NOTE: This is a personal fork of Crush where I'm experimenting with things. You'll also find my patches merged here before they're merged into upstream. I've also unconditionally disabled metrics and yote the CLA; devs shouldn't assign their copyrights to maintainers and hand them the rug they'll yank from under you later.

Install my fork either…

• Using bin (highly recommended because it's one tool to manage and update myriad CLI tools distributed as statically-linked binaries, like nasin pali)

  bin install goinstall://git.secluded.site/crush@latest
  

• Or using the go toolchain (requires tracking updates manually)

  go install git.secluded.site/crush@latest
  

I pull upstream changes into the upstream branch here, break my branches off that, then merge them into my dev branch, which gets rebased on upstream fairly often. dev history will get rewritten frequently.

Contributions are welcome (see following section) and I'll try to maintain anything I accept here.

Contributions

Patch requests are in amolith/llm-projects on pr.pico.sh. You don't need a new account to contribute, you don't need to fork this repo, you don't need to fiddle with git send-email, you don't need to faff with your email client to get git request-pull working...

You just need:

• Git
• SSH
• An SSH key

# Clone this repo, make your changes, and commit them
# Create a new patch request with
git format-patch origin/main --stdout | ssh pr.pico.sh pr create amolith/llm-projects
# After potential feedback, submit a revision to an existing patch request with
git format-patch origin/main --stdout | ssh pr.pico.sh pr add {prID}
# List patch requests
ssh pr.pico.sh pr ls amolith/llm-projects

See "How do Patch Requests work?" on pr.pico.sh's home page for a more complete example workflow.

Everything from here on is from the original Crush README.

Crush

Your new coding bestie, now available in your favourite terminal.
Your tools, your code, and your workflows, wired into your LLM of choice.

你的新编程伙伴，现在就在你最爱的终端中。
你的工具、代码和工作流，都与您选择的 LLM 模型紧密相连。

Features

• Multi-Model: choose from a wide range of LLMs or add your own via OpenAI- or Anthropic-compatible APIs
• Flexible: switch LLMs mid-session while preserving context
• Session-Based: maintain multiple work sessions and contexts per project
• LSP-Enhanced: Crush uses LSPs for additional context, just like you do
• Extensible: add capabilities via MCPs (http, stdio, and sse)
• Works Everywhere: first-class support in every terminal on macOS, Linux, Windows (PowerShell and WSL), FreeBSD, OpenBSD, and NetBSD

Installation

Use a package manager:

# Homebrew
brew install charmbracelet/tap/crush

# NPM
npm install -g @charmland/crush

# Arch Linux (btw)
yay -S crush-bin

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

Windows users:

# Winget
winget install charmbracelet.crush

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

# Add the NUR channel.
nix-channel --add https://github.com/nix-community/NUR/archive/main.tar.gz nur
nix-channel --update

# Get Crush in a Nix shell.
nix-shell -p '(import <nur> { pkgs = import <nixpkgs> {}; }).repos.charmbracelet.crush'

{
  inputs = {
    nixpkgs.url = "github:NixOS/nixpkgs/nixos-unstable";
    nur.url = "github:nix-community/NUR";
  };

  outputs = { self, nixpkgs, nur, ... }: {
    nixosConfigurations.your-hostname = nixpkgs.lib.nixosSystem {
      system = "x86_64-linux";
      modules = [
        nur.modules.nixos.default
        nur.repos.charmbracelet.modules.crush
        {
          programs.crush = {
            enable = true;
            settings = {
              providers = {
                openai = {
                  id = "openai";
                  name = "OpenAI";
                  base_url = "https://api.openai.com/v1";
                  type = "openai";
                  api_key = "sk-fake123456789abcdef...";
                  models = [
                    {
                      id = "gpt-4";
                      name = "GPT-4";
                    }
                  ];
                };
              };
              lsp = {
                go = { command = "gopls"; enabled = true; };
                nix = { command = "nil"; enabled = true; };
              };
              options = {
                context_paths = [ "/etc/nixos/configuration.nix" ];
                tui = { compact_mode = true; };
                debug = false;
              };
            };
          };
        }
      ];
    };
  };
}

sudo mkdir -p /etc/apt/keyrings
curl -fsSL https://repo.charm.sh/apt/gpg.key | sudo gpg --dearmor -o /etc/apt/keyrings/charm.gpg
echo "deb [signed-by=/etc/apt/keyrings/charm.gpg] https://repo.charm.sh/apt/ * *" | sudo tee /etc/apt/sources.list.d/charm.list
sudo apt update && sudo apt install crush

echo '[charm]
name=Charm
baseurl=https://repo.charm.sh/yum/
enabled=1
gpgcheck=1
gpgkey=https://repo.charm.sh/yum/gpg.key' | sudo tee /etc/yum.repos.d/charm.repo
sudo yum install crush

