Open Interpreter
Open Interpreter is a terminal coding agent built to get the best results out of low-cost and open models. The project has been rebuilt as a Rust fork of OpenAI's Codex, and its distinctive feature is harness emulation: it can mimic the agent loop of tools such as Claude Code, Kimi Code, Qwen Code or SWE-agent, so each model runs inside the harness it performs best in.
It suits developers who want a capable coding agent without being locked into one premium model, for example teams running Kimi, GLM, Qwen or DeepSeek models, or anyone who switches providers often. It runs commands inside native sandboxes on macOS, Linux and Windows, can be used from ACP-compatible editors, acts as a drop-in replacement for the Codex SDK, and reads shared AGENTS.md files and .agents/skills directories so your setup stays portable. A built-in QA skill can drive web apps in a real browser or test native apps.
Getting started: install with `curl -fsSL https://www.openinterpreter.com/install | sh` on macOS and Linux, or the PowerShell script on Windows, then type `i` or `interpreter` to start a session. Use `/model` to choose a provider and `/harness` to switch harnesses.
Features
Why choose it
Trade-offs
Maintenance check
- Last commit
- 2026-11-10
- Commits, last 90 days
- 100+
- Releases, last 90 days
- 15
- Latest release
- rust-v0.0.60 (2026-11-09)
- Open issues
- 40
- Recent issues with at least one comment
- 6/17
Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.
Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.
Most discussed open issues
- #1908 DeepSeek Chat Completions profile fails after Allow Always/tool approval5 comments · 2026-09-14
- #1928 Does not work with Gemini due to hard-coded 'store' key4 comments · 2026-09-29
- #1962 Provider catalog generator ignores explicit API base URL overrides2 comments · 2026-11-01
- #1956 feat(security): Sub-35us AST Invariant Gate to prevent catastrophic shell calls & secret leaks2 comments · 2026-10-29
- #1949 Chat-wire providers show the OpenAI "high-risk cyber activity" warning whenever the routed model differs2 comments · 2026-10-20
Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.
Who it fits
- You want a fast Rust-based terminal coding agent (Apache-2.0) that squeezes better results out of low-cost and open-weights models via harness emulation.
- You want native OS sandboxing (Seatbelt on macOS, Landlock+bubblewrap on Linux, AppContainer on Windows) and support for AGENTS.md, skills, and MCP.
- You are looking for the old Python `pip install open-interpreter` library from 2023–2024; the project has been completely rewritten as a Rust fork of Codex.
- You just want a free-tier official Gemini agent without configuring endpoints and harnesses; Gemini CLI is simpler.
How it differs
Open Interpreter is provider-agnostic and emulates harnesses like Claude Code and SWE-agent for open and low-cost models; Gemini CLI is Google's official agent tied to Gemini models with built-in Google Search grounding.
Compatibility
Quick start
Use cases
Alternatives
Comments
No comments yet. Be the first!