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

Agent Me

Agent Me is an open-source, self-hostable personal AI system that uses reviewable knowledge, retrieval and sequential agent roles to answer questions with supporting evidence. Its documented implementation combines a FastAPI backend and React interface, with Markdown knowledge and optional SQLite-backed personal workspace data.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Agent Me — 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 it when a personal AI needs to draw on maintained knowledge and make its evidence and workflow stages inspectable, rather than respond from a single prompt alone.

Who it is for

  • People building a personal assistant grounded in their notes, memories and decisions.
  • People who want to retrieve prior project context for ongoing work.
  • Developers exploring inspectable retrieval and multi-role AI workflows.

Documented uses

  • Retrieve relevant personal knowledge to answer a question.
  • Bring past project context into ongoing work.
  • Use recorded preferences and experiences as context for answers.
  • Inspect evidence, workflow stages and verification information behind a response.
Before you choose

Requirements & limits

The project is presented as open source under the MIT license. The documented self-hosted Docker Compose setup uses local modes without an API key; connecting an optional OpenAI-compatible provider requires an API key.

  • The current knowledge substrate is version-controlled Markdown, with an optional private workspace for SQLite-backed profile entries, chat transcripts and user-confirmed memories.
  • The default Docker configuration uses local extractive and collaboration modes; only the chat endpoint is described as using an optional external provider.
  • The local toolchain lists Python 3.11+, Node.js 22+, uv, npm and Git; Docker Compose is an alternative documented setup path.
  • Automatic temporal reasoning, richer identity models, knowledge graphs and broader tool calling are described as future extensions, not current capabilities.

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

Start Agent Me with Docker Compose

Launch the documented local web application and API using the default configuration.

Before you start

  • Docker with the Compose plugin.

Steps

  1. Clone the Agent Me repository and change into its directory.

  2. Copy .env.example to .env.

  3. Run docker compose up --build.

  4. Open the web application at http://localhost:5173 or the API documentation at http://localhost:8000/docs.

Expected outcome

The local web application and API are started; the documented default modes require no API key.

Guide limitations

  • This guide covers startup only; it does not configure a personal knowledge corpus or an external model provider.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
9 October 2026
Original website title
jzjzzzzzzz/agent-me · Official homepage title · retained in its source language
How we review sourcesSuggest a correction