laya
A multilingual decision model library that makes choice, score and yes/no decisions over text in a single fast pass. It also includes a router that picks the right model per request, for classification and routing tasks.
Pick a small issue you can reproduce, then fix it with your AI coding agent.
Share on XLicense: Apache-2.0
Overview
Laya is a Python library for making typed decisions over text in a single forward pass, without generating tokens. It answers choice, score and yes/no questions in more than 100 languages, and the README quotes about 33 ms per request. A router picks the right checkpoint for each request, such as English or multilingual. You pass a piece of text and a set of questions, and get answers with probabilities. It installs with pip and has optional extras for an HTTP server, MCP, LangChain, LlamaIndex, CrewAI and ONNX.
Key features
- Choice, score and yes/no decisions in one forward pass
- Works across 100+ languages
- Router selects the checkpoint per request
- Optional extras: HTTP server, MCP, LangChain, LlamaIndex, CrewAI
- TypeScript version in laya-ts
Best for
Developers building classification or routing steps, such as sending a support message to a department. Long documents need max_len set to 8192, and the README advises checking accuracy on your own data.
- Upstream
- NandhaKishorM/laya
- Fork on GitHub
- Guo-astro/laya
- Upstream stars
- 35k
- Category
- AI agents and LLM tools
- Language
- Python
- License
- Apache-2.0
- Forked
- 2026-09-22
- Sync status
- Updated by last syncLast synced 2026-11-09
More in AI agents and LLM tools
/last30days is an AI-agent skill for researching recent discussions across social platforms, video, news, markets, and the web. It brings scattered signals together in a synthesized brief for trend research and preparation.
Forked 2026-10-22Last synced 2026-11-09License: MITAI agents and LLM toolsGitHub
A portable C99 inference engine for running Kimi K3 on a CPU without a GPU or machine-learning framework. It streams the large checkpoint from disk to support inference with limited RAM, for batch text generation or text chat.
Forked 2026-10-21Last synced 2026-11-09License: Apache-2.0AI agents and LLM toolsGitHub
LayerFS gives AI agents writable workspaces over shared history, so they can work in parallel without copying the base. Use it to checkpoint, branch, rewind, and merge agent changes.
Forked 2026-10-21Last synced 2026-11-09License: MITAI agents and LLM toolsGitHub
Magnitude runs open models locally and tunes kernels for your hardware. Use it to connect local models to supported agents or an OpenAI-compatible client.
Forked 2026-10-19Last synced 2026-11-09License: Apache-2.0AI agents and LLM toolsGitHub