{"id":29936311,"url":"https://github.com/charmbracelet/crush","last_synced_at":"2026-06-06T03:01:48.612Z","repository":{"id":307157953,"uuid":"987670088","full_name":"charmbracelet/crush","owner":"charmbracelet","description":"Glamourous agentic coding for all 💘","archived":false,"fork":false,"pushed_at":"2026-04-26T01:05:33.000Z","size":24810,"stargazers_count":23502,"open_issues_count":407,"forks_count":1564,"subscribers_count":96,"default_branch":"main","last_synced_at":"2026-04-26T03:35:06.455Z","etag":null,"topics":["agentic-ai","ai","llms","ravishing"],"latest_commit_sha":null,"homepage":"","language":"Go","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/charmbracelet.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":"CLA.md"}},"created_at":"2025-05-21T12:14:57.000Z","updated_at":"2026-04-26T02:56:52.000Z","dependencies_parsed_at":"2025-07-29T20:26:24.586Z","dependency_job_id":"d0a74e89-3114-4740-939e-2c97894ea3e7","html_url":"https://github.com/charmbracelet/crush","commit_stats":null,"previous_names":["charmbracelet/crush","charmbracelet/opencode"],"tags_count":158,"template":false,"template_full_name":null,"purl":"pkg:github/charmbracelet/crush","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/charmbracelet%2Fcrush","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/charmbracelet%2Fcrush/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/charmbracelet%2Fcrush/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/charmbracelet%2Fcrush/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/charmbracelet","download_url":"https://codeload.github.com/charmbracelet/crush/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/charmbracelet%2Fcrush/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32408447,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-29T02:37:21.628Z","status":"ssl_error","status_checked_at":"2026-04-29T02:36:50.947Z","response_time":110,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agentic-ai","ai","llms","ravishing"],"created_at":"2025-08-02T22:02:04.014Z","updated_at":"2026-06-02T03:01:51.440Z","avatar_url":"https://github.com/charmbracelet.png","language":"Go","funding_links":[],"categories":["Go","HarmonyOS","\u003ca name=\"programming\"\u003e\u003c/a\u003eProgramming","📚 Tools","AI","💻 Terminal-Based AI Agents","Runtime","Tools and Code","Agent workflow highlights","Tools","CLI Coding Tools","Agent Harness 🚀","CLI \u0026 Terminal Tools","命令行工具","CLI","A01_文本生成_文本对话","Agents \u0026 Orchestration","Available on GitHub","ツール","Development Toolkits","Terminal-Based AI Agents","Alternatives to Claude Code","Table of Contents","🚀 AI Tools for Vim, Neovim, and Terminal","1. Local Agents","💻 Terminal \u0026 CLI Agents","AI Agent Frameworks","Terminal-native coding agents","AI Coding Assistants \u0026 Agents","🔭 Tools"],"sub_categories":["Windows Manager","🌟 What You'll Find Here:","AI Terminal","Vibe Coding and AI Coding Assistants","Coding Agents","AI Agents Stack","5. The Convergence: Harness-as-a-Service (HaaS)","AI Coding CLIs","大语言对话模型及数据","IDE \u0026 エディタアシスタント","CLI Tools","Coding Agents \u0026 IDE Extensions","Agent","Open Source","Interactive Pair Programmers"],"readme":"# Crush\n\n\u003cp align=\"center\"\u003e\n    \u003ca href=\"https://stuff.charm.sh/crush/charm-crush.png\"\u003e\u003cimg width=\"450\" alt=\"Charm Crush Logo\" src=\"https://github.com/user-attachments/assets/cf8ca3ce-8b02-43f0-9d0f-5a331488da4b\" /\u003e\u003c/a\u003e\u003cbr /\u003e\n    \u003ca href=\"https://github.com/charmbracelet/crush/releases\"\u003e\u003cimg src=\"https://img.shields.io/github/release/charmbracelet/crush\" alt=\"Latest Release\"\u003e\u003c/a\u003e\n    \u003ca href=\"https://github.com/charmbracelet/crush/actions\"\u003e\u003cimg src=\"https://github.com/charmbracelet/crush/actions/workflows/build.yml/badge.svg\" alt=\"Build Status\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003eYour new coding bestie, now available in your favourite terminal.\u003cbr /\u003eYour tools, your code, and your workflows, wired into your LLM of choice.\u003c/p\u003e\n\u003cp align=\"center\"\u003e终端里的编程新搭档，\u003cbr /\u003e无缝接入你的工具、代码与工作流，全面兼容主流 LLM 模型。