---
title: "Integrations"
description: "Use Caro from Claude Code, Codex, Cursor, Continue, Aider, Tabby, opencode, crush, and more. Caro speaks Claude Code skills, MCP, and the OpenAI Chat Completions API."
url: "https://caro.sh/integrations"
markdown_url: "https://caro.sh/integrations.md"
lang: "en"
type: "website"
image: "https://caro.sh/og/integrations.png"
---

For Agents & IDEs

# Use Caro from your agent

Caro is a safety-validated shell-command generator that other coder agents and agentic IDEs can call as a tool. Pick the integration surface that matches your stack — copy-paste configs below.

## Integration surfaces

### Claude Code skill

Bundled at `.claude/skills/caro-shell/SKILL.md`. Auto-discovered by Claude Code.

### MCP server

`caro mcp serve` — exposes shell-command tools over the Model Context Protocol. Coming soon.

### OpenAI-compat HTTP

`caro serve --openai` — OpenAI Chat Completions endpoint. Unlocks Codex, Cursor, Continue, Aider, Tabby in one shot. Coming soon.

## Caro-as-a-tool — outward integrations

### Working today

- Claude Code (skill) ✅ Working Claude Code skill validated 2026-04-26

  Bundled skill at \`.claude/skills/caro-shell/SKILL.md\`. Triggers when the user asks for shell-command synthesis; shells out to the published \`caro\` binary with \`--dry-run\` and presents the safety-validated suggestion for approval.

  ```
  # Install the caro CLI first
  cargo install caro

  # Then point Claude Code at the skill bundled in this repo:
  #   .claude/skills/caro-shell/SKILL.md
  # Claude Code auto-discovers skills from .claude/skills/ in any project.
  ```

  <https://www.anthropic.com/claude-code>

### In progress

- Claude Code (MCP server) 🚧 In progress MCP server

  Planned \`caro mcp serve\` subcommand exposing \`generate\_command\`, \`validate\_command\`, \`explain\_safety\`, \`show\_decision\_tree\` over the Model Context Protocol. Spec drafted in \`.github/first-time-issues/06-mcp-claude-code-integration.md\`.

  Tracking: see GitHub issues labeled \`integration\` + \`mcp\`

- OpenAI-compat HTTP shim 🚧 In progress OpenAI-compat HTTP

  Planned \`caro serve --openai\` mode. Exposes an OpenAI Chat Completions endpoint backed by caro's safety-validated generation. Single integration unlocks Codex, Cursor, Continue, Aider, Tabby, and most long-tail tools that already speak OpenAI's schema.

  Tracking: see GitHub issues labeled \`integration\` + \`openai-compat\`

- crush 🚧 In progress MCP server

  Charm.sh terminal coding agent. Codex MCP server config pattern in flight.

  Tracking: PR #789 (Crush MCP config)

- Gemini CLI 🚧 In progress Native backend

  Google's agentic CLI. Caro-side Gemini backend in flight.

  Tracking: PR #782 (Gemini integration workflows)

### Planned

- OpenAI Codex ⏳ Planned OpenAI-compat HTTP

  Will work via the OpenAI-compat shim once that ships — point Codex at \`http\://localhost:PORT/v1\` instead of \`api.openai.com\`.

  <https://openai.com/codex>

- Cursor ⏳ Planned OpenAI-compat HTTP

  Cursor accepts a custom OpenAI base URL in settings. Once the OpenAI-compat shim ships, set base URL to caro and enjoy validated shell-command tool calls.

  [https://cursor.com](https://cursor.com/)

- Continue.dev ⏳ Planned OpenAI-compat HTTP

  Continue (VS Code / JetBrains) supports OpenAI-compatible providers via \`config.json\`. OpenAI-compat shim covers it.

  [https://continue.dev](https://continue.dev/)

- Aider ⏳ Planned OpenAI-compat HTTP

  Aider speaks OpenAI; OpenAI-compat shim covers it.

  [https://aider.chat](https://aider.chat/)

- Tabby (self-hosted) ⏳ Planned OpenAI-compat HTTP

  Self-hosted coding assistant. Point its model endpoint at the caro shim.

  [https://tabby.tabbyml.com](https://tabby.tabbyml.com/)

- opencode ⏳ Planned MCP server

  Charm.sh terminal coding agent. Will integrate via MCP server or OpenAI shim.

  [https://opencode.ai](https://opencode.ai/)

- droid ⏳ Planned MCP server

  Mobile-first agent. Plan: MCP server or OpenAI shim.

- Sourcegraph Amp ⏳ Planned MCP server

  Enterprise coding agent. MCP-based integration once \`caro mcp serve\` ships.

  <https://sourcegraph.com/amp>

- Letta (MemGPT) ⏳ Planned MCP server

  Persistent-memory agent runtime. Tool registration via MCP.

  [https://letta.com](https://letta.com/)

- Qwen Code ⏳ Planned OpenAI-compat HTTP

  Qwen-based coding agent; OpenAI-compat shim or native backend.

- Jules (Google) ⏳ Planned Native backend

  Google's async coding agent. Coordinate with the Gemini backend work.

## Backends Caro can drive

Caro itself is a multi-backend client. Use any of these for inference; safety validation runs the same regardless of backend.

- MLX (embedded, Apple Silicon) ✅ Working

  On-device inference via MLX + llama.cpp. Default on macOS arm64. No network. Ships in the default \`cargo install caro\` build.

  ```
  caro --backend embedded "kill the process on port 3000"
  ```

- Candle CPU (embedded) ✅ Working

  Cross-platform CPU inference via Candle. Slower but works everywhere. Ships in the default \`cargo install caro\` build.

- Anthropic Claude API 🚧 In progress

  Backend implementation exists at \`src/backends/remote/claude.rs\` (\`ClaudeBackend\`, \`BackendType::Claude\`), but the CLI does not yet route \`--backend claude\` to it — the published binary returns \`Unknown backend 'claude'\`. Wiring is the missing piece.

- OpenRouter (incl. \`auto\`) ⏳ Planned

  Single backend → 100+ models including OpenRouter's \`auto\` routing. Planned: clones the vLLM backend shape.

- Claude Code session token ⏳ Planned

  Reuse the user's active Claude Code authentication (subscription or API). Default to Haiku for cheap fast inference.

Want caro to integrate with a tool not listed? [File an integration request ](https://github.com/wildcard/caro/issues/new?labels=integration,nightly-discovery)— the caro-integrator agent reviews these every night.