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
tinyhumansai/openhuman
OpenHuman is an early-beta, local-first personal AI system built around three pieces: a memory layer, an agent orchestrator, and a research component. The memory layer, called Memory Tree, compresses a user's data into scored Markdown trees stored locally in SQLite and mirrored as an editable Obsidian vault, avoiding an opaque vector-only store; an auto-fetch loop refreshes it roughly every 20 minutes from more than 100 OAuth-connected services such as Gmail, Notion, GitHub, and Slack, plus thousands of MCP servers and skills. The orchestrator runs durable, checkpointed agent graphs through the open-source tinyagents library: an agent proposes an automation called a Workflow, the user reviews it on a visual canvas before it is saved, and subsequent runs are trigger-driven and gated by approval; stuck agents can be steered mid-run, and halted ones report a root cause, with every run replayable at its real per-call cost. Long-term goals and durable per-thread to-dos are tracked with a shared kanban board attached to each conversation. A compression step called TokenJuice shrinks tool output before it reaches the model, cutting token usage by up to roughly 80% so that a memory this large stays affordable to query. OpenHuman ships as downloadable desktop installers, plus terminal installs via Homebrew, .deb, and AUR, rather than as a hosted service, keeping data and orchestration on the user's own machine. It is written primarily in Rust, distributed as open source, and was the top trending GitHub repository for nine consecutive days shortly after launch.
https://github.com/tinyhumansai/openhuman
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.
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.
moltis-org/moltis
A persistent personal AI agent server written in Rust and shipped as a single binary, with sandboxed tool execution, memory, voice, MCP support and messaging channels such as Telegram and Signal.