MaiBot

Active

GitHub Python GPL-3.0

Description

An LLM-based intelligent agent as a digital lifeform that values warmth