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