mem0ai/mem0
Mem0 is an open-source memory layer that enhances AI agents and assistants with personalized, adaptive memory capabilities for improved context-aware interactions across various applications.
Awesome AI Agents › Virtual Assistants
vellum-ai/vellum-assistant
Vellum Assistant is an open-source personal AI assistant, built by Vellum, that aims to deliver a working personal agent out of the box rather than requiring the reader to assemble one. Its distinguishing feature is a typed memory system with eight categories: episodic, semantic, procedural, emotional, prospective, behavioural, narrative and shared. Each category has its own staleness window and is served by hybrid dense and sparse retrieval, with isolation per user and per channel. Structured items such as identity facts, preferences, projects and events are extracted from conversations with source attribution and deduplication, and embeddings run locally by default. Personality lives in a SOUL.md file that the assistant writes itself during onboarding by observing how the user communicates, supported by a per-user journal of reflections and a NOW.md scratchpad tracking current focus and open threads. The assistant is proactive: every hour it re-reads its notes, looks for anything unfinished or approaching a deadline, and messages the user through the appropriate channel without interrupting an active conversation. Security is enforced through actor identity resolved once and applied everywhere, with guardian, trusted and unknown levels; unknown actors cannot read memory, invoke tools or escalate. Credentials are held in a separate process and never reach the model, every tool call runs in a sandbox, and the default posture is deny. Computer use is permission-gated with grant-once, ten-minute or always options, letting the assistant read and edit files, run commands and drive a browser on the real machine. Skills are plugins defined by SKILL.md and TOOLS.json that inject tools and prompt sections at runtime. Channels include macOS, iOS, web, voice, email, Telegram, Slack and Twilio, with OAuth for Slack, Notion, Google, HubSpot, Linear, Discord, Twitter and Telegram. It runs managed on the Vellum platform or self-hosted, with a desktop app and a TypeScript CLI installed through bun.
https://github.com/vellum-ai/vellum-assistant
Also in Virtual Assistants
CherryHQ/cherry-studio
Cherry Studio is a cross-platform desktop client that supports multiple large language model providers, offering extensive AI assistant features, document processing, and practical productivity tools in an open-source environment.
tinyhumansai/openhuman
Local-first personal AI harness combining a persistent memory brain, multi-agent orchestration, and autonomous web and data research.
khoj-ai/khoj
Khoj is a self-hostable personal AI platform that transforms any local or online large language model into a customizable, autonomous AI assistant for research, automation, and document retrieval.
kortix-ai/suna
Suna is an open-source generalist AI assistant that automates real-world tasks through natural conversation, combining browser automation, file management, web crawling, and API integrations in a secure, modular architecture.
gptme/gptme
gptme is a versatile personal AI assistant that operates in your terminal, equipped with tools for coding, file editing, web browsing, and vision, providing a powerful local alternative to popular AI agents for diverse knowledge work.
CherryHQ/cherry-studio-app
Cherry Studio App is the official mobile application that enables powerful AI Large Language Models interaction on iOS and Android devices, supporting multiple LLM providers and offering tools for conversation management and data migration.
cosmicstack-labs/mercury-agent
Personal AI agent in TypeScript that runs continuously from CLI, Telegram or web with permission-gated tools, SQLite-backed long-term memory, token budgets and installable skills.