Or, download it:

• Packages are available in Debian and RPM formats
• Binaries are available for Linux, macOS, Windows, FreeBSD, OpenBSD, and NetBSD

Or just install it with Go:

go install github.com/charmbracelet/crush@latest

[!WARNING] Productivity may increase when using Crush and you may find yourself nerd sniped when first using the application. If the symptoms persist, join the Discord and nerd snipe the rest of us.

Getting Started

The quickest way to get started is to grab an API key for your preferred provider such as Anthropic, OpenAI, Groq, or OpenRouter and just start Crush. You'll be prompted to enter your API key.

That said, you can also set environment variables for preferred providers.

By the Way

Is there a provider you’d like to see in Crush? Is there an existing model that needs an update?

Crush’s default model listing is managed in Catwalk, a community-supported, open source repository of Crush-compatible models, and you’re welcome to contribute.

Configuration

Crush runs great with no configuration. That said, if you do need or want to customize Crush, configuration can be added either local to the project itself, or globally, with the following priority:

1. .crush.json
2. crush.json
3. $HOME/.config/crush/crush.json

Configuration itself is stored as a JSON object:

{
  "this-setting": { "this": "that" },
  "that-setting": ["ceci", "cela"]
}

As an additional note, Crush also stores ephemeral data, such as application state, in one additional location:

# Unix
$HOME/.local/share/crush/crush.json

# Windows
%LOCALAPPDATA%\crush\crush.json

LSPs

Crush can use LSPs for additional context to help inform its decisions, just like you would. LSPs can be added manually like so:

{
  "$schema": "https://charm.land/crush.json",
  "lsp": {
    "go": {
      "command": "gopls",
      "env": {
        "GOTOOLCHAIN": "go1.24.5"
      }
    },
    "typescript": {
      "command": "typescript-language-server",
      "args": ["--stdio"]
    },
    "nix": {
      "command": "nil"
    }
  }
}

MCPs

Crush also supports Model Context Protocol (MCP) servers through three transport types: stdio for command-line servers, http for HTTP endpoints, and sse for Server-Sent Events. Environment variable expansion is supported using $(echo $VAR) syntax.

{
  "$schema": "https://charm.land/crush.json",
  "mcp": {
    "filesystem": {
      "type": "stdio",
      "command": "node",
      "args": ["/path/to/mcp-server.js"],
      "timeout": 120,
      "disabled": false,
      "env": {
        "NODE_ENV": "production"
      }
    },
    "github": {
      "type": "http",
      "url": "https://api.githubcopilot.com/mcp/",
      "timeout": 120,
      "disabled": false,
      "headers": {
        "Authorization": "Bearer $GH_PAT"
      }
    },
    "streaming-service": {
      "type": "sse",
      "url": "https://example.com/mcp/sse",
      "timeout": 120,
      "disabled": false,
      "headers": {
        "API-Key": "$(echo $API_KEY)"
      }
    }
  }
}

Memory

Crush automatically includes two memory files for cross-project instructions.

• ~/.config/crush/CRUSH.md: Crush-specific rules that would confuse other agentic coding tools. If you only use Crush, this is the only one you need to edit.
• ~/.config/AGENTS.md: generic instructions that other coding tools might read. Avoid referring to Crush-specific tools or workflows here.

You can customize these paths using the memory_paths option in your configuration:

{
  "$schema": "https://charm.land/crush.json",
  "options": {
    "memory_paths": [
      "/path/to/custom/memory/file.md",
      "/path/to/folder/of/files/" // recursively load all .md files in folder
    ]
  }
}

Ignoring Files

Crush respects .gitignore files by default, but you can also create a .crushignore file to specify additional files and directories that Crush should ignore. This is useful for excluding files that you want in version control but don't want Crush to consider when providing context.

The .crushignore file uses the same syntax as .gitignore and can be placed in the root of your project or in subdirectories.

Allowing Tools

By default, Crush will ask you for permission before running tool calls. If you'd like, you can allow tools to be executed without prompting you for permissions. Use this with care.

{
  "$schema": "https://charm.land/crush.json",
  "permissions": {
    "allowed_tools": [
      "view",
      "ls",
      "grep",
      "edit",
      "mcp_context7_get-library-doc"
    ]
  }
}

You can also skip all permission prompts entirely by running Crush with the --yolo flag. Be very, very careful with this feature.

