# ggml — developer ecosystem report

> AI inference at the edge

- GitHub org: `ggml-org`
- Category: ai
- Overall score: 55.0 / 100
- Overall rank: #139
- Last refreshed: 2026-08-20

## Pillar scores

| Pillar | Score / 100 | Rank | Weight in overall |
| --- | --- | --- | --- |
| Code & Polish | 50.0 | #446 | ~22% |
| Education | 83.0 | #67 | ~18% |
| AI readiness | 14.0 | #715 | part of Reach |
| Builder experience | 0.0 | #1 | ~12% |
| Community | 79.0 | #4 | ~16% |
| Reach | 81.0 | #28 | ~18% |
| Momentum | 36.0 | #397 | ~14% |

## Links

- GitHub: https://github.com/ggml-org
- Website: https://ggml.ai

## Public GitHub totals

| Metric | Value |
| --- | --- |
| Repos analyzed | 12 |
| Stars | 198,524 |
| Forks | 30,220 |
| Open issues | 3,829 |
| Contributors | — |

## Top repositories

| Repo | Stars | Language | Description |
| --- | --- | --- | --- |
| [llama.cpp](https://github.com/ggml-org/llama.cpp) | 124,765 | C++ | LLM inference in C/C++ |
| [whisper.cpp](https://github.com/ggml-org/whisper.cpp) | 53,042 | C++ | Port of OpenAI's Whisper model in C/C++ |
| [ggml](https://github.com/ggml-org/ggml) | 15,201 | C++ | Tensor library for machine learning |
| [llama.vim](https://github.com/ggml-org/llama.vim) | 2,147 | Vim Script | Vim plugin for LLM-assisted code/text completion |
| [llama.vscode](https://github.com/ggml-org/llama.vscode) | 1,482 | TypeScript | VS Code extension for LLM-assisted code/text completion |
| [Llama-macOS](https://github.com/ggml-org/Llama-macOS) | 1,454 | Swift | A cosy home for your LLMs. |
| [p1](https://github.com/ggml-org/p1) | 194 | — | LLM-based code completion engine |
| [llama.qtcreator](https://github.com/ggml-org/llama.qtcreator) | 66 | C++ | Local LLM-assisted text completion for Qt Creator. |
| [ci](https://github.com/ggml-org/ci) | 32 | Shell | CI for ggml and related projects |
| [llama-install.sh](https://github.com/ggml-org/llama-install.sh) | 29 | Python | Build and install script for llama.app |
| [convert](https://github.com/ggml-org/convert) | 18 | Shell | Convert models to GGUF |
| [llama.pages](https://github.com/ggml-org/llama.pages) | 18 | Svelte | llama.cpp's official website |

## Methodology

Scores are computed from public signals only (GitHub, package registries, docs sites, community platforms). Pillar definitions: https://www.smoower.com/docs.md

---

HTML version: https://www.smoower.com/ggml-org
Machine index: https://www.smoower.com/llms.txt · MCP server: https://www.smoower.com/mcp · REST API: https://www.smoower.com/api/v1