OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Memory & RAG

BrainAPI

BrainAPI is a Python-based AI memory and retrieval layer that converts unstructured text into an event-centric knowledge graph. AI agents extract and connect facts, and natural-language queries return answers with traceable graph paths.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

BrainAPI — OpenViST project profile in Agent Memory & RAG.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use BrainAPI when an AI application needs to connect facts across records and retrieve answers through explicit relationships, rather than relying only on similarity-based retrieval.

Who it is for

  • Developers building AI agents that need persistent, graph-structured memory.
  • Teams creating question-answering or recommendation features from documents, notes, messages or events.

Documented uses

  • Transform unstructured records into connected facts about people, actions, dates and context.
  • Ask natural-language questions that require relationships across ingested information.
  • Inspect the graph path associated with a retrieved answer.
  • Use relationships extracted from content to support recommendations.
Before you choose

Requirements & limits

  • The documented local setup requires Python 3.11+; the TUI setup path also configures services and starts the API, MCP server, worker and console.
  • The documented development path uses Poetry and Make.
  • Docker deployment documentation offers a light profile with Postgres, DeepSeek and OpenAI embeddings, and a heavy profile with Neo4j, Milvus, Mongo and GCP/Azure.
  • BrainAPI’s event-centric graph and traceable retrieval paths distinguish its described approach from similarity-only retrieval.
  • The example demonstrates cross-record relationship questions, but does not establish that every answer will be correct.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up and start BrainAPI with its TUI

Initialize a BrainAPI installation and start its backing services, API, MCP server, worker, and console.

Before you start

  • Node.js/npm to install the brainapi-tui package.
  • Python 3.11 or later, as indicated by the repository README.
  • Complete the interactive setup wizard or provide its configuration flags.

Steps

  1. Install the TUI with the command below.

    Documented command
    npm install -g brainapi-tui

  2. Run brainapi init and complete the setup wizard; the command clones the project, installs dependencies, and configures services.

  3. Run brainapi start to start the backing services and BrainAPI components.

  4. Open the console at http://localhost:8000/console and log in using the BRAINPAT_TOKEN generated during setup.

Expected outcome

The README describes a local setup with the API at `http://localhost:8000`, the console at `http://localhost:8000/console`, and the MCP server at `http://localhost:8001/mcp`.

Guide limitations

  • The setup wizard configures services; the README does not specify universal provider credentials or service choices, which depend on configuration.
  • The console login requires the token generated during setup.
  • The documented startup command also starts backing services; flags to alter what starts are listed in the README.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
Lumen-Labs/brainapi2 · Official homepage title · retained in its source language
How we review sourcesSuggest a correction