Claude Engineer

Claude Engineer is an open-source terminal and lightweight web-based coding assistant created by Pietro Schirano (Doriandarko). Built in Python, it serves as an autonomous coding agent harness designed to interface directly with Anthropic's Claude models over the Anthropic API. In day-to-day use, developers interact with Claude Engineer through an interactive CLI shell (such as `ce3.py`) or a local Flask-based web interface (`app.py`). The harness equips Claude with custom tool definitions that inspect directories, read source files, execute terminal commands, run code snippets, and apply diff-based patches to project files. Claude Engineer distinguishes itself by its transparent and hackable architecture. Rather than running as an opaque binary or commercial SaaS wrapper, its prompt structures, tool bindings, and execution loops reside directly in editable Python modules (`tools/` and `prompts/`), making it both a practical daily coding agent and a reference harness for developers building custom LLM agent workflows. The project is open source and hosted on GitHub. It operates on a Bring-Your-Own-Key (BYOK) model, requiring only an active Anthropic API key with no recurring subscription fees.

Tags: ai agent, cli, code assistant, coding agent, OpenSource

Visit Claude Engineer

Key features

  • Anthropic Claude Integration — Interacts directly with Claude 3 and Claude 3.5 models via the Anthropic API using your own API key. - Diff-Based File Editing — Inspects, modifies, and patches local project files using structured diff editing routines. - Local Tool Execution — Provides the agent with local filesystem inspection, file creation, code execution, and shell access. - Dual Interface Modes — Can be run as an interactive terminal CLI or via a local Flask web UI. - Modular Prompt & Tool System — Exposes all system prompts, tool declarations, and agent behaviors in standard Python and text templates for easy extension.

Use cases

Use Case: Local Codebase Refactoring Developers prompt the CLI agent to inspect multi-file directory structures, locate specific function implementations, and apply targeted diff updates across several files simultaneously.

Use Case: Interactive Prototyping and Debugging Engineers scaffold new features by having the agent generate code, run it locally via execution tools, inspect console errors, and iteratively fix syntax or logic issues.

Use Case: Custom Agent Experimentation AI engineers use the repository as a modular baseline to benchmark Claude tool-calling schemas, modify system prompts, and plug in custom execution environments.

Who it is for

Claude Engineer is intended for Python developers, hackers, and software engineers who want a customizable, scriptable terminal assistant powered directly by Anthropic API keys. It is less suited for non-technical users or enterprise teams seeking managed IDE plugins with centralized enterprise access controls.

Install guide

Installation Clone the repository and install the required Python dependencies: bash git clone https://github.com/Doriandarko/claude-engineer.git cd claude-engineer pip install -r requirements.txt (Note: Alternatively, install dependencies using poetry or pyproject.toml if using a virtual environment manager.)

First Run Configure your environment variables by creating a .env file from the provided example: bash cp .env.example .env Add your Anthropic API key to .env: env ANTHROPIC_API_KEY=your_anthropic_api_key_here Launch the terminal agent: bash python ce3.py Or launch the web interface: bash python app.py

Example Session Inside the interactive CLI prompt, instruct the agent to inspect and edit your project: text Claude-Engineer> Scan the current directory, summarize the module structure, and create a test suite for app.py under tests/test_app.py.

Part of CLI Coding Agents

Categories: AI Coding Agents, Code Assistants, Developer Tools

Related CLI agents

  • Plandex — Plandex is an open-source terminal-based AI coding agent designed to handle complex, multi-file engineering tasks in large codebases. Created by…
  • OpenCode — OpenCode is an open-source AI coding agent developed by Anomaly that operates across terminal environments, desktop applications, and IDE extensions.…
  • OpenHands — OpenHands (formerly OpenDevin) is an open-source autonomous AI software development agent and orchestration platform. It provides an extensible runtime environment…
  • Subtask — Subtask is an open-source CLI agent harness and orchestration tool developed by zippoxer in Go. It is built to coordinate…
  • EchoCoding — EchoCoding is an open-source agent harness and audio-augmented developer tooling layer created by launsion-boop. Designed to run alongside AI coding…
  • pi-reflect — pi-reflect is an open-source agent harness and self-improvement extension for pi coding agents, developed by jo-inc. It inspects agent session…
  • AI Tools
  • Categories
  • Industries
  • CLI Coding Agents
  • MCP Servers
  • MCP Categories