# deepseek-ai/DeepSeek-Coder

DeepSeek Coder: Let the Code Write Itself

Repository: https://github.com/deepseek-ai/DeepSeek-Coder
Canonical: https://ross.abutalabs.com/products/deepseek-coder
Homepage: https://chat.deepseek.com/
Language: Python
License: MIT
License Family: permissive
Last push: 2025-11-11T06:44:56+00:00

## Health v2 (maintenance only)
Score: 50/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 51, release rhythm 35, longevity 74
- inputs: {"age_days": 1048, "days_push": 295, "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 24217, forks 2922 (observed 2026-08-28T04:11:35.783292+00:00)

## What it is
DeepSeek Coder is a series of open code language models (1B to 33B) trained from scratch on 2T tokens of code and natural language, with a repository providing inference and fine-tuning code. It supports project-level code completion and infilling with a 16K context window.

## Use cases
- autocomplete code in my editor with a local model
- generate code from natural language descriptions
- fill in missing code in a project
- fine-tune a code LLM on my own codebase
- run an open-source code model offline

## When to choose
- you need a self-hosted code generation model with permissive MIT licensing
- you want project-level completion and infilling with long context
- you need a range of model sizes to fit your hardware

## When to avoid
- you only want a hosted API without managing GPUs
- you need general-purpose chat rather than code-focused models
- you lack GPU resources for larger model sizes

## Facets
- artifact type: library
- maturity: active
- function: llm-inference, machine-learning, llm-training
- domain: large-language-models, developer-tools, artificial-intelligence
- platform: python
- tags: code-generation, code-completion, open-weights, transformer-models, infilling, gpu, linux

## Member repositories
- deepseek-ai/DeepSeek-Coder (main) score 50

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:35.783292+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 2026-08-29T16:56:16.290119+00:00, confidence not recorded.
  - readme: https://github.com/deepseek-ai/DeepSeek-Coder (fetched 2026-08-28T04:11:35.783292+00:00, sha f3b6055b5012)
- Data as of 2026-08-30T08:39:29.467469+00:00.