Initialization

When you initialize a project, Crush analyzes your codebase and creates a context file that helps it work more effectively in future sessions. By default, this file is named AGENTS.md, but you can customize the name and location with the initialize_as option:

{
  "$schema": "https://charm.land/crush.json",
  "options": {
    "initialize_as": "AGENTS.md"
  }
}

This is useful if you prefer a different naming convention or want to place the file in a specific directory (e.g., CRUSH.md or docs/LLMs.md). Crush will fill the file with project-specific context like build commands, code patterns, and conventions it discovered during initialization.

Attribution Settings

By default, Crush adds attribution information to Git commits and pull requests it creates. You can customize this behavior with the attribution option:

{
  "$schema": "https://charm.land/crush.json",
  "options": {
    "attribution": {
      "trailer_style": "co-authored-by",
      "generated_with": true
    }
  }
}

• trailer_style: Controls the attribution trailer added to commit messages (default: assisted-by)
  • assisted-by: Adds Assisted-by: [Model Name] via Crush <crush@charm.land> (includes the model name)
  • co-authored-by: Adds Co-Authored-By: Crush <crush@charm.land>
  • none: No attribution trailer
• generated_with: When true (default), adds 💘 Generated with Crush line to commit messages and PR descriptions

Custom Providers

Crush supports custom provider configurations for both OpenAI-compatible and Anthropic-compatible APIs.

[!NOTE] Note that we support two "types" for OpenAI. Make sure to choose the right one to ensure the best experience!

• openai should be used when proxying or routing requests through OpenAI.
• openai-compat should be used when using non-OpenAI providers that have OpenAI-compatible APIs.

OpenAI-Compatible APIs

Here’s an example configuration for Deepseek, which uses an OpenAI-compatible API. Don't forget to set DEEPSEEK_API_KEY in your environment.

{
  "$schema": "https://charm.land/crush.json",
  "providers": {
    "deepseek": {
      "type": "openai-compat",
      "base_url": "https://api.deepseek.com/v1",
      "api_key": "$DEEPSEEK_API_KEY",
      "models": [
        {
          "id": "deepseek-chat",
          "name": "Deepseek V3",
          "cost_per_1m_in": 0.27,
          "cost_per_1m_out": 1.1,
          "cost_per_1m_in_cached": 0.07,
          "cost_per_1m_out_cached": 1.1,
          "context_window": 64000,
          "default_max_tokens": 5000
        }
      ]
    }
  }
}

Anthropic-Compatible APIs

Custom Anthropic-compatible providers follow this format:

{
  "$schema": "https://charm.land/crush.json",
  "providers": {
    "custom-anthropic": {
      "type": "anthropic",
      "base_url": "https://api.anthropic.com/v1",
      "api_key": "$ANTHROPIC_API_KEY",
      "extra_headers": {
        "anthropic-version": "2023-06-01"
      },
      "models": [
        {
          "id": "claude-sonnet-4-20250514",
          "name": "Claude Sonnet 4",
          "cost_per_1m_in": 3,
          "cost_per_1m_out": 15,
          "cost_per_1m_in_cached": 3.75,
          "cost_per_1m_out_cached": 0.3,
          "context_window": 200000,
          "default_max_tokens": 50000,
          "can_reason": true,
          "supports_attachments": true
        }
      ]
    }
  }
}

Amazon Bedrock

Crush currently supports running Anthropic models through Bedrock, with caching disabled.

• A Bedrock provider will appear once you have AWS configured, i.e. aws configure
• Crush also expects the AWS_REGION or AWS_DEFAULT_REGION to be set
• To use a specific AWS profile set AWS_PROFILE in your environment, i.e. AWS_PROFILE=myprofile crush
• Alternatively to aws configure, you can also just set AWS_BEARER_TOKEN_BEDROCK

Vertex AI Platform

Vertex AI will appear in the list of available providers when VERTEXAI_PROJECT and VERTEXAI_LOCATION are set. You will also need to be authenticated:

gcloud auth application-default login

To add specific models to the configuration, configure as such:

{
  "$schema": "https://charm.land/crush.json",
  "providers": {
    "vertexai": {
      "models": [
        {
          "id": "claude-sonnet-4@20250514",
          "name": "VertexAI Sonnet 4",
          "cost_per_1m_in": 3,
          "cost_per_1m_out": 15,
          "cost_per_1m_in_cached": 3.75,
          "cost_per_1m_out_cached": 0.3,
          "context_window": 200000,
          "default_max_tokens": 50000,
          "can_reason": true,
          "supports_attachments": true
        }
      ]
    }
  }
}

