Crow CLI
Crow CLI is an Agent Client Protocol (ACP) native coding agent that operates in the terminal or within ACP-compatible editors. It leverages a multi-modal ReAct loop to perform file operations, shell commands, and web searches, while maintaining persistent semantic memory across sessions via LanceDB.
Recent versions introduced vision tools for image analysis, improved memory integration using LanceDB, and experimental support for a desktop client fork.
As of
- Native ACP implementation with client capability detection
- Persistent memory service using LanceDB with ColBERT and ColPali embeddings
- Built-in MCP toolserver supporting terminal access, file manipulation, and web interaction
- Task-based cancellation and conversation compaction for long-running workflows
- Support for multi-modal inputs including vision for whiteboard and image analysis
Developers who want an ACP-native, self-hosted coding assistant that provides cross-session semantic memory and works seamlessly within modern editors like Zed.
Users who prefer a zero-configuration, fully managed SaaS agent or those who do not wish to manage local infrastructure like Docker containers.
The tool is open-source under the MIT license and is free to use, though users must provide their own LLM API keys and maintain local services like Docker for memory and search.
Crow CLI is a highly extensible, powerful tool for developers seeking a transparent, local-first agent framework that prioritizes session persistence and standard-compliant agent communication.
Is Crow CLI free?
Yes - Crow CLI is Open Source. The tool is open-source under the MIT license and is free to use, though users must provide their own LLM API keys and maintain local services like Docker for memory and search.
What is Crow CLI best for?
Developers who want an ACP-native, self-hosted coding assistant that provides cross-session semantic memory and works seamlessly within modern editors like Zed.
Who makes Crow CLI?
Crow CLI is developed by Crow. It is listed in the Terminal & CLI Agents category on ai.dosa.dev.
Sign in with GitHub or Google to Zap tools, vote, and get a README badge showing your stack.
Content on this page is AI-generated. Please verify details with the vendor's website for accuracy.