Getting Started
What Wolbarg is, why it exists, and the core philosophy behind its provider architecture.
What is Wolbarg?
Wolbarg is a TypeScript SDK that gives multiple AI agents a shared, persistent semantic memory. You store facts with remember(), retrieve them with recall(), optionally ingest documents, and compress memories when you need an LLM summary.
Version 0.2 rebuilds the internals around replaceable providers: storage, embeddings, keyword search, rerankers, OCR, vision, and chunking — while keeping the public API small.
Why does it exist?
Most agent stacks either bolt memory onto a chat transcript or depend on a hosted vector database. Wolbarg sits in between: a local-first (or bring-your-own Postgres) memory layer with explicit providers, ACID writes, and hybrid retrieval.
Core philosophy
- Everything is configurable — swap any provider.
- Nothing is required unless necessary — only
organization,storage, andembedding. - Optional features degrade gracefully — missing reranker / OCR / keyword search skips that step, no crash.
- Calling a feature without its provider fails cleanly — e.g.
compresswithoutllmis a TypeScript error and a runtimeProviderNotConfiguredError.
What's in v0.2
- Constructor DI + factory helpers (
sqlite,openaiEmbedding, …) - SQLite and PostgreSQL storage
- Hybrid recall (semantic + BM25), metadata filters, MMR, rerankers
- Document
ingest(PDF, DOCX, Markdown, images + optional OCR/vision) - Pluggable chunking strategies
- Optional LLM compression
What it is not
- Not an agent / orchestration framework
- Not a hosted vector database SaaS
- Not a chat UI
When should you use it?
Use Wolbarg when multiple agents (or one long-running agent) need durable, searchable memory with clear backends and no infrastructure lock-in.