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
xming521/WeClone
WeClone is an end-to-end pipeline for turning a person's own chat history into a fine-tuned large language model that imitates their conversational style, then deploying that model as a chatbot. The workflow covers exporting chat logs from supported platforms (WeChat natively, with Telegram support and WhatsApp planned), cleaning and preprocessing the exported text, filtering out sensitive personal information before training, fine-tuning an open-weight LLM on the resulting dataset, and finally serving the tuned model through a bot integration so the "digital avatar" can hold conversations on the user's behalf. It also supports image-modal data in the chat history, so visual context from conversations can be folded into training rather than discarded. Because the fine-tuning and eventual deployment are both designed to run locally, the project emphasizes keeping the person's private conversational data and the resulting model under their own control rather than sending it to a third-party service. The target audience is individuals who want a personal assistant or companion bot that speaks in their own voice and references their own conversational habits, rather than a generic assistant persona. This sits adjacent to, but distinct from, general agent frameworks: WeClone's scope is the data pipeline from raw chat export to a deployed conversational bot, not a broader agentic toolkit with planning, tool use or multi-step task execution. It is implemented in Python, uses standard LLM fine-tuning tooling, and is popular in Chinese-language open-source communities, with most of its interface and examples bilingual (Chinese/English). Suitable for users comfortable running a local fine-tuning job and willing to supply their own exported chat data and compute.
https://github.com/xming521/WeClone
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.
wangzan101/Mika
Android AI assistant that operates phone apps and the web on a hidden background screen from a single spoken or typed instruction, while you keep using your phone normally.
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.