vellum-ai/vellum-assistant

An AI Assistant that’s easy to setup, does your work 24/7, knows your preferences and gets better over time.

What it solves

Vellum Assistant is a personal AI assistant designed to be ready-to-use out of the box, eliminating the long setup and iterative trial-and-error typically associated with configuring personal AI agents. It provides a persistent, evolving memory system and cross-platform accessibility across multiple channels.

How it works

The system uses a sophisticated memory architecture featuring eight distinct types of memory (episodic, semantic, procedural, emotional, prospective, behavioral, narrative, and shared) with hybrid dense and sparse retrieval. It maintains a user's identity and behavioral patterns in files like SOUL.md and NOW.md for current focus.

To interact with the user, it operates across various channels (macOS, Windows, iOS, Web, Voice, Email, Telegram, Slack, Twilio) and can be hosted either as a managed service on the Vellum Platform or self-hosted locally. It supports a wide range of LLM providers including Anthropic, OpenAI, Google Gemini, and local models via Ollama.

Who it’s for

Individuals seeking a highly personalized AI assistant that remembers context across different devices and apps, and those who want a professional-grade agentic system without the manual maintenance of markdown files or SQLite databases.

Highlights

  • Advanced Memory: Eight memory types with source attribution, deduplication, and local embeddings by default.
  • Proactivity: Hourly checks of notes to notify the user about unfinished tasks or upcoming deadlines.
  • Security: Sandboxed tool execution, permission-gated computer use (files, browser, commands), and isolated credential management.
  • Extensibility: Support for dynamic "skills" via SKILL.md and TOOLS.json plugins.
  • Broad Integration: Native OAuth support for platforms like Notion, Google, HubSpot, and Linear.

Related

  • Project
    beilusaiying/always-accompany

    A multi-purpose AI agent framework focused on context and attention mechanisms, providing layered memory and dynamic retrieval for long-term companionship, coding, and work.

  • Project
    AlphaAvatar/AlphaAvatar

    A self-hostable framework for creating proactive, multimodal personal AI assistants with long-term memory, persona tracking, and plugin-based tool integration.

  • Project
    Mirix-AI/MIRIX

    A multi-agent personal assistant that builds long-term memory through screen observation and natural conversation, featuring a specialized six-component memory system.

  • Project
    hhyqhh/inno-agent

    Inno Agent is an open‑source personal learning AI built on the Pi coding‑agent SDK. It adds three memory layers (learner profile, wiki, session logs), a natural‑language scheduler, IM channel support (Feishu/WeChat), and an in‑browser practice lab. Available as an Electron desktop app, a React web UI, or a terminal CLI, it works with any OpenAI‑ or Anthropic‑compatible model and can be extended via a skill hub. The project is MIT‑licensed and includes Docker, sandboxing, and a session‑replay showcase.

  • Project
    fuyuxiang/echo-agent

    Echo Agent is an open‑source, self‑hosted AI‑agent runtime that provides long‑term memory, automatic skill extraction/evolution, and pluggable tool integration. It can run interactively in a terminal, as a long‑living Gateway service with a web dashboard and API, or be embedded in a desktop application (EchoAgent Desktop). The core runtime manages the agent loop, session context, model routing, permissions, and automation channels, while the memory system recalls past facts and the evolution system turns execution traces into reusable Skills. Install via `pip install "echo-agent[all]"`, configure an LLM API key, and start with `echo-agent run` or `echo-agent gateway`.