Open Interpreter

Open Interpreter is an open-source coding agent for the terminal, focused on getting the best results from low-cost and open models. It is a fork of OpenAI's Codex CLI, written in Rust, and installs with a single command on macOS, Linux and Windows.

Open Interpreter can emulate the agent harness each model was tuned for, such as Claude Code, Kimi Code or Qwen Code, and you switch harnesses and models from inside the session. It runs commands in a native sandbox, works with any OpenAI-compatible provider, and speaks the Codex exec protocol and ACP, so it fits editors and tools built for those. It uses shared standards like AGENTS.md, MCP and .agents/skills, and ships a QA skill for testing web and native apps.

Open Interpreter makes cheaper and open models practical for real coding work by matching the setup each model expects. It keeps your configuration in shared, readable formats, so moving to or from another agent is easy.

Stars

0

Forks

0

Commits

0

Repository

openinterpreter/openinterpreter

• Claude CodeAnthropic's coding agent for the terminal, sold with a Claude subscription.
• CursorAI code editor built on VS Code, sold as a subscription.
• Codex CLINo. 218OpenAI's open-source terminal coding agent, which Open Interpreter is forked from.
• OpenCodeNo. 078Open-source AI coding agent for the terminal that works with many model providers.

See every open-source alternative to Claude Code in the collection.