petal-power/second-brain
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
repo for storing the second brain project
33 Commits 4 Branches 0 Tags 1.1 MiB
Python 82.4%
HTML 15.5%
Shell 1%
Dockerfile 0.9%
Mako 0.2%
main
Go to file
Travis Herbranson 8d29f2fb08 Merge branch 'claude/config-local-overlay': settings.local.toml overlay loader 
Adds a section-level overlay so config.py reads settings.local.toml
(gitignored) on top of the committed settings.toml. Lets the operator
keep secrets and per-host paths out of git while still committing the
shared template — same pattern other homelab projects use.

One commit (d40f25c): src/second_brain/config.py picks up the overlay
file when present, and tests/test_config_overlay.py covers the merge
semantics. No change to the committed settings.toml format; no secret
introduced into the repo tree.
2026-05-25 17:16:26 -04:00
alembic transcripts: capture segment-level output into a new JSONB column 2026-05-25 13:40:49 -04:00
config postgres migration: schema, models, embeddings, alembic 2026-05-24 22:46:48 -04:00
deploy Merge branch 'claude/laughing-shirley-52f4a6': queue-page add form + tower CUDA-12 pin 2026-05-25 15:43:47 -04:00
prompts project init 2026-05-22 19:08:22 -04:00
reviews web: show "Re-extract only" for articles too 2026-05-25 16:15:39 -04:00
src/second_brain config: load settings.local.toml as a section-level overlay 2026-05-25 17:09:57 -04:00
tests config: load settings.local.toml as a section-level overlay 2026-05-25 17:09:57 -04:00
.gitignore add .gitignore 2026-05-24 21:10:53 -04:00
alembic.ini postgres migration: schema, models, embeddings, alembic 2026-05-24 22:46:48 -04:00
CLAUDE.md docs: refresh CLAUDE.md to current shipped state 2026-05-25 15:46:20 -04:00
postgres-migration-planning.md docs: update CLAUDE.md + migration plan to reflect shipped Postgres design 2026-05-24 22:57:31 -04:00
pyproject.toml tower: pin CUDA-12 wheels + LD_LIBRARY_PATH wrapper for the systemd service 2026-05-25 15:39:13 -04:00
README.md updates to project files 2026-05-24 22:23:59 -04:00
uv.lock tower: pin CUDA-12 wheels + LD_LIBRARY_PATH wrapper for the systemd service 2026-05-25 15:39:13 -04:00

README.md

second-brain

A personal knowledge system built on a video/article extraction pipeline and an LLM-maintained wiki (inspired by the Karpathy LLM Wiki pattern).

What it does

  1. Pull — download YouTube videos or fetch web articles
  2. Transcribe — extract transcripts via Whisper (videos) or trafilatura (articles)
  3. Extract — single-shot Claude call produces structured notes per source
  4. Review — web UI to accept or reject extractions
  5. Compile — wiki compiler folds accepted extractions into a living Obsidian vault

Quick start

# Install dependencies
uv sync

# Copy and edit config
cp config/settings.toml config/settings.local.toml

# Queue a source
uv run second-brain add https://www.youtube.com/watch?v=...

# Run the pipeline
uv run second-brain process

# Review in the web UI
uv run second-brain serve

# Compile to wiki
uv run second-brain compile

Domains

Extractions are tagged by domain so the right prompt template is used:

Domain Focus
development Software, programming, systems
content Content creation, video production
business Entrepreneurship, marketing, ops
homelab Self-hosted infra, networking, DevOps

Extractor backends

Two backends, selectable via [extractor].backend in config/settings.toml:

  • cli (default) — shells out to claude -p --output-format json --json-schema .... Runs under your Max OAuth subscription, no per-token billing. The wrapper spawns the CLI in a throwaway tempfile.TemporaryDirectory and strips ANTHROPIC_API_KEY / ANTHROPIC_AUTH_TOKEN from the env so host CLAUDE.md, hooks, and settings don't leak in, and the subscription is used instead of the API key.
  • api — uses the anthropic Python SDK, requires ANTHROPIC_API_KEY. Install with uv sync --extra api (the SDK is an optional dependency).

Requirements

  • Python 3.12+
  • Either the claude CLI on PATH (default backend) or ANTHROPIC_API_KEY (api backend)
  • ffmpeg (for Whisper audio extraction)

In-flight work

  • Postgres + pgvector migration — SQLite is the current backing store but the project is moving to Travis's Postgres instance. Planning questions live in postgres-migration-planning.md; nothing has been migrated yet.