Founder & CEO @ FIM Labs · MS AI · Enterprise AI Agents & Document Intelligence · China × Global
Building cognitive architectures that give LLMs better memory than mine 🧠
class TaoAn:
def __init__(self):
self.location = "Singapore × Beijing"
self.company = "FIM Labs"
self.role = "Founder & CEO"
self.education = "MS in Artificial Intelligence, Hawaii Pacific University (2026)"
self.interests = ["RAG", "LLM Memory Architectures", "Knowledge Graphs", "Agentic Workflows"]
self.current_focus = "Enterprise AI agents & document intelligence across the China × Global boundary"
self.belief = "Most 'AI agents' should be workflows — fix the plumbing before buying a bigger pump."
def say_hi(self):
print("Thanks for dropping by! Let's build something cool together.")
me = TaoAn()
me.say_hi()
| Project | What it is |
|---|---|
| CogCanvas | Training-free long-term memory for LLM conversations — extracts verbatim-grounded artifacts into a queryable graph. 32.4% on LoCoMo (+7.8pp vs RAG). |
| nano-spec | Spec-driven thinking, nano-sized docs — minimal-but-sufficient specs that AI coding assistants can act on reliably. ⭐ 45+ |
| FIM One | Open-source AI agent platform that embeds as a Copilot or connects systems as a Hub — bridging global SaaS with the China enterprise stack. |
📖 Selected Research
📄 AI as Equalizer or Amplifier? Task Complexity as the Moderating Factor for Human Expertise in Hybrid Intelligence Systems Accepted at HHAI 2026 — 5th Int'l Conference on Hybrid Human-Artificial Intelligence (Munich, Jul 2026)
🧠 CogCanvas: Verbatim-Grounded Artifact Extraction for Long LLM Conversations arXiv preprint, 2026 — 32.4% on LoCoMo (+7.8pp vs RAG), +20.6pp on temporal reasoning
♾️ Cognitive Workspace: Towards Functional Infinite Context Through Active Memory Management arXiv:2508.13171
"The best way to predict the future is to invent it." — Alan Kay