Crab Code

Crab Code is an open-source terminal-based AI coding assistant and multi-agent coordination engine written in Rust by developer lingcoder. Built as a modular workspace across multiple dedicated crates, the project provides terminal-native interfaces for executing code modifications, running sandboxed processes, and delegating complex development tasks to autonomous agents.

Tags: ai agent, cli, coding agent, developer tools, OpenSource

Visit Crab Code

Key features

  • Modular Rust Architecture — Structured across distinct crates separating core agent loops, authentication, filesystem interaction, and terminal interfaces. - Multi-Agent Coordination (Crab-Team) — Actor-based engine facilitating agent rosters, mailboxes, and work queues for collaborative sub-agent task execution. - WASM Plugin Runtime — Sandboxed plugin execution powered by Wasmtime for extensible tool capabilities. - Model & API Integrations — Multi-provider backend supporting direct API endpoints, Bedrock, Vertex AI, and custom proxies. - MCP Protocol Support — Model Context Protocol integration over standard transports and WebSockets for external context and tool access. - PTY & Process Sandboxing — Integrated pseudo-terminal process execution with sandbox controls for safe command execution. - Interactive TUI & CLI Modes — Configurable interface modes ranging from lightweight command-line invocations to a full terminal user interface.

Use cases

Use Case: Sandboxed Task Automation Developers running code modifications or executing terminal workflows can let Crab Code interact with local files and run shell commands in a sandboxed PTY environment, verifying test suites and build outputs before final review.

Use Case: Multi-Agent Parallel Problem Solving Using the crab-team actor infrastructure, users can orchestrate multi-agent workflows where a coordinator agent delegates distinct subtasks—such as documentation, testing, and implementation—to dedicated worker agents communicating through internal queues.

Use Case: Extensible Tooling via MCP and WASM Teams with custom infrastructure can expose internal services to Crab Code using standard Model Context Protocol servers or sandboxed WebAssembly plugins executed directly in the runtime.

Who it is for

Crab Code is aimed at Rust developers, terminal power users, and engineers looking for a fast, memory-safe CLI coding agent with deep multi-agent coordination and modular crate architecture. It is less suitable for users seeking out-of-the-box IDE graphical extensions or plug-and-play non-terminal interfaces.

Install guide

Installation Crab Code is built with standard Rust tooling. Clone the repository and compile using Cargo: bash git clone https://github.com/lingcoder/crab-code.git cd crab-code cargo build --release To install the binary directly onto your system PATH: bash cargo install --path crates/cli

First Run Set your desired LLM API credentials in your environment before launching: bash export ANTHROPIC_API_KEY="your-api-key" # or set custom endpoints / proxies as configured in your settings Run the executable to launch the interactive terminal interface: bash crab-code

Example Session Instruct Crab Code to analyze your current directory and run a build inspection: bash crab-code "Inspect the workspace crates, verify compile status with cargo check, and suggest fixes for any warnings."

Part of CLI Coding Agents

Categories: AI Coding Agents, Code Assistants, Developer Tools

Related CLI agents

  • OpenCode — OpenCode is an open-source AI coding agent developed by Anomaly that operates across terminal environments, desktop applications, and IDE extensions.…
  • goose — goose is an open-source, general-purpose AI agent built in Rust, hosted under the vendor-neutral Agentic AI Foundation (AAIF) at the…
  • SWE-agent — SWE-agent is an open-source autonomous software engineering agent harness built and maintained by researchers from Princeton University and Stanford University.…
  • OpenHands — OpenHands (formerly OpenDevin) is an open-source autonomous AI software development agent and orchestration platform. It provides an extensible runtime environment…
  • Plandex — Plandex is an open-source terminal-based AI coding agent designed to handle complex, multi-file engineering tasks in large codebases. Created by…
  • Weaver — Weaver is an open-source agent harness and orchestration framework maintained by sean35mm on GitHub. Built on top of the Bun…
  • AI Tools
  • Categories
  • Industries
  • CLI Coding Agents
  • MCP Servers
  • MCP Categories