Otto
35f53a0f1c
Before: limit_nodes defaulted to 0 (unlimited) causing 51052 nodes to load After: limit_nodes defaults to 500 for reasonable browser performance Change: Query(0, ge=0, le=50000) -> Query(500, ge=0, le=50000)
Second Brain
An embeddable, offline-first memory system for AI agents with correctness tracking, neural scoring, and semantic retrieval.
What's New (Phase 2-5)
- Sentence-Transformer Embeddings (
src/embedder.py) — Cached, offline, 384-Dim - ChromaDB Vector Store (
src/chroma_store.py) — Semantic similarity search - Neural Confidence Scorer (
src/neural_scorer.py) — PyTorch RL net, trains on confirm/reject feedback - Hybrid Retrieval (
src/retriever.py) — Keyword + Semantic + Neural fusion - FastAPI Dashboard (
fastapi_app.py) — Lightweight web UI (search + confirm/reject) and JSON API - Streamlit Dashboard (
src/app_dashboard.py) — (optional) richer UI for neural training, etc. - Graph Visualization (
src/graph_view.py) — Interactive Cytoscape.js graph with confidence colors
Architecture
Obsidian
Setup and timers: second-brain/docs/OBSIDIAN.md
Quickstart (Dashboard)
Install minimal dashboard deps:
python3 -m pip install -r requirements-dashboard.txt
Run:
SECOND_BRAIN_WORKSPACE="$(pwd)" python3 fastapi_app.py
Then open: http://localhost:8501/
Port is configurable via SECOND_BRAIN_PORT (or PORT), e.g.:
SECOND_BRAIN_WORKSPACE="$(pwd)" SECOND_BRAIN_PORT=8502 python3 fastapi_app.py