Research Infrastructure
Search, memory, and agent tooling I built to accelerate my own research — it powers the citation-graph demo.
research-kb
in progressA hybrid-search knowledge base I built to accelerate my own research: BM25 full-text, vector embeddings, and a citation and concept graph over a large multi-domain corpus spanning causal inference, RL and control, and sequence models. It's exposed as MCP tools so an assistant can search and traverse it directly, and it's the data source behind the /lab/research-graph demo on this site. Infrastructure for my own learning, not a product.
Stack: Python · BM25 · vector search · knowledge graph · MCP
What's next
Densifying the citation graph and hardening corpus metadata quality across domains.
research-agent
prototypeAn early prototype of a multi-agent research pipeline built on research-kb: it decomposed a question, retrieved evidence, synthesized a structured answer, and validated citations against the sources — the querying layer of that enabling system. The repo is now archived.
Stack: Python · LangGraph · MCP · research-kb
What's next
An earlier prototype of the querying layer, now archived — its approach is folded into the active research tooling.
research_toolkit
in progressA collection of Claude Code skills exposing the research-kb and research-agent stack as repeatable workflows: literature review, causal-assumption audits, citation-network analysis, and cross-domain concept discovery. The point is to validate research claims systematically before anything is published.
Stack: Python · Claude Code · MCP · research-kb · research-agent
What's next
A methodology page on how that validation works — the local research-* dogfooding sandboxes that vet claims before they ship — is coming under this cluster.