "Claude Opus 5" --context-window 200000

# Set it as the default large-model slot
model large lmuai/claude-opus-5

The type is openai-compat, not openai

Crush has two OpenAI types. Per the official docs, openai is for proxying or routing requests through OpenAI itself, while openai-compat is for non-OpenAI providers that offer OpenAI-compatible APIs. LMU AI is the latter, so use openai-compat.

Works for models served over the Anthropic protocol, such as claude-opus-5, claude-sonnet-5, qwen3.8-max-preview, deepseek-v4-pro, glm-5.2, and kimi-k3.

# Add LMU AI as a provider (Anthropic protocol)
provider add lmuai-anthropic \
  --type anthropic \
  --base-url "https://api.lmuai.com" \
  --api-key "sk-your-lmu-ai-api-key" \
  --extra-header anthropic-version 2023-06-01

# Register the models you want
model add lmuai-anthropic/claude-opus-5 \
  --name "Claude Opus 5" \
  --context-window 200000 \
  --can-reason true \
  --supports-images true

model add lmuai-anthropic/glm-5.2 --name "GLM-5.2" --context-window 200000

# Set it as the default large-model slot
model large lmuai-anthropic/claude-opus-5

Don't add /v1 to the Anthropic base URL

Set --base-url to https://api.lmuai.com — not https://api.lmuai.com/v1. Crush appends /v1/messages itself, so the extra segment makes it request /v1/v1/messages, which fails with:

not found: POST "https://api.lmuai.com/v1/v1/messages": 404 Not Found

This is the opposite of openai-compat (which does need /v1) — don't mix them up.

Config files are trusted code

An official warning: crushrc runs with your shell privileges before the UI appears, and any $(...) in crush.json runs at load time. Don't launch Crush in a directory whose config you haven't reviewed, and don't source config files of unknown origin.

Start using it

Restart Crush once configured:

crush

Switch models from within a session with:

/models

LMU AI models missing from /models?

Crush's built-in model list comes from the Catwalk database, which doesn't include LMU AI model IDs. You must register them with model add <provider>/<model-id> first — they'll appear in the /models list after a restart.

Common model IDs

Model ID	Notes
`claude-opus-5`	Claude Opus 5 (flagship, recommended)
`claude-sonnet-5`	Claude Sonnet 5 (balanced)
`claude-haiku-4-5`	Claude Haiku 4.5 (fast)
`gpt-5.6-sol`	GPT-5.6 Sol
`glm-5.2`	GLM-5.2
`qwen3.8-max-preview`	Qwen 3.8 Max Preview
`deepseek-v4-pro`	DeepSeek V4 Pro
`kimi-k3`	Kimi K3

Not sure which model to enter? Go to the Model Gallery to see every available model ID and copy it with one click.

Legacy JSON config

crush.json is officially deprecated

Crush originally used crush.json, which is now deprecated — the maintainers have said they'll keep supporting it, but new configuration options will only be added to the Bash config (crushrc). Plenty of tutorials still teach the JSON format, but new setups should use crushrc as shown above.

Already have a JSON config and want to migrate? Start Crush and just ask it in plain language to convert it for you.

If you do want to use JSON, the format looks like this (in a crush.json in your project directory or under ~/.config/crush/):

{
  "$schema": "https://charm.land/crush.json",
  "providers": {
    "lmuai": {
      "id": "lmuai",
      "name": "LMU AI",
      "type": "openai-compat",
      "base_url": "https://api.lmuai.com/v1",
      "api_key": "sk-your-lmu-ai-api-key",
      "models": [
        {
          "id": "claude-opus-5",
          "name": "Claude Opus 5",
          "context_window": 200000,
          "default_max_tokens": 32000
        }
      ]
    }
  }
}

Don't omit type and models in JSON

Just id / name / base_url / api_key won't work: type decides which protocol is used (omitting it falls back to a default guess), and models decides what you can pick under /models. This is the most common reason a copy-pasted minimal example fails.

Notes

The config file is ~/.config/crush/crushrc (%USERPROFILE%\.config\crush\crushrc on Windows); ~/.local/share/crush/crush.json is machine-owned state — don't edit it
Use --type openai-compat for LMU AI's OpenAI-compatible endpoint (not openai), and --type anthropic for the Anthropic protocol
The two types take opposite --base-url forms: anthropic takes https://api.lmuai.com (no /v1), while openai-compat takes https://api.lmuai.com/v1 (with /v1). Adding /v1 on the Anthropic side produces /v1/v1/messages and a 404
For the API key, just enter the sk- key generated in the LMU AI console
LMU AI models aren't in Crush's built-in list, so they must be registered with model add before they appear under /models

Last updated: 2026-09-09