Publications

Autonomous Agent Patterns / Frameworks

Run Qwen3.6-35B-A3B on 6GB VRAM Using Llama.cpp

LLM‑Wiki — The Foundation for Market‑Intelligence Knowledge

Building an OpenClaw-like AI for Teams: A Multi-User Assistant with Scheduled Intelligence and Financial Expertise

Enrich Agents with Domain-Specific Knowledge to Make AI Smarter (Ontology, Skills, RAG, Tool Calling)

Explore with an AI-Powered Tool to Automatically Identify "Best" Trading Strategies for Any Stock

Reduce Trading Stress with AI-Powered Intelligent Tools

Challenges in Working with Market Data

Time Series Foundation Models for Forecasting Task

Awesome Financial Reasoning Workflow (Fin-R1 Model + MCP Tools / RAG) on Open-WebUI/Ollama

MCPO: Supercharge Open-WebUI / Ollama with MCP Tools

Revolutionizing Code Agents with Multi-million Token Context + Agentic Workflow Prompts + Memory Bank

Llamacpp 128K GGUF, RoPE Scaling, Tensor Override for Local Vibe Coding (Cline/Roo Code)