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.
OpenLake is a high performance storage engine for efficient LLM inference and GPU Training
| Date | Stars |
|---|---|
| 2026-07-31 | 2307 |
| 2026-08-02 | 2302 |
| 2026-08-06 | 2302 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
35.0
growth rate 0.00%/day
<div align="center">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/openlake-project/openlake/refs/heads/main/assets/openlake-logo-wide-dark.png" width=60%>
<img alt="OpenLake" src="https://raw.githubusercontent.com/openlake-project/openlake/refs/heads/main/assets/openlake-logo-wide.png" width=60%>
</picture>
<h3 align="center">
Fast, easy and efficient storage for LLM Inference and Training
</h3>
<p align="center">
| <a href="https://theopenlake.com/blog"><b>Blog</b></a> | <a href="https://github.com/openlake-project/openlake/tree/main/docs"><b>Documentation</b></a> | <a href="https://theopenlake.com/compare.html"><b>Comparision</b></a> | <a href="https://discord.gg/TNXqVSnP6x"><b>Discord/X</b></a> | <a href="https://theopenlake.com"><b>Website</b></a> |
</p>
[](LICENSE)
[](rust-toolchain.toml)
[](https://discord.gg/TNXqVSnP6x)
[](https://theopenlake.com)
</div>
🔥 Distributed storage for GPU workloads. Built on Rust on `io_uring`, OpenLake is a state of the art storage engine delivering million+ iops within 1ms.
---
## Why OpenLake?
OpenLake is a storage engine for AI infrastructure. With OpenLake you get high throughput for small I/O and cache like performance while being fully persistent and durable.
Keep GPUs fed during training and inference reducing idle time and getting more from your accelerators.
OpenLake is fast with:
- **KV Cache Offload**. Reduced LLM Inference costs by having Petabyte scale KV cache store co-located on GPU hosts.
- **VectorDB**: Fast index building and vector serving.
- **Checkpointing**: Ultra fast checkpoint storage and retrieval for RL and ML workloads.
- **Model Training**: Small file I/O and fast random reads, reduced GPU costs/training time.
- **Context Storage**: Store massive conversations, memories and context for fast agentic retrieval.
Learn more: [Blogs →](https://theopenlake.com/blog) | [Benchmarks →](https://theopenlake.com/blog/taming-the-beast-managing-100-tb-of-kv-cache-on-open-source-inference) | [KV Offload](#1-convert-your-gpu-nodes-into-infinite-kv-pool) | [Object Store](#2-pb-scale-object-store-for-your-gpu-fleet)
<br>
<p align="center">
<img src="https://raw.githubusercontent.com/openlake-project/openlake/main/assets/ttft-recompute.png" width="49%">
<img src="https://raw.githubusercontent.com/openlake-project/openlake/main/assets/total-gpu-sec.png" width="49%">
</p>
<p align="center"><sub>66× speedup on time to first token first token when cached. (128K context window)</sub></p>
GPU nodes contribute to create an OpenLake cluster. The inference engine writes KV once and reads it back in milliseconds (using the host RAM and disk), saving prefill for long and repeated prompts.
## Quickstart:
### 1) Setup KV Pool on GPU nodes:
Drop OpenLake into your existing setup. No code changes:
#### a. Install the connector and start the store:
```bash
pip install openlake-vllm
openlaked
```
#### b. Run vLLM with OpenLake enabled:
```bash
export PYTHONHASHSEED=0
vllm serve <model_name> --kv-transfer-config '{"kv_connector":"OpenLakeConnector","kv_connector_module_path":"openlake_client.openlake_connector","kv_role":"kv_both","kv_connector_extra_config":{"openlake_nodes":["127.0.0.1:9400"],"openlake_device":"local"}}'
```
Note: By default OpenLake offloads to the same host. To enable OpenLake across your GPU fleet, please start `openlaked` with a `--config`.
OpenLake enabled vs disabled:
<img width="1914" height="720" alt="openlake-video" src="https://raw.githubusercontent.com/openlake-project/openlake/main/assets/openlake-perf.gif" />
<p align="center"><sub>OpenLake and vLLM serving Gemma4-31B on H100 (256K Excerpt of 10,931 characters
Read on GitHub
Arnav Balyan · Uber
139
9
4
2
2
2
2
2
2
1
1
1
1
1
1
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:d4b8065a4ed007d5, topic:llm, topic:gpt
matched fp:d4b8065a4ed007d5, topic:model-serving
matched fp:d4b8065a4ed007d5, topic:gpu