\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\u003cimg width=\"800\" alt=\"Crush Demo\" src=\"https://github.com/user-attachments/assets/58280caf-851b-470a-b6f7-d5c4ea8a1968\" /\u003e\u003c/p\u003e\n\n## Features\n\n- **Multi-Model:** choose from a wide range of LLMs or add your own via OpenAI- or Anthropic-compatible APIs\n- **Flexible:** switch LLMs mid-session while preserving context\n- **Session-Based:** maintain multiple work sessions and contexts per project\n- **LSP-Enhanced:** Crush uses LSPs for additional context, just like you do\n- **Extensible:** add capabilities via MCPs (`http`, `stdio`, and `sse`)\n- **Works Everywhere:** first-class support in every terminal on macOS, Linux, Windows (PowerShell and WSL), Android, FreeBSD, OpenBSD, and NetBSD\n- **Industrial Grade:** built on the Charm ecosystem, powering 25k+ applications, from leading open source projects to business-critical infrastructure\n\n## Installation\n\nUse a package manager:\n\n```bash\n# Homebrew\nbrew install charmbracelet/tap/crush\n\n# NPM\nnpm install -g @charmland/crush\n\n# Arch Linux (btw)\nyay -S crush-bin\n\n# Nix\nnix run github:numtide/nix-ai-tools#crush\n\n# FreeBSD\npkg install crush\n```\n\nWindows users:\n\n```bash\n# Winget\nwinget install charmbracelet.crush\n\n# Scoop\nscoop bucket add charm https://github.com/charmbracelet/scoop-bucket.git\nscoop install crush\n```\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eNix (NUR)\u003c/strong\u003e\u003c/summary\u003e\n\nCrush is available via the official Charm [NUR](https://github.com/nix-community/NUR) in `nur.repos.charmbracelet.crush`, which is the most up-to-date way to get Crush in Nix.\n\nYou can also try out Crush via the NUR with `nix-shell`:\n\n```bash\n# Add the NUR channel.\nnix-channel --add https://github.com/nix-community/NUR/archive/main.tar.gz nur\nnix-channel --update\n\n# Get Crush in a Nix shell.\nnix-shell -p '(import \u003cnur\u003e { pkgs = import \u003cnixpkgs\u003e {}; }).repos.charmbracelet.crush'\n```\n\n### NixOS \u0026 Home Manager Module Usage via NUR\n\nCrush provides NixOS and Home Manager modules via NUR.\nYou can use these modules directly in your flake by importing them from NUR. Since it auto detects whether its a home manager or nixos context you can use the import the exact same way :)\n\n```nix\n{\n  inputs = {\n    nixpkgs.url = \"github:NixOS/nixpkgs/nixos-unstable\";\n    nur.url = \"github:nix-community/NUR\";\n  };\n\n  outputs = { self, nixpkgs, nur, ... }: {\n    nixosConfigurations.your-hostname = nixpkgs.lib.nixosSystem {\n      system = \"x86_64-linux\";\n      modules = [\n        nur.modules.nixos.default\n        nur.repos.charmbracelet.modules.crush\n        {\n          programs.crush = {\n            enable = true;\n            settings = {\n              providers = {\n                openai = {\n                  id = \"openai\";\n                  name = \"OpenAI\";\n                  base_url = \"https://api.openai.com/v1\";\n                  type = \"openai\";\n                  api_key = \"sk-fake123456789abcdef...\";\n                  models = [\n                    {\n                      id = \"gpt-4\";\n                      name = \"GPT-4\";\n                    }\n                  ];\n                };\n              };\n              lsp = {\n                go = { command = \"gopls\"; enabled = true; };\n                nix = { command = \"nil\"; enabled = true; };\n              };\n              options = {\n                context_paths = [ \"/etc/nixos/configuration.nix\" ];\n                tui = { compact_mode = true; };\n                debug = false;\n              };\n            };\n          };\n        }\n      ];\n    };\n  };\n}\n```\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eDebian/Ubuntu\u003c/strong\u003e\u003c/summary\u003e\n\n```bash\nsudo mkdir -p /etc/apt/keyrings\ncurl -fsSL https://repo.charm.sh/apt/gpg.key | sudo gpg --dearmor -o /etc/apt/keyrings/charm.gpg\necho \"deb [signed-by=/etc/apt/keyrings/charm.gpg] https://repo.charm.sh/apt/ * *\" | sudo tee /etc/apt/sources.list.d/charm.list\nsudo apt update \u0026\u0026 sudo apt install crush\n```\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eFedora/RHEL\u003c/strong\u003e\u003c/summary\u003e\n\n```bash\necho '[charm]\nname=Charm\nbaseurl=https://repo.charm.sh/yum/\nenabled=1\ngpgcheck=1\ngpgkey=https://repo.charm.sh/yum/gpg.key' | sudo tee /etc/yum.repos.d/charm.repo\nsudo yum install crush\n```\n\n\u003c/details\u003e\n\nOr, download it:\n\n- [Packages][releases] are available in Debian and RPM formats\n- [Binaries][releases] are available for Linux, macOS, Windows, FreeBSD, OpenBSD, and NetBSD\n\n[releases]: https://github.com/charmbracelet/crush/releases\n\nOr just install it with Go:\n\n```\ngo install github.com/charmbracelet/crush@latest\n```\n\n\u003e [!WARNING]\n\u003e Productivity may increase when using Crush and you may find yourself nerd\n\u003e sniped when first using the application. If the symptoms persist, join the\n\u003e [Slack][slack] or [Discord][discord] and nerd snipe the rest of us.