# openinterpreter/openinterpreter

A coding agent for open models like Kimi K3

Repository: https://github.com/openinterpreter/openinterpreter
Canonical: https://ross.abutalabs.com/products/openinterpreter
Homepage: http://openinterpreter.com/
Language: Rust
License: Apache-2.0
License Family: permissive
Topics: coding-agent, deepseek, kimi, qwen, rust, acp
Last push: 2026-08-20T03:35:38+00:00

## Health v2 (maintenance only)
Score: 95/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 98, longevity 81
- inputs: {"age_days": 1146, "days_push": 13, "days_rel": 13, "gap_med": 0.0, "n_releases_24m": 17}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 68163, forks 5866 (observed 2026-08-28T04:12:20.864877+00:00)

## What it is
Open Interpreter is a Rust-based terminal coding agent optimized for low-cost open models like Kimi K3, DeepSeek, and Qwen. It emulates provider-recommended agent harnesses (Claude Code, Kimi Code, Codex, etc.) and is compatible with ACP editors and the OpenAI Codex SDK.

## Use cases
- run a coding agent with open models like Kimi K3 or DeepSeek
- get Codex-like terminal coding assistant for cheap models
- switch agent harnesses to maximize model performance
- use a coding agent inside ACP-compatible editors
- replace Codex CLI with an open-source binary override

## When to choose
- you want a terminal coding agent tuned for low-cost open-weight models
- you need harness emulation for Claude Code, Kimi Code, or Qwen Code
- you want ACP or Codex SDK compatibility with a self-hosted agent

## When to avoid
- you need a GUI-based coding assistant
- you rely exclusively on closed frontier models with proprietary harness features

## Facets
- artifact type: cli-tool
- maturity: active
- function: agent-framework, llm-inference, cli, developer-tools
- domain: large-language-models, developer-tools
- platform: cli, windows, rust
- tags: coding-agent, harness-emulation, open-models, acp, codex-compatible, terminal-agent, ai-agents, command-line, macos, linux

## Member repositories
- openinterpreter/openinterpreter (main) score 95

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:20.864877+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:16:23.912770+00:00, confidence not recorded.
  - readme: https://github.com/openinterpreter/openinterpreter (fetched 2026-08-28T04:12:20.864877+00:00, sha 137de6b6ac1d)
  - homepage: http://openinterpreter.com/ (fetched 2026-08-28T17:52:00.173994+00:00, sha b4f8d1a37a02)
- Data as of 2026-08-30T08:39:29.467469+00:00.