# Fireworks.ai — developer ecosystem report

- GitHub org: `fw-ai`
- Category: ai
- Overall score: 56.0 / 100
- Overall rank: #126
- Last refreshed: 2026-08-19

## Pillar scores

| Pillar | Score / 100 | Rank | Weight in overall |
| --- | --- | --- | --- |
| Code & Polish | 37.0 | #817 | ~22% |
| Education | 78.0 | #163 | ~18% |
| AI readiness | 11.0 | #790 | part of Reach |
| Builder experience | 0.0 | #1 | ~12% |
| Community | 58.0 | #56 | ~16% |
| Reach | 69.0 | #86 | ~18% |
| Momentum | 33.0 | #450 | ~14% |

## Links

- GitHub: https://github.com/fw-ai
- Website: https://fireworks.ai

## Public GitHub totals

| Metric | Value |
| --- | --- |
| Repos analyzed | 12 |
| Stars | 425 |
| Forks | 137 |
| Open issues | 299 |
| Contributors | — |

## Top repositories

| Repo | Stars | Language | Description |
| --- | --- | --- | --- |
| [cookbook](https://github.com/fw-ai/cookbook) | 194 | Jupyter Notebook | Recipes and resources for training, building generative AI with Fireworks |
| [benchmark](https://github.com/fw-ai/benchmark) | 112 | Python | Benchmark suite for LLMs from Fireworks.ai |
| [fireconnect](https://github.com/fw-ai/fireconnect) | 45 | JavaScript | CLI to use Fireworks AI models in Claude Code, Codex, OpenCode, Pi, and other coding agents. |
| [forge](https://github.com/fw-ai/forge) | 17 | TypeScript | — |
| [minimax-kernels](https://github.com/fw-ai/minimax-kernels) | 17 | Python | Kernels for MiniMax models. |
| [llama-cuda-graph-example](https://github.com/fw-ai/llama-cuda-graph-example) | 11 | — | Example of applying CUDA graphs to LLaMA-v2 |
| [fireworks_poe_bot](https://github.com/fw-ai/fireworks_poe_bot) | 9 | Python | Infrastructure to run a poe.com bot based on Fireworks.ai hosted models |
| [ai-starter-kits](https://github.com/fw-ai/ai-starter-kits) | 8 | Python | AI App Starter Templates - ChatBots, Summarisers and more! |
| [langchain](https://github.com/fw-ai/langchain) | 4 | Python | ⚡ Building applications with LLMs through composability ⚡ |
| [flashinfer](https://github.com/fw-ai/flashinfer) | 2 | Python | — |
| [llm_eval_meta](https://github.com/fw-ai/llm_eval_meta) | 2 | Python | Repro for official Llama 3.1 Benchmarks |
| [llm_eval](https://github.com/fw-ai/llm_eval) | 2 | Python | Fireworks OSS Evaluation suite for evals |

## 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/fw-ai
Machine index: https://www.smoower.com/llms.txt · MCP server: https://www.smoower.com/mcp · REST API: https://www.smoower.com/api/v1