bxw91
UserVector Graph RAG for code & docs with Persistent Chat-Session Memory — BM25 (multi-lang), AST chunking. Hybrid, Compute, Scan, Timeline, Absence, Salience. Graph + temporal knowledge. Privacy Stamps. Source Adapters. Chat summarisation + verbatim copy + free scan. Git indexing. CLI, MCP and Claude Code plugin. Ollama or cloud LLMs. Dashboard.
Categories
Indexed Skills (3)
authoring-brainpalace-docs
Use when `brainpalace sync-docs --fix` reports PROSE-NEEDED, when a new command/skill/mode needs its human prose (Purpose, Examples) written, or when a human wants to mark a doc-verifier UNVERIFIABLE claim as human-confirmed. Authoring playbook for interface docs whose machine regions are generated.
configuring-brainpalace
Installation and configuration skill for BrainPalace document search system. Use when asked to "install BrainPalace", "setup BrainPalace", "configure BrainPalace", "setting up document search", "installing brainpalace packages", "configuring API keys", "initializing project for search", "troubleshooting BrainPalace", "pip install brainpalace", "BrainPalace not working", "BrainPalace setup error", "configure embeddings provider", "setup ollama for BrainPalace", or "BrainPalace environment variables". Covers package installation, provider configuration, project initialization, and server management.
using-brainpalace
Expert BrainPalace skill for document search with BM25 keyword, semantic vector, hybrid, graph, multi, compute, scan, absence, and timeline retrieval modes. Use when asked to "search documentation", "query domain", "find in docs", "bm25 search", "hybrid search", "semantic search", "graph search", "multi search", "compute query", "scan sessions", "absence query", "timeline query", "find dependencies", "code relationships", "searching knowledge base", "querying indexed documents", "finding code references", "exploring codebase", "what calls this function", "find imports", "trace dependencies", "brain search", "brain query", "knowledge base search", "cache management", "clear embedding cache", "cache hit rate", or "cache status". Supports multi-instance architecture with automatic server discovery. GraphRAG mode enables relationship-aware queries for code dependencies and entity connections. Pluggable providers for embeddings (OpenAI, Cohere, Ollama) and summarization (Anthropic, OpenAI, Gemini, Grok, Ollama). S
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.