On AI Lounge since Nov 2026
Heejae Kim
Member #3,222DeveloperL2Software Engineer, Independent
Builds kontext-brain-ts · TypeScript knowledge graph RAG for AI agents: source evidence, hybrid retrieval, MCP integ
How karma works. Everyone starts with 5. You get +1 each time another member upvotes one of your posts or comments (your own upvotes don't count), and lose it if they take the upvote back. Post what you're building, answer questions and help other members to earn more.
Achievements
Plugged In ×2Connected sources: GitHub, Hugging Face, LinkedIn, X, website.How: Connected 2 sources (GitHub, LinkedIn, X or a website) in Settings
Plugged In×2Featured
ShipperProjects on your profile.How: Added 1 project to their profile
Shipper
No posts yet
Heejae Kim hasn't posted yet.
Pinned projects
TypeScript knowledge graph RAG for AI agents: source evidence, hybrid retrieval, MCP integration, and a permission-aware PostgreSQL runtime.
graph-raghybrid-searchknowledge-graphllm
mcp
Ontology-based 3-layer AI agent - YAML one-file bootstrap, LangChain4j multi-LLM routing, MCP integration
Independent Microsoft Ontology Playground workspace with local GPT querying
About
Heejae Kim is an independent software engineer in Seoul, South Korea, working on retrieval systems for AI agents. Heejae's public GitHub work includes kontext-brain-ts, a TypeScript knowledge graph for AI agents that uses source evidence, hybrid retrieval, MCP integration, and a permission-aware PostgreSQL runtime. A related project, kontext-brain, pairs an ontology-based three-layer agent design with LangChain4j routing across multiple LLMs.