Local Models

Local models can also be configured via OpenAI-compatible API. Here are two common examples:

Ollama

{
  "providers": {
    "ollama": {
      "name": "Ollama",
      "base_url": "http://localhost:11434/v1/",
      "type": "openai-compat",
      "models": [
        {
          "name": "Qwen 3 30B",
          "id": "qwen3:30b",
          "context_window": 256000,
          "default_max_tokens": 20000
        }
      ]
    }
  }
}

LM Studio

{
  "providers": {
    "lmstudio": {
      "name": "LM Studio",
      "base_url": "http://localhost:1234/v1/",
      "type": "openai-compat",
      "models": [
        {
          "name": "Qwen 3 30B",
          "id": "qwen/qwen3-30b-a3b-2507",
          "context_window": 256000,
          "default_max_tokens": 20000
        }
      ]
    }
  }
}

Logging

Sometimes you need to look at logs. Luckily, Crush logs all sorts of stuff. Logs are stored in ./.crush/logs/crush.log relative to the project.

The CLI also contains some helper commands to make perusing recent logs easier:

# Print the last 1000 lines
crush logs

# Print the last 500 lines
crush logs --tail 500

# Follow logs in real time
crush logs --follow

Want more logging? Run crush with the --debug flag, or enable it in the config:

{
  "$schema": "https://charm.land/crush.json",
  "options": {
    "debug": true,
    "debug_lsp": true
  }
}

Desktop Notifications

Crush defaults to sending desktop notifications that let you know:

• When its turn is finished (automatically cancelled when you interact with the chat interface)
• When it's waiting for permission to execute a tool (automatically cancelled when you interact with the permission dialog)

Disabling notifications

If you prefer to work without desktop notifications, you can disable them in your crush.json config.

{
  "$schema": "https://charm.land/crush.json",
  "options": {
    "disable_notifications": true
  }
}

Provider Auto-Updates

By default, Crush automatically checks for the latest and greatest list of providers and models from Catwalk, the open source Crush provider database. This means that when new providers and models are available, or when model metadata changes, Crush automatically updates your local configuration.

Disabling automatic provider updates

For those with restricted internet access, or those who prefer to work in air-gapped environments, this might not be want you want, and this feature can be disabled.

To disable automatic provider updates, set disable_provider_auto_update into your crush.json config:

{
  "$schema": "https://charm.land/crush.json",
  "options": {
    "disable_provider_auto_update": true
  }
}

Or set the CRUSH_DISABLE_PROVIDER_AUTO_UPDATE environment variable:

export CRUSH_DISABLE_PROVIDER_AUTO_UPDATE=1

Manually updating providers

Manually updating providers is possible with the crush update-providers command:

# Update providers remotely from Catwalk.
crush update-providers

# Update providers from a custom Catwalk base URL.
crush update-providers https://example.com/

# Update providers from a local file.
crush update-providers /path/to/local-providers.json

# Reset providers to the embedded version, embedded at crush at build time.
crush update-providers embedded

# For more info:
crush update-providers --help

Metrics

Crush records pseudonymous usage metrics (tied to a device-specific hash), which maintainers rely on to inform development and support priorities. The metrics include solely usage metadata; prompts and responses are NEVER collected.

Details on exactly what’s collected are in the source code (here and here).

You can opt out of metrics collection at any time by setting the environment variable by setting the following in your environment:

export CRUSH_DISABLE_METRICS=1

Or by setting the following in your config:

{
  "options": {
    "disable_metrics": true
  }
}

Crush also respects the DO_NOT_TRACK convention which can be enabled via export DO_NOT_TRACK=1.

A Note on Claude Max and GitHub Copilot

Crush only supports model providers through official, compliant APIs. We do not support or endorse any methods that rely on personal Claude Max and GitHub Copilot accounts or OAuth workarounds, which violate Anthropic and Microsoft’s Terms of Service.

We’re committed to building sustainable, trusted integrations with model providers. If you’re a provider interested in working with us, reach out.

Contributing

See the contributing guide.

Whatcha think?

We’d love to hear your thoughts on this project. Need help? We gotchu. You can find us on:

• Twitter
• Slack
• Discord
• The Fediverse
• Bluesky

License

FSL-1.1-MIT

Part of Charm.

Charm热爱开源 • Charm loves open source