tiannuo-yang/SearchAgent-X

A High-Efficiency System of Large Language Model Based Search Agents

26
/ 100
Experimental

This system helps developers build and deploy large language model (LLM) based search agents that need to quickly find information and reason about it. It takes a corpus of documents, an embedding model, and an LLM, then efficiently processes user requests by performing interleaved search and reasoning. Developers working on LLM-powered applications will find this useful for speeding up their projects.

No commits in the last 6 months.

Use this if you are a developer building LLM-based search agents and need to serve them with low latency and high throughput, or if you're mitigating slow multi-turn LLM rollouts during post-training.

Not ideal if you are an end-user looking for a ready-to-use search application rather than a system for building one.

LLM development AI model serving search agent optimization LLM fine-tuning information retrieval
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 7 / 25
Community 8 / 25

How are scores calculated?

Stars

77

Forks

5

Language

Python

License

Last pushed

Jul 02, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/tiannuo-yang/SearchAgent-X"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.