Otto 7814fa4a65 feat: free-first reaktivierung Teil 2 — torch-freier embedder, Live-Aktivitäten im Graph, systemd-Pfadkorrektur
- src/embedder.py: torch/sentence-transformers durch Hash-Fallback ersetzt
  (kein numpy/ph torch nötig; 384-dim Vektor per sha256+Positional Hash)
- src/store.py: _touch_access() tracked reads für Live-Graph-Aktivität
- fastapi_app.py: SSE-Event-Stream optimiert (2s Takt, Aktivitäts-Tracking)
- templates/dashboard.html: Graph 2.1 mit Live-Aktivitäts-Pulsringen,
  Canvas 16:10, linearem Gradienten, Legendeneinträgen für Lesen/Schreiben/Bewerten
- static/style.css: Grafik-Radius 6px, Activity-Legendenfarben
- openclaw_cron_wrapper.py: CRON_TASKS_DIR ins second-brain-Verzeichnis
- systemd/*.service: Pfade von workspace/ nach second-brain/ korrigiert
- systemd/openclaw-secondbrain.target: neuer Multi-User-Target für Second Brain
- .gitignore: backups/ hinzugefügt

Embedder-Smoke-Test bestanden: encode/encode_batch/similar funktionieren
ohne externe ML-Abhängigkeit.

Refs: #36
2026-06-25 03:03:21 +02:00
2026-05-30 00:38:57 +02:00
2026-05-30 00:38:57 +02:00
2026-05-26 21:02:39 +02:00

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

Description
Zweites Gehirn für OpenCLaw - Langzeit- und Kurzzeitgedächtnis, Bewertungsnetzwerke, Proaktivität, Fehlerkorrektur
Readme 853 KiB
Languages
Python 74.3%
HTML 21.3%
CSS 4.2%
Shell 0.2%