Skip to content

BrainAPI is a knowledge graph–powered AI memory layer that transforms unstructured data into structured knowledge, enabling intelligent search, recommendations, and contextual memory for AI agents and applications.

docs: document hybrid brainapi init flags in README

Cursor Agente4408c602c1b
diff --git a/README.md b/README.md
index 882429b..3cc7e5f 100644
--- a/README.md
+++ b/README.md
@@ -63,11 +63,11 @@ That trace is the difference. Not a nearest-neighbour guess — a **reasoned, wa
## 🏃 Quickstart (fastest way to run it)
-The quickest way to get BrainAPI running is the **`brainapi` TUI** — an interactive CLI that clones the project, sets up a Python environment, walks you through configuration, starts the backing services, and launches everything for you. Pick the defaults and you'll be up in a few minutes.
+The quickest way to get BrainAPI running is the **`brainapi` TUI** — a CLI that clones the project, sets up a Python environment, configures services, starts backing services, and launches everything for you. Run the interactive wizard, or pass flags to skip prompts (hybrid / non-interactive).
```sh
npm install -g brainapi-tui
-brainapi init # clone, install deps, interactive setup → choose "Use default settings"
+brainapi init # clone, install deps, setup wizard (or pass flags to skip prompts)
brainapi start # backing services + API + MCP + worker + console
```
@@ -83,7 +83,7 @@ Log in to the console with the `BRAINPAT_TOKEN` generated during setup. That's i
| Command | What it does |
| ----------------- | ------------------------------------------------------------------------------------------- |
-| `brainapi init` | Clone the repo into `~/.brainapi/source/`, create a venv, run the setup wizard |
+| `brainapi init` | Clone into `~/.brainapi/source/`, create a venv, run setup (flags skip individual prompts) |
| `brainapi start` | Bring up backing services and run the API, MCP server, and Celery worker (Ctrl-C stops all) |
| `brainapi config` | Re-open the setup wizard to change one area (databases, models, pipeline, plugins, …) |
| `brainapi doctor` | Check Python, Docker, Ollama, cloud credentials, and configured services |
@@ -91,7 +91,7 @@ Log in to the console with the `BRAINPAT_TOKEN` generated during setup. That's i
Running any command (except `help`) before `init` will run `init` first automatically.
-**Useful `brainapi start` flags:** `--pipeline accurate|lightweight`, `--no-services`, `--no-api` / `--no-mcp` / `--no-worker`, `--only api,mcp,worker`. Full reference → [`tui/README.md`](tui/README.md).
+**Useful `brainapi init` flags:** `--defaults`, `--vector-db`, `--models-mode`, provider keys/models, `--brainpat-token`, `--no-plugins`, `--no-start-services` (any passed value skips that wizard prompt). **`brainapi start` flags:** `--pipeline accurate|lightweight`, `--no-services`, `--no-api` / `--no-mcp` / `--no-worker`, `--only api,mcp,worker`. Full reference → [`tui/README.md`](tui/README.md).
> The TUI installs into `~/.brainapi/` (source, venv, `.env`, and `state.json`) — separate from any git clone. Override with `BRAINAPI_HOME`, `BRAINAPI_REPO_URL`, or `BRAINAPI_BRANCH`.
diff --git a/tui/README.md b/tui/README.md
index 5cd5072..acb748c 100644
--- a/tui/README.md
+++ b/tui/README.md
@@ -55,11 +55,12 @@ brainapi init \
| Auth / plugins | `--brainpat-token`, `--plugin <name[@version]>` (repeatable), `--no-plugins` |
If any config flag is present (or `--defaults`), the “Use default settings?” question is skipped.
+
## Commands
| Command | Description |
| ----------------- | -------------------------------------------------------------------------------------------------- |
-| `brainapi init` | Full bootstrap: clone the repo, create a Python venv, install deps, and run the interactive setup. |
+| `brainapi init` | Full bootstrap: clone the repo, create a venv, install deps, and run setup (flags skip prompts). |
| `brainapi start` | Start docker compose containers for the chosen services and launch the API. |
| `brainapi config` | Re-run the interactive flow and rewrite `.env`. |
| `brainapi doctor` | Check that Python, Docker, Ollama, GCP credentials, and configured services are reachable. |
@@ -87,7 +88,7 @@ If any config flag is present (or `--defaults`), the “Use default settings?”
## Configuration
-The interactive flow asks:
+The interactive flow asks (any matching CLI flag skips that prompt):
1. Use default settings? (NetworkX + Postgres + pgvector + remote GCP Vertex)
2. Otherwise: Vector DB → Data DB → Graph DB → Models mode