#121 · Primary category: LLM Application Frameworks
xsai
🤖💬 extra-small AI SDK.
Project last updated:08/29/26
GitHub Stars
650
Forks
59
Contributors
29
License
MIT
Why we included this project
If you've reached for the Vercel AI SDK and wished it shipped with less baggage, xsAI is worth a look. It's a TypeScript library that talks to any OpenAI-compatible endpoint, whether that's OpenAI itself, Ollama, or a local gateway, through a focused set of utilities for generating text, streaming responses, and structured output. The project keeps its footprint small by building directly on the Fetch API, staying ESM-only, and avoiding dependencies unless they're strictly required, which makes it a practical choice for edge functions and browser bundles. Tool calling is supported out of the box, so you can wire up agents that invoke functions without pulling in a heavier framework. Teams that want a portable foundation for OpenAI-compatible apps rather than a full application framework will find the trade-offs clearly documented.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
langchain
The agent engineering platform.
dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
litellm
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
llama_index
LlamaIndex is the leading document agent and OCR platform