Laya System One
Laya is a System One decision engine.
Platform availability
Available on 1 of 10 platforms
- Unraid
- TrueNAS (not listed)
- Umbrel (not listed)
- ZimaOS (not listed)
- Proxmox (not listed)
- Helm (not listed)
- Mac (not listed)
- Windows (not listed)
- Linux (not listed)
- Any server (not listed)
Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.
76/100 Good
- Maintained
- 91last commit 11 days ago
- Popular
- 9135,507 GitHub stars
- Easy to install
- 351 install platform, install notes, Docker image
- Light to run
- 303 GB minimum RAM
- Security check
- 100no serious findings, CI, tests
Availability: platform listings confirmed today, links checked 25 days ago
- GitHub stars
- 35,507
- Open issues
- 101
- Last commit
- 2026-11-10
- Latest release
- v0.4.31
- License
- Apache-2.0
- Activity
- declining
Checked 8 days ago - source: GitHub (NandhaKishorM/laya)
Resources & Compatibility
Minimum requirements: 3 GB RAM, 647 MB disk. ARM (e.g. Raspberry Pi) is not supported.
Checked 54 days ago - source: Docker Hub image tags and published docs
First-install notes
- Install Laya with pip and Python 3.8+ Run pip install laya using pip (the Python package installer) on Python 3.8 or newer. If your Python is older, the install or later imports can fail. source
- First run downloads model from Hub The first time you load the model with laya.load('convaiinnovations/laya'), Laya downloads its weight files from Hugging Face. Keep internet access and disk space available, or the load can fail. source
- Use your GPU if one is available If you have a supported NVIDIA GPU, set the device to CUDA (NVIDIA's graphics computing) so Laya can run faster. Without it, the model may run on CPU, which is usually slower. source
- Unraid install & first start Choose cpu or nvidia at install; nvidia sets Extra Parameters to --runtime=nvidia and needs the Unraid NVIDIA Driver plugin. Optionally set an API key (clients send Authorization: Bearer YOUR_API_KEY). First start downloads the model weights into the Model cache folder and shows healthy once loaded; keep the API port on a trusted network. source
Fetched 39 days ago - each note links to its source
Variants
Alternatives
No alternatives collected yet.
Common questions
Do I need internet access when Laya starts for the first time?
Yes. The first time the model loads, it downloads weight files from Hugging Face, so keep internet access and disk space available.
How do I run Laya with an NVIDIA GPU?
Use a supported NVIDIA GPU and set the device to CUDA. Without it, the model may run on CPU, which is usually slower.
How long can Laya documents be?
Laya-multilingual can read up to 8,192 tokens when max_len=8192 is passed. Accuracy beyond about 4,000 tokens of preceding text can vary, so test long documents on your own data.
Can Laya be exposed as an HTTP service?
Yes. The laya[serve] extra provides an HTTP server, so install that extra if you want to expose Laya over HTTP.
Can I preload Laya models instead of downloading them on first use?
The Router downloads a checkpoint on first use. If you want the models ready before requests arrive, use Router(preload=True) to load all three checkpoints up front.
Answers sourced from deepwiki.com, github.com
Community
Collected 49 days ago - public community threads