Vector Search

Failure-memory layer for coding agents: search evidence-rated failure lessons by error text.

Local long-term memory shared by all your AI agents, kept word for word on your own PC.

Ask a codebase a question, get back the source that answers it — every block cited to file:line.

Cross-agent handoff: the next coding agent starts from the last one's facts, not a blank page.

bioRxiv/medRxiv/arXiv preprint full text as structured sections for AI agents + search.

An append-only ledger of sourced, dated, confidence-scored claims your agent cites and you audit

Self-hosted memory for AI agents over MCP: knowledge graph, vectors, graph RAG, cited answers.

Knowledge-graph RAG for multi-language codebases: index, query and edit code in natural language.

Persistent AI memory in one SQLite file: 3-layer hybrid search, confidence scoring, 29 tools.

Store and retrieve text in a Qdrant vector database by similarity search.

Vector collections and document search backed by a Chroma HTTP service.

Occupation classifier: free text to ranked O*NET-SOC codes with tasks, skills and RIASEC. Local.

Convert .eml and .mbox email to clean Markdown for RAG, LLM pipelines, and local knowledge bases

Local retrieval for AI agents: index code, docs, PDFs, data in SQLite; 24 parsers, served via MCP.

Cross-session memory and hybrid RAG over your notes and docs. Local-first, with cited answers.

Adaptive memory for AI agents — FAISS search, chat extraction, cross-project linking

Memory for AI assistants in one SQLite file: full-text search, no vectors, no embeddings.

A semantic search engine for files and code.

Self-correcting agent memory: recall, supersede, revert, forget, GDPR erasure, audit receipts.

Recognition-first cross-agent memory federation. One shared memory across all your agents.