# OpenCodeInterpreter/OpenCodeInterpreter

OpenCodeInterpreter is a suite of open-source code generation systems aimed at bridging the gap between large language models and sophisticated proprietary systems like the GPT-4 Code Interpreter. It significantly enhances code generation capabilities by integrating execution and iterative refinement functionalities.

Repository: https://github.com/OpenCodeInterpreter/OpenCodeInterpreter
Canonical: https://ross.abutalabs.com/products/opencodeinterpreter
Homepage: https://opencodeinterpreter.github.io/
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2024-05-07T11:13:02+00:00

## Health v2 (maintenance only)
Score: 25/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 66
- inputs: {"age_days": 926, "days_push": 848, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1757, forks 221 (observed 2026-08-28T04:05:32.262387+00:00)

## What it is
OpenCodeInterpreter is a suite of open-source code generation models and deployment code that integrates code execution and iterative refinement, aiming to match systems like the GPT-4 Code Interpreter. It includes open-sourced models on Hugging Face, the Code-Feedback training dataset, and a local demo deployment setup.

## Use cases
- generate code from natural language instructions with a local open-source model
- run generated code and iteratively refine it based on execution feedback
- self-host a GPT-4 Code Interpreter alternative
- fine-tune or evaluate code LLMs using the Code-Feedback dataset
- benchmark code generation models on HumanEval and MBPP

## When to choose
- you want an open-source alternative to GPT-4's code interpreter with execution feedback
- you need to run code generation models locally or on your own GPU infrastructure
- you want training data or models for research on execution-refined code generation

## When to avoid
- you need a lightweight code completion plugin for an editor rather than a full model suite
- you cannot host large GPU models (up to 33B parameters)
- you need actively maintained software with recent updates

## Facets
- artifact type: framework
- maturity: maintenance
- function: llm-inference, machine-learning
- domain: large-language-models, machine-learning, developer-tools
- platform: python, self-hosted
- tags: code-generation, execution-feedback, code-llm, huggingface, iterative-refinement, code-interpreter, docker

## Member repositories
- OpenCodeInterpreter/OpenCodeInterpreter (main) score 25

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:32.262387+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 2026-08-30T03:27:38.501047+00:00, confidence not recorded.
  - readme: https://github.com/OpenCodeInterpreter/OpenCodeInterpreter (fetched 2026-08-28T04:05:32.262387+00:00, sha 745fe2b434c4)
  - homepage: https://opencodeinterpreter.github.io/ (fetched 2026-08-29T11:05:45.460418+00:00, sha f65278dd005a)
- Data as of 2026-08-30T08:39:29.467469+00:00.