ThunderAgent-org/ThunderAgent
A simple, fast and robust program-aware agentic inference system.
This is a tool for developers building AI agents that use large language models (LLMs) and various external tools. It acts as an intelligent traffic controller, taking requests from your agent client and efficiently routing them to LLM infrastructure like vLLM or SGLang, while also managing external resources like Docker containers. The end-user is a developer or machine learning engineer creating agentic applications and looking to optimize their performance and stability.
284 stars.
Use this if you are developing AI agent applications and need to significantly boost the throughput and reliability of your agent's interactions with large language models and external tools.
Not ideal if you are an end-user of an AI agent and not involved in its technical development, or if you are building simple LLM applications without complex agentic workflows or tool use.
Stars
284
Forks
21
Language
Python
License
MIT
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/ThunderAgent-org/ThunderAgent"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
tmgthb/Autonomous-Agents
Autonomous Agents (LLMs) research papers. Updated Daily.
arakoodev/EdgeChains
EdgeChains.js is Full-Stack GenAI library. Front-end, backend, apis, prompt management,...
x-glacier/GenerativeAgentsCN
本项目为Generative Agents项目的重构+深度汉化版本，旨在为中文用户提供一个利于维护的基础版本，以便后续实验或功能拓展。
xavierpuigf/virtualhome
API to run VirtualHome, a Multi-Agent Household Simulator
shadi-fsai/a1facts
a1facts - the precision layer for AI agents