Repositories (9)
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
Implementation of all RL algorithms in a simpler way
Core 7 layers of production grade agentic system
9 Different Ways to Optimize AI Agent Memories
Building a Production-Grade MCP Server Architecture with a Multi-Agent System
An end-to-end pipeline to optimize and host LLM for 100K parallel queries
AI agent that controls a computer
An automated Python tool that uses LLMs and internet to automatically fix your code until it runs perfectly.
End-to-end agentic quantum-ML pipeline: PennyLane GPU quantum-kernel anomaly detection + LangGraph multi-agent system + locally-hosted Qwen3-14B, benchmarked across network-intrusion, LHC physics, and fraud.