textrawl
Your second brain, wired for AI. Search documents, remember conversations, discover connections.
Why textrawl?
Crawl Everything
Markdown, PDF, HTML, email, DOCX. Your documents, structured for AI.
Semantic Search
Find by meaning, not just keywords. Hybrid search fuses keyword and vector results.
Persistent Memory
Remember facts, track conversations, and build a knowledge graph across sessions.
Proactive Insights
Automatically discover connections, patterns, and outliers across your knowledge base.
Web Dashboard
Command center for your knowledge. Browse, upload, explore timelines, and build custom applets.
Multimodal
Process images and audio alongside documents. Vision descriptions and speech transcription built in.
Multiple Interfaces
Web dashboard, MCP for AI assistants, REST API, CLI, and desktop app. Your knowledge, however you want it.
Local First
Run entirely on your machine. Your data never leaves.
Tools & API
Twenty-five tools that give you — and your AI — access to everything you know. Available via MCP, REST API, or the dashboard.
Document Tools
searchHybrid semantic + full-text search
get_documentRetrieve full document content
list_documentsBrowse with pagination and filters
update_documentUpdate document metadata
add_noteCreate notes with auto-embedding
Memory Tools
remember_factStore facts about entities
build_knowledgeBatch store facts and relations
query_memorySearch, list, or look up entities
relate_entitiesCreate entity relationships
forget_entityDelete entity and memories
extract_memoriesExtract entities from text via LLM
Conversation Tools
save_conversation_contextSave conversation for recall
query_conversationsSearch, list, or get conversations
delete_conversationDelete a conversation session
Insight Tools
get_insightsView discovered patterns and connections
discover_connectionsTrigger insight scan
dismiss_insightDismiss an insight
Unified Tools
askUnified RAG across all sources
daily_briefingDaily summary and resurfaced knowledge
save_urlSave web pages as documents
timelineBrowse knowledge chronologically
get_statsStatistics across all features
Postgres Analysis
pg_analyzeDatabase health analysis
pg_recommendationsOptimization recommendations
pg_report_historyCompare analysis over time
Up and running in 60 seconds
git clone https://github.com/jeffgreendesign/textrawl.gitClone the repo
pnpm run setupConfigure credentials
pnpm run devStart the server
Why I built this
I kept losing context. Notes in one app, bookmarks in another, PDFs scattered across folders. When I needed to find something, search always failed me.
Textrawl started as a personal knowledge base—a way to crawl my own documents and make them searchable with semantic understanding, not just keyword matching.
Now it's a personal knowledge server — accessible through a dashboard, AI assistants via MCP, or the REST API. Your second brain, available everywhere.