Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Composable Elixir library for LLM interactions built on Req and Finch
| Date | Stars |
|---|---|
| 2026-07-31 | 551 |
| 2026-08-01 | 551 |
| 2026-08-06 | 551 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
60.0
growth rate 0.00%/day
# ReqLLM [](https://hex.pm/packages/req_llm) [](https://hexdocs.pm/req_llm/) [](https://github.com/agentjido/req_llm/actions/workflows/ci.yml) [](https://github.com/agentjido/req_llm/blob/main/LICENSE) [](https://jido.run) [](https://jido.run/ecosystem) [](https://jido.run/discord) > **Join the community!** Come chat about building AI tools with Elixir and coding Elixir with LLMs in [The Swarm: Elixir AI Collective](https://jido.run/discord) Discord server. A [Req](https://github.com/wojtekmach/req)- and [Finch](https://github.com/sneako/finch)-backed package to call LLM APIs that standardizes requests and responses across providers. ## Why Req LLM? LLM APIs are inconsistent. ReqLLM provides a unified, idiomatic Elixir interface with standardized requests and responses across providers. **Unified architecture:** - **High-level API** – Vercel AI SDK-inspired functions (`generate_text/3`, `stream_text/3`, `generate_object/4` and more) that normalize requests and responses across providers. - **Provider transports** – Req powers request/response calls; Finch powers streaming. Provider callbacks translate model metadata, options, bodies, and responses behind the same public API. **Model Support Snapshot** ReqLLM currently exposes **1,205 models across 21 implemented provider integrations** from [LLMDB](https://llmdb.xyz), the model catalog maintained through `llm_db`. Counting the cataloged-but-not-separate `google_vertex_anthropic` namespace, the registry contains **1,218 models across 22 provider namespaces**. That breadth extends well beyond chat: ReqLLM tracks **92 non-text operation models** across embedding, image generation, text-to-speech, transcription, rerank, and OCR APIs. The fixture suite currently contains **622 unique recorded model specs**, giving ReqLLM a compatibility ledger for text and multi-modal provider behavior. | Provider | ID | Catalog models | Operation surface | Recorded specs | Guide | |---|---|---:|---|---:|---| | [Alibaba Cloud Bailian](https://llmdb.xyz/?providers=alibaba) | `alibaba` | 50 | text, OCR 1, transcription 1 | 0 | — | | [Alibaba Cloud Bailian (China)](https://llmdb.xyz/?providers=alibaba_cn) | `alibaba_cn` | 82 | text, OCR 1, transcription 1 | 0 | — | | [Amazon Bedrock](https://llmdb.xyz/?providers=amazon_bedrock) | `amazon_bedrock` | 92 | text, embedding 3 | 7 | [Guide](guides/amazon_bedrock.md) | | [Anthropic](https://llmdb.xyz/?providers=anthropic) | `anthropic` | 11 | text | 11 | [Guide](guides/anthropic.md) | | [Azure OpenAI](https://llmdb.xyz/?providers=azure) | `azure` | 103 | text, embedding 6 | 26 | [Guide](guides/azure.md) | | [Cerebras](https://llmdb.xyz/?providers=cerebras) | `cerebras` | 5 | text | 2 | [Guide](guides/cerebras.md) | | [Cohere](https://llmdb.xyz/?providers=cohere) | `cohere` | 17 | text, rerank 5 | 5 | — | | [ElevenLabs](https://llmdb.xyz/?providers=elevenlabs) | `elevenlabs` | 4 | speech 4 | 4 | — | | [Fireworks AI](https://llmdb.xyz/?providers=fireworks_ai) | `fireworks_ai` | 12 | text | 12 | [Guide](guides/fireworks_ai.md) | | [Google Gemini](https://llmdb.xyz/?providers=google) | `google` | 50 | text, embedding 2, image 8 | 24 | [Guide](guides/google.md) | | [Google Vertex AI](https://llmdb.xyz/?providers=google_vertex) | `google_vertex` | 40 | text | 11 | [Guide](guides/google_vertex.md) | | [Groq](https://llmdb.xyz/?providers=groq) | `groq` | 18 | text, speech 2, transcription 2 | 11 | [Guide](guides/groq.md) | | [Meta Model API](https://llmdb.xyz/?providers=meta) | `me
Excerpt of 27,982 characters
Read on GitHub
Mike Hostetler · Epic Creative · Israel
393
68
36
21
17
13
13
Danila Poyarkov
11
8
7
Barna Kovacs · Austria
7
6
6
5
5
5
Steve Hodgkiss
4
4
4
Julian Scheid
4
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:39b09d208d39ee6d, topic:llm