Open sourcePython · ≈69k stars · Apache-2.0
Open Interpreter
A natural language interface for computers.
Open Interpreter lets language models run code on your computer — a code-execution harness where the model writes code and the harness executes it with confirmation gates. Oriented to open models (DeepSeek, Kimi, Qwen), it made 'the agent is the loop' tangible early.
Pros & cons
Each point cites its sources and says what kind of evidence backs it. A second reviewer tried to refute every claim before it was kept.
Pros
- DocsNow a Rust coding agent forked from OpenAI's Codex and aimed at low-cost open models. `/harness` switches between emulated harnesses, including a reimplementation of Kimi Code.[1]
- DocsBuilt to be portable: it supports AGENTS.md, shared .agents/skills, MCP, ACP and the Codex exec protocol, so the Codex SDK can drive it with a one-line override.[1]
- MetadataApache-2.0 (the Python era was AGPL-3.0), with frequent releases and only 17 open issues.[1][2]
- User reportsOne user still keeps the Python 'Classic' version as a Swiss-army terminal helper for one-off tasks.[1]
Cons
- Independent testThe rewrite replaced the original general 'run code on your computer' tool; that Python version lives on mainly in a community fork.[1]
- Independent testAn independent review found no published benchmarks backing the harness-emulation performance claims.[1]
- MetadataThe Rust line is young: tags started in mid-2026 and releases are still 0.0.x (rust-v0.0.56).[1]
- DocsThe recommended install pipes a remote script into your shell (`curl ... | sh`, or `irm | iex` on Windows).[1]
- Best for
- Developers who run cheap open-weight models (Kimi, GLM, DeepSeek, Qwen) and want a Codex-compatible harness tuned for them.
- Watch out for
- This is a different product from the 2023 Open Interpreter; old tutorials and integrations no longer apply.
Assessed Oct 29, 2026 · adversarially reviewedSuggest a correction
People
Founder
Creator of Open Interpreter
Harness engineering
Activity
- Last push
- · yesterday
- Latest release
- rust-v0.0.61
· 10d ago - Last 90 days
- 13 releases
rust-v0.0.61Open Interpreter 0.0.61
· 10d agoOpen Interpreter 0.0.61 Models No model-provider catalog or request-admission behavior changes are included in this release. Release Attest Linux Open Interpreter archives and their checksum manifest in the original tagged build. Verify that original build provenance before…
rust-v0.0.60Open Interpreter 0.0.60
· 12d agoOpen Interpreter 0.0.60 Models No model-provider catalog or request-admission behavior changes are included in this release. App server Add one canonical file-backed managed Goal creation contract for an explicit authenticated absent/noGoal state and an exact completed…
rust-v0.0.59Open Interpreter 0.0.59
· 2w agoOpen Interpreter 0.0.59 Models No model-provider catalog or request-admission behavior changes are included in this release. App server Add owner-bound, read-only background-terminal status with bounded terminal metrics and fail-closed thread ownership.
rust-v0.0.58Open Interpreter 0.0.58
· 2w agoOpen Interpreter 0.0.58 Models Validate the maintained Codex 0.159.0 compatibility profile for Open Interpreter model discovery and request admission. Feedback Preserve legacy feedback delivery alongside optional signed attachment uploads, with protocol and streaming-guide…
rust-v0.0.57Open Interpreter 0.0.57
· 3w agoOpen Interpreter 0.0.57 Models Validate the maintained Codex 0.159.0 compatibility profile for Open Interpreter model discovery and request admission.
Checked against GitHub on Nov 21, 2026. Release notes are shortened to plain text.
Neighbours on the workbench
TypeScript · ≈395k stars · MIT
openclaw/openclaw
The viral open-source personal AI assistant that really does things.
Maintained by OpenClaw Foundation
v2026.11.6releasedShell · ≈329k stars · MIT
mattpocock/skills
Small, composable agent skills for real engineering work.
Maintained by Matt Pocock (AI Hero)
MDX · ≈323k stars · MIT
obra/superpowers
An agentic skills framework and software methodology that works.
Maintained by Jesse Vincent (obra)
Connections
Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.
Maintained by · 1
- Open InterpreterOrganisation
