install

Capturing in 60 seconds.

Install the Claude Code plugin, capture once — then come back to a populated resume card. No account, and capture → resume needs no key at all; the loopback backend keeps everything on your machine.

1

Install the plugin

No venv, no path editing — the plugin's MCP server bootstraps its own environment on first run.

$ /plugin marketplace add anthonysuherli/br8n
$ /plugin install br8n@br8n

Then reload the session so the MCP server connects.

2

Capture, then come back

Capture and resume work with no key at all — snapshots are stored without embeddings.

/br8n:capture  ·  /br8n:pickup
3

Add keys for search & explore (optional)

Semantic search needs an embedding key — AI_GATEWAY_API_KEY or OPENAI_API_KEY. The explore / gap-fill pipeline needs that plus TAVILY_API_KEY for web search. Without them, capture and resume still work.

4

Sanity-check the setup (optional)

Reports your Python version, which backend tier is configured, whether sqlite-vec loads, whether the DB path is writable, and whether the embedding and explore keys are present. Anything missing is named explicitly.

$ python -m br8n.api.main --check
5

Or run the API / MCP server directly

The blessed launcher binds 127.0.0.1 and turns auth off — safe because it never leaves loopback. The MCP entry point serves any MCP-compatible client or agent — exposing br8n_capture, br8n_resume, br8n_explore.

$ BR8N_BACKEND=local python -m br8n.api.main
serving on http://127.0.0.1:8002 — loopback only
$ BR8N_BACKEND=local python -m br8n.interfaces.mcp.server
The free tier is local-first and verifiable: SQLite at ~/.br8n/brain.db, bound to loopback, no account. Capture and resume need no key; search and explore need one. Your code context never leaves your laptop.
Working on br8n rather than with it? Clone the repo, then cd backend and pip install -e ".[dev]" into a Python 3.11 venv. That's the contributor path, not the try-it path.
Cloud is designed, not yet built. br8n launches free-first. The paid differentiators — cross-machine sync, cross-repo search, team sharing, managed keys — are on the roadmap, not shipping today.

Under the hood, the cloud path swaps the local SQLite store for a hosted Supabase backend behind the same get_store() seam, with a login for a real per-request token. When it's ready, the same capture→resume loop and the same surfaces will simply follow you across machines — no change to how you work.

Want it when it lands? Start on the free tier today — switch to Free / Local ›