\n\n## Getting Started\n\nThe quickest way to get started is to grab an API key for your preferred\nprovider such as Anthropic, OpenAI, Groq, OpenRouter, or Vercel AI Gateway and just start\nCrush. You'll be prompted to enter your API key.\n\nThat said, you can also set environment variables for preferred providers.\n\n| Environment Variable        | Provider                                           |\n| --------------------------- | -------------------------------------------------- |\n| `HYPER_API_KEY`             | Charm Hyper                                        |\n| `ANTHROPIC_API_KEY`         | Anthropic                                          |\n| `OPENAI_API_KEY`            | OpenAI                                             |\n| `VERCEL_API_KEY`            | Vercel AI Gateway                                  |\n| `GEMINI_API_KEY`            | Google Gemini                                      |\n| `SYNTHETIC_API_KEY`         | Synthetic                                          |\n| `ZAI_API_KEY`               | Z.ai                                               |\n| `MINIMAX_API_KEY`           | MiniMax                                            |\n| `HF_TOKEN`                  | Hugging Face Inference                             |\n| `CEREBRAS_API_KEY`          | Cerebras                                           |\n| `OPENROUTER_API_KEY`        | OpenRouter                                         |\n| `IONET_API_KEY`             | io.net                                             |\n| `ALIBABA_SINGAPORE_API_KEY` | Alibaba (Singapore)                                |\n| `GROQ_API_KEY`              | Groq                                               |\n| `AVIAN_API_KEY`             | Avian                                              |\n| `OPENCODE_API_KEY`          | OpenCode Zen \u0026 Go                                  |\n| `VERTEXAI_PROJECT`          | Google Cloud VertexAI (Gemini)                     |\n| `VERTEXAI_LOCATION`         | Google Cloud VertexAI (Gemini)                     |\n| `AWS_ACCESS_KEY_ID`         | Amazon Bedrock (Claude)                            |\n| `AWS_SECRET_ACCESS_KEY`     | Amazon Bedrock (Claude)                            |\n| `AWS_REGION`                | Amazon Bedrock (Claude)                            |\n| `AWS_PROFILE`               | Amazon Bedrock (Custom Profile)                    |\n| `AWS_BEARER_TOKEN_BEDROCK`  | Amazon Bedrock                                     |\n| `AZURE_OPENAI_API_ENDPOINT` | Azure OpenAI models                                |\n| `AZURE_OPENAI_API_KEY`      | Azure OpenAI models (optional when using Entra ID) |\n| `AZURE_OPENAI_API_VERSION`  | Azure OpenAI models                                |\n\n### Subscriptions\n\nIf you prefer subscription-based usage, here are some plans that work well in\nCrush:\n\n- [Synthetic](https://synthetic.new/pricing)\n- [GLM Coding Plan](https://z.ai/subscribe)\n- [Kimi Code](https://www.kimi.com/membership/pricing)\n- [MiniMax Coding Plan](https://platform.minimax.io/subscribe/coding-plan)\n\n### By the Way\n\nIs there a provider you’d like to see in Crush? Is there an existing model that needs an update?\n\nCrush’s default model listing is managed in [Catwalk](https://github.com/charmbracelet/catwalk), a community-supported, open source repository of Crush-compatible models, and you’re welcome to contribute.\n\n\u003ca href=\"https://github.com/charmbracelet/catwalk\"\u003e\u003cimg width=\"174\" height=\"174\" alt=\"Catwalk Badge\" src=\"https://github.com/user-attachments/assets/95b49515-fe82-4409-b10d-5beb0873787d\" /\u003e\u003c/a\u003e\n\n## Configuration\n\n\u003e [!TIP]\n\u003e Crush ships with a builtin `crush-config` skill for configuring itself. In\n\u003e many cases you can simply ask Crush to configure itself.