# CodeGeeX

CodeGeeX4-ALL-9B, a versatile model for all AI software development scenarios, including code completion, code interpreter, web search, function calling, repository-level Q&A and much more.

Repository: https://github.com/zai-org/CodeGeeX4
Canonical: https://ross.abutalabs.com/products/codegeex
Homepage: https://codegeex.cn
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2024-08-25T14:26:16+00:00
Link (homepage): https://codegeex.cn

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 56
- inputs: {"age_days": 791, "days_push": 738, "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 2585, forks 267 (observed 2026-08-28T04:07:02.650752+00:00)

## What it is
CodeGeeX is a family of open multilingual code generation large language models (13B and successors CodeGeeX2/CodeGeeX4) pre-trained on 20+ programming languages, with IDE extensions for VS Code and JetBrains. It supports code generation, crosslingual code translation, and includes the HumanEval-X benchmark.

## Use cases
- generate code from natural language prompts
- translate code between programming languages
- autocomplete code inside VS Code or JetBrains
- self-host an open code generation LLM
- benchmark multilingual code models with HumanEval-X

## When to choose
- you need an open-source code LLM you can self-host or fine-tune
- you want AI code completion in VS Code or JetBrains IDEs
- you need multilingual code generation or crosslingual translation
- you want to evaluate models on HumanEval-X

## When to avoid
- you only want a hosted commercial coding assistant without model management
- you lack GPU resources for large model inference
- you need the absolute latest frontier code model rather than an open one

## Facets
- artifact type: library
- maturity: active
- function: llm-inference, machine-learning, deep-learning
- domain: large-language-models, artificial-intelligence, developer-tools
- platform: python, cross-platform
- tags: code-generation, code-llm, pretrained-models, humaneval-x, ide-plugin, multilingual, gpu

## Member repositories
- zai-org/CodeGeeX4 (main) score 23
- zai-org/CodeGeeX (mirror) score 32
- zai-org/CodeGeeX2 (mirror) score 28

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:02.650752+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 2026-08-29T17:25:11.188679+00:00, confidence not recorded.
  - readme: https://github.com/zai-org/CodeGeeX4 (fetched 2026-08-28T04:07:02.650752+00:00, sha beecde067fbf)
  - homepage: https://codegeex.cn (fetched 2026-08-29T08:25:41.479285+00:00, sha 44136fa355b3)
- Data as of 2026-08-30T08:39:29.467469+00:00.