\n\nCrush runs great with no configuration. That said, if you do need or want to\ncustomize Crush, configuration can be added either local to the project itself,\nor globally, with the following priority:\n\n1. `.crush.json`\n2. `crush.json`\n3. `$HOME/.config/crush/crush.json`\n\nConfiguration itself is stored as a JSON object:\n\n```json\n{\n  \"this-setting\": { \"this\": \"that\" },\n  \"that-setting\": [\"ceci\", \"cela\"]\n}\n```\n\nAs an additional note, Crush also stores ephemeral data, such as application\nstate, in one additional location:\n\n```bash\n# Unix\n$HOME/.local/share/crush/crush.json\n\n# Windows\n%LOCALAPPDATA%\\crush\\crush.json\n```\n\n\u003e [!TIP]\n\u003e You can override the user and data config locations by setting:\n\u003e\n\u003e - `CRUSH_GLOBAL_CONFIG`\n\u003e - `CRUSH_GLOBAL_DATA`\n\n### LSPs\n\nCrush can use LSPs for additional context to help inform its decisions, just\nlike you would. LSPs can be added manually like so:\n\n```json\n{\n  \"$schema\": \"https://charm.land/crush.json\",\n  \"lsp\": {\n    \"go\": {\n      \"command\": \"gopls\",\n      \"env\": {\n        \"GOTOOLCHAIN\": \"go1.24.5\"\n      }\n    },\n    \"typescript\": {\n      \"command\": \"typescript-language-server\",\n      \"args\": [\"--stdio\"]\n    },\n    \"nix\": {\n      \"command\": \"nil\"\n    }\n  }\n}\n```\n\n### MCPs\n\nCrush also supports Model Context Protocol (MCP) servers through three transport\ntypes: `stdio` for command-line servers, `http` for HTTP endpoints, and `sse`\nfor Server-Sent Events.\n\nShell-style value expansion (`$VAR`, `${VAR:-default}`, `$(command)`, quoting,\nnesting) works in `command`, `args`, `env`, `headers`, and `url`, so\nfile-based secrets work out of the box. You can use values like `\"$TOKEN\"`\nor `\"$(cat /path/to/secret/token)\"`. Expansion runs through Crush's embedded\nshell, so the same syntax works on every supported system, Windows included.\n\nUnset variables expand to the empty string by default, matching bash. For\nrequired credentials, use `${VAR:?message}` so an unset variable fails loudly\nat load time with `message` instead of silently resolving to empty:\n\n```json\n{ \"api_key\": \"${CODEBERG_TOKEN:?set CODEBERG_TOKEN}\" }\n```\n\nHeaders (both MCP `headers` and provider `extra_headers`) whose value\nresolves to the empty string are dropped from the outgoing request rather\nthan sent as `Header:`. That keeps optional env-gated headers like\n`\"OpenAI-Organization\": \"$OPENAI_ORG_ID\"` clean when the variable is unset.\n\nProvider `extra_body` is a non-expanding JSON passthrough; put env-driven\nvalues in `extra_headers` or the provider's `api_key` / `base_url`, all of\nwhich do expand.\n\n\u003e **Security note:** `crush.json` is trusted code. Any `$(...)` in it runs at\n\u003e load time with your shell's privileges, before the UI appears. Don't launch\n\u003e Crush in a directory whose `crush.json` you haven't reviewed.\n\n```json\n{\n  \"$schema\": \"https://charm.land/crush.json\",\n  \"mcp\": {\n    \"filesystem\": {\n      \"type\": \"stdio\",\n      \"command\": \"node\",\n      \"args\": [\"/path/to/mcp-server.js\"],\n      \"timeout\": 120,\n      \"disabled\": false,\n      \"disabled_tools\": [\"some-tool-name\"],\n      \"env\": {\n        \"NODE_ENV\": \"production\"\n      }\n    },\n    \"github\": {\n      \"type\": \"http\",\n      \"url\": \"https://api.githubcopilot.com/mcp/\",\n      \"timeout\": 120,\n      \"disabled\": false,\n      \"disabled_tools\": [\"create_issue\", \"create_pull_request\"],\n      \"headers\": {\n        \"Authorization\": \"Bearer $GH_PAT\"\n      }\n    },\n    \"streaming-service\": {\n      \"type\": \"sse\",\n      \"url\": \"https://example.com/mcp/sse\",\n      \"timeout\": 120,\n      \"disabled\": false,\n      \"headers\": {\n        \"API-Key\": \"$(echo $API_KEY)\"\n      }\n    }\n  }\n}\n```\n\n### Hooks\n\nCrush has preliminary support for hooks. For details, see\n[the hook guide](./docs/hooks/).\n\n### Sharing a workspace across clients\n\nWhen Crush is run against a shared backend (for example two TUIs talking to\nthe same `crush serve`), clients are grouped into **workspaces** keyed by\ntheir resolved `--cwd`. Two clients with the same `--cwd` join the same\nunderlying workspace, so they share the session list, message history,\npermission queue, LSP, and MCP state.\n\nJoining is implicit: pointing a second client at the same working directory\nattaches it to the existing workspace. Each new invocation, however, starts\nin its own fresh session by default. To pick up the conversation another\nclient already has open, use the session manager (the session picker) and\nselect it. Sessions surface two signals there:\n\n- `IsBusy` is set while an agent turn is in flight for that session.\n- `AttachedClients` reports how many clients are currently viewing it.\n\nA non-zero `AttachedClients` (often combined with `IsBusy`) is the cue that a\nsession is \"in progress\" on another client and joining it will mirror that\nview live.\n\nThe first client to create a workspace fixes its process-wide flags. In\nparticular, `--yolo` and `--debug` follow a **first-wins** rule: later\nclients that arrive at the same `--cwd` with different values for those\nflags do not change the running workspace. A debug log line is emitted\nrecording the mismatch, and the workspace keeps the flags it was created\nwith.\n\nA workspace lives as long as at least one client has an SSE event stream\nopen against it. When the last stream disconnects, the workspace is torn\ndown. There is a short grace window right after `POST /v1/workspaces` so a\nclient that has created the workspace but not yet opened its event stream\ndoes not get reaped before it can attach.\n\n### Ignoring Files\n\nCrush respects `.gitignore` files by default, but you can also create a\n`.crushignore` file to specify additional files and directories that Crush\nshould ignore. This is useful for excluding files that you want in version\ncontrol but don't want Crush to consider when providing context.\n\nThe `.crushignore` file uses the same syntax as `.gitignore` and can be placed\nin the root of your project or in subdirectories.\n\n### Allowing Tools\n\nBy default, Crush will ask you for permission before running tool calls. If\nyou'd like, you can allow tools to be executed without prompting you for\npermissions. Use this with care.\n\n```json\n{\n  \"$schema\": \"https://charm.land/crush.json\",\n  \"permissions\": {\n    \"allowed_tools\": [\n      \"view\",\n      \"ls\",\n      \"grep\",\n      \"edit\",\n      \"mcp_context7_get-library-doc\"\n    ]\n  }\n}\n```\n\nYou can also skip all permission prompts entirely by running Crush with the\n`--yolo` flag. Be very, very careful with this feature.\n\n### Disabling Built-In Tools\n\nIf you'd like to prevent Crush from using certain built-in tools entirely, you\ncan disable them via the `options.disabled_tools` list. Disabled tools are\ncompletely hidden from the agent.\n\n```json\n{\n  \"$schema\": \"https://charm.land/crush.json\",\n  \"options\": {\n    \"disabled_tools\": [\"bash\", \"sourcegraph\"]\n  }\n}\n```\n\nTo disable tools from MCP servers, see the [MCP config section](#mcps).\n\n### Disabling Skills\n\nIf you'd like to prevent Crush from using certain skills entirely, you can\ndisable them via the `options.disabled_skills` list. Disabled skills are hidden\nfrom the agent, including builtin skills and skills discovered from disk.\n\n```json\n{\n  \"$schema\": \"https://charm.land/crush.json\",\n  \"options\": {\n    \"disabled_skills\": [\"crush-config\"]\n  }\n}\n```\n\n### Agent Skills\n\nCrush supports the [Agent Skills](https://agentskills.io) open standard for\nextending agent capabilities with reusable skill packages. Skills are folders\ncontaining a `SKILL.md` file with instructions that Crush can discover and\nactivate on demand.\n\nThe global paths we looks for skills are:\n\n* `$CRUSH_SKILLS_DIR`\n* `$XDG_CONFIG_HOME/agents/skills` or `~/.config/agents/skills/`\n* `$XDG_CONFIG_HOME/crush/skills` or `~/.config/crush/skills/`\n* `~/.agents/skills/`\n* `~/.claude/skills/`\n* On Windows, we _also_ look at\n  * `%LOCALAPPDATA%\\agents\\skills\\` or `%USERPROFILE%\\AppData\\Local\\agents\\skills\\`\n  * `%LOCALAPPDATA%\\crush\\skills\\` or `%USERPROFILE%\\AppData\\Local\\crush\\skills\\`\n* Additional paths configured via `options.skills_paths`\n\nOn top of that, we _also_ load skills in your project from the following\nrelative paths:\n\n* `.agents/skills`\n* `.crush/skills`\n* `.claude/skills`\n* `.cursor/skills`\n\n```jsonc\n{\n  \"$schema\": \"https://charm.land/crush.json\",\n  \"options\": {\n    \"skills_paths\": [\n      \"~/.config/crush/skills\", // Windows: \"%LOCALAPPDATA%\\\\crush\\\\skills\",\n      \"./project-skills\",\n    ],\n  },\n}\n```\n\nYou can get started with example skills from [anthropics/skills](https://github.com/anthropics/skills):\n\n```bash\n# Unix\nmkdir -p ~/.config/crush/skills\ncd ~/.config/crush/skills\ngit clone https://github.com/anthropics/skills.git _temp\nmv _temp/skills/* . \u0026\u0026 rm -rf _temp\n```\n\n```powershell\n# Windows (PowerShell)\nmkdir -Force \"$env:LOCALAPPDATA\\crush\\skills\"\ncd \"$env:LOCALAPPDATA\\crush\\skills\"\ngit clone https://github.com/anthropics/skills.git _temp\nmv _temp/skills/* . ; rm -r -force _temp\n```\n\n#### User-Invocable Skills\n\nSkills can be made invocable as commands from the commands palette (Ctrl+P). Add `user-invocable: true` to the skill's YAML frontmatter:\n\n```yaml\n---\nname: my-skill\ndescription: A skill that can be invoked as a command.\nuser-invocable: true\n---\n```\n\nUser-invocable skills appear in the commands palette with a `user:` or `project:` prefix:\n- Skills from global directories show as `user:skill-name`\n- Skills from project directories show as `project:skill-name`\n\nWhen invoked, the skill's instructions are loaded into the conversation context.\n\nTo prevent the model from auto-triggering a skill (while still allowing user invocation), add `disable-model-invocation: true`:\n\n```yaml\n---\nname: my-skill\ndescription: Only invocable by users, not the model.\nuser-invocable: true\ndisable-model-invocation: true\n---\n```\n\nSkills with `disable-model-invocation` won't appear in the model's available skills list but can still be invoked manually by users.\n\n### Desktop notifications\n\nCrush sends desktop notifications when a tool call requires permission and when\nthe agent finishes its turn. They're only sent when the terminal window isn't\nfocused _and_ your terminal supports reporting the focus state.\n\n```jsonc\n{\n  \"$schema\": \"https://charm.land/crush.json\",\n  \"options\": {\n    \"disable_notifications\": false, // default\n  },\n}\n```\n\nTo disable desktop notifications, set `disable_notifications` to `true` in your\nconfiguration. On macOS, notifications currently lack icons due to platform\nlimitations.\n\n### Initialization\n\nWhen you initialize a project, Crush analyzes your codebase and creates\na context file that helps it work more effectively in future sessions.\nBy default, this file is named `AGENTS.md`, but you can customize the\nname and location with the `initialize_as` option:\n\n```json\n{\n  \"$schema\": \"https://charm.land/crush.json\",\n  \"options\": {\n    \"initialize_as\": \"AGENTS.md\"\n  }\n}\n```\n\nThis is useful if you prefer a different naming convention or want to\nplace the file in a specific directory (e.g., `CRUSH.md` or\n`docs/LLMs.md`). Crush will fill the file with project-specific context\nlike build commands, code patterns, and conventions it discovered during\ninitialization.\n\n### Attribution Settings\n\nBy default, Crush adds attribution information to Git commits and pull requests\nit creates. You can customize this behavior with the `attribution` option:\n\n```json\n{\n  \"$schema\": \"https://charm.land/crush.json\",\n  \"options\": {\n    \"attribution\": {\n      \"trailer_style\": \"co-authored-by\",\n      \"generated_with\": true\n    }\n  }\n}\n```\n\n- `trailer_style`: Controls the attribution trailer added to commit messages\n  (default: `assisted-by`)\n  - `assisted-by`: Adds `Assisted-by: Crush:[ModelID]` as specified in [the convention](https://docs.kernel.org/process/coding-assistants.html#attribution)\n  - `co-authored-by`: Adds `Co-Authored-By: Crush \u003ccrush@charm.land\u003e`\n  - `none`: No attribution trailer\n- `generated_with`: When true (default), adds `💘 Generated with Crush` line to\n  commit messages and PR descriptions\n\n### Custom Providers\n\nCrush supports custom provider configurations for both OpenAI-compatible and\nAnthropic-compatible APIs.\n\n\u003e [!NOTE]\n\u003e Note that we support two \"types\" for OpenAI. Make sure to choose the right one\n\u003e to ensure the best experience!\n\u003e\n\u003e - `openai` should be used when proxying or routing requests through OpenAI.\n\u003e - `openai-compat` should be used when using non-OpenAI providers that have OpenAI-compatible APIs.\n\n#### OpenAI-Compatible APIs\n\nHere’s an example configuration for Deepseek, which uses an OpenAI-compatible\nAPI. Don't forget to set `DEEPSEEK_API_KEY` in your environment.\n\n```json\n{\n  \"$schema\": \"https://charm.land/crush.json\",\n  \"providers\": {\n    \"deepseek\": {\n      \"type\": \"openai-compat\",\n      \"base_url\": \"https://api.deepseek.com/v1\",\n      \"api_key\": \"$DEEPSEEK_API_KEY\",\n      \"models\": [\n        {\n          \"id\": \"deepseek-chat\",\n          \"name\": \"Deepseek V3\",\n          \"cost_per_1m_in\": 0.27,\n          \"cost_per_1m_out\": 1.1,\n          \"cost_per_1m_in_cached\": 0.07,\n          \"cost_per_1m_out_cached\": 1.1,\n          \"context_window\": 64000,\n          \"default_max_tokens\": 5000\n        }\n      ]\n    }\n  }\n}\n```\n\n#### Anthropic-Compatible APIs\n\nCustom Anthropic-compatible providers follow this format:\n\n```json\n{\n  \"$schema\": \"https://charm.land/crush.json\",\n  \"providers\": {\n    \"custom-anthropic\": {\n      \"type\": \"anthropic\",\n      \"base_url\": \"https://api.anthropic.com/v1\",\n      \"api_key\": \"$ANTHROPIC_API_KEY\",\n      \"extra_headers\": {\n        \"anthropic-version\": \"2023-06-01\"\n      },\n      \"models\": [\n        {\n          \"id\": \"claude-sonnet-4-20250514\",\n          \"name\": \"Claude Sonnet 4\",\n          \"cost_per_1m_in\": 3,\n          \"cost_per_1m_out\": 15,\n          \"cost_per_1m_in_cached\": 3.75,\n          \"cost_per_1m_out_cached\": 0.3,\n          \"context_window\": 200000,\n          \"default_max_tokens\": 50000,\n          \"can_reason\": true,\n          \"supports_attachments\": true\n        }\n      ]\n    }\n  }\n}\n```\n\n### Amazon Bedrock\n\nCrush currently supports running Anthropic models through Bedrock, with caching disabled.\n\n- A Bedrock provider will appear once you have AWS configured, i.e. `aws configure`\n- Crush also expects the `AWS_REGION` or `AWS_DEFAULT_REGION` to be set\n- To use a specific AWS profile set `AWS_PROFILE` in your environment, i.e. `AWS_PROFILE=myprofile crush`\n- Alternatively to `aws configure`, you can also just set `AWS_BEARER_TOKEN_BEDROCK`\n\n### Vertex AI Platform\n\nVertex AI will appear in the list of available providers when `VERTEXAI_PROJECT` and `VERTEXAI_LOCATION` are set. You will also need to be authenticated:\n\n```bash\ngcloud auth application-default login\n```\n\nTo add specific models to the configuration, configure as such:\n\n```json\n{\n  \"$schema\": \"https://charm.land/crush.json\",\n  \"providers\": {\n    \"vertexai\": {\n      \"models\": [\n        {\n          \"id\": \"claude-sonnet-4@20250514\",\n          \"name\": \"VertexAI Sonnet 4\",\n          \"cost_per_1m_in\": 3,\n          \"cost_per_1m_out\": 15,\n          \"cost_per_1m_in_cached\": 3.75,\n          \"cost_per_1m_out_cached\": 0.3,\n          \"context_window\": 200000,\n          \"default_max_tokens\": 50000,\n          \"can_reason\": true,\n          \"supports_attachments\": true\n        }\n      ]\n    }\n  }\n}\n```\n\n### Local Models\n\nLocal models can also be configured via OpenAI-compatible API. Here are two common examples:\n\n#### Ollama\n\n```json\n{\n  \"providers\": {\n    \"ollama\": {\n      \"name\": \"Ollama\",\n      \"base_url\": \"http://localhost:11434/v1/\",\n      \"type\": \"openai-compat\",\n      \"models\": [\n        {\n          \"name\": \"Qwen 3 30B\",\n          \"id\": \"qwen3:30b\",\n          \"context_window\": 256000,\n          \"default_max_tokens\": 20000\n        }\n      ]\n    }\n  }\n}\n```\n\n#### LM Studio\n\n```json\n{\n  \"providers\": {\n    \"lmstudio\": {\n      \"name\": \"LM Studio\",\n      \"base_url\": \"http://localhost:1234/v1/\",\n      \"type\": \"openai-compat\",\n      \"models\": [\n        {\n          \"name\": \"Qwen 3 30B\",\n          \"id\": \"qwen/qwen3-30b-a3b-2507\",\n          \"context_window\": 256000,\n          \"default_max_tokens\": 20000\n        }\n      ]\n    }\n  }\n}\n```\n\n## Logging\n\nSometimes you need to look at logs. Luckily, Crush logs all sorts of\nstuff. Logs are stored in `./.crush/logs/crush.log` relative to the project.\n\nThe CLI also contains some helper commands to make perusing recent logs easier:\n\n```bash\n# Print the last 1000 lines\ncrush logs\n\n# Print the last 500 lines\ncrush logs --tail 500\n\n# Follow logs in real time\ncrush logs --follow\n```\n\nWant more logging? Run `crush` with the `--debug` flag, or enable it in the\nconfig:\n\n```json\n{\n  \"$schema\": \"https://charm.land/crush.json\",\n  \"options\": {\n    \"debug\": true,\n    \"debug_lsp\": true\n  }\n}\n```\n\n## Provider Auto-Updates\n\nBy default, Crush automatically checks for the latest and greatest list of\nproviders and models from [Catwalk](https://github.com/charmbracelet/catwalk),\nthe open source Crush provider database. This means that when new providers and\nmodels are available, or when model metadata changes, Crush automatically\nupdates your local configuration.\n\n### Disabling automatic provider updates\n\nFor those with restricted internet access, or those who prefer to work in\nair-gapped environments, this might not be want you want, and this feature can\nbe disabled.\n\nTo disable automatic provider updates, set `disable_provider_auto_update` into\nyour `crush.json` config:\n\n```json\n{\n  \"$schema\": \"https://charm.land/crush.json\",\n  \"options\": {\n    \"disable_provider_auto_update\": true\n  }\n}\n```\n\nOr set the `CRUSH_DISABLE_PROVIDER_AUTO_UPDATE` environment variable:\n\n```bash\nexport CRUSH_DISABLE_PROVIDER_AUTO_UPDATE=1\n```\n\n### Manually updating providers\n\nManually updating providers is possible with the `crush update-providers`\ncommand:\n\n```bash\n# Update providers remotely from Catwalk.\ncrush update-providers\n\n# Update providers from a custom Catwalk base URL.\ncrush update-providers https://example.com/\n\n# Update providers from a local file.\ncrush update-providers /path/to/local-providers.json\n\n# Reset providers to the embedded version, embedded at crush at build time.\ncrush update-providers embedded\n\n# For more info:\ncrush update-providers --help\n```\n\n## Metrics\n\nCrush records pseudonymous usage metrics (tied to a device-specific hash),\nwhich maintainers rely on to inform development and support priorities. The\nmetrics include solely usage metadata; prompts and responses are NEVER\ncollected.\n\nDetails on exactly what’s collected are in the source code ([here](https://github.com/charmbracelet/crush/tree/main/internal/event)\nand [here](https://github.com/charmbracelet/crush/blob/main/internal/llm/agent/event.go)).\n\nYou can opt out of metrics collection at any time by setting the environment\nvariable by setting the following in your environment:\n\n```bash\nexport CRUSH_DISABLE_METRICS=1\n```\n\nOr by setting the following in your config:\n\n```json\n{\n  \"options\": {\n    \"disable_metrics\": true\n  }\n}\n```\n\nCrush also respects the [`DO_NOT_TRACK`](https://donottrack.sh/) convention\nwhich can be enabled via `export DO_NOT_TRACK=1`.\n\n## Q\u0026A\n\n### Why is clipboard copy and paste not working?\n\nInstalling an extra tool might be needed on Unix-like environments.\n\n| Environment         | Tool                     |\n| ------------------- | ------------------------ |\n| Windows             | Native support           |\n| macOS               | Native support           |\n| Linux/BSD + Wayland | `wl-copy` and `wl-paste` |\n| Linux/BSD + X11     | `xclip` or `xsel`        |\n\n## Contributing\n\nSee the [contributing guide](https://github.com/charmbracelet/crush?tab=contributing-ov-file#contributing).\n\n## Whatcha think?\n\nWe’d love to hear your thoughts on this project. Need help? We gotchu. You can find us on:\n\n- [Twitter](https://twitter.com/charmcli)\n- [Slack][slack]\n- [Discord][discord]\n- [The Fediverse](https://mastodon.social/@charmcli)\n- [Bluesky](https://bsky.app/profile/charm.land)\n\n[slack]: https://charm.land/slack\n[discord]: https://charm.land/discord\n\n## License\n\n[FSL-1.1-MIT](https://github.com/charmbracelet/crush/raw/main/LICENSE.md)\n\n---\n\nPart of [Charm](https://charm.land).\n\n\u003ca href=\"https://charm.land/\"\u003e\u003cimg alt=\"The Charm logo\" width=\"400\" src=\"https://stuff.charm.sh/charm-banner-softy.jpg\" /\u003e\u003c/a\u003e\n\n\u003c!--prettier-ignore--\u003e\nCharm热爱开源 • Charm loves open source\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcharmbracelet%2Fcrush","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcharmbracelet%2Fcrush","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcharmbracelet%2Fcrush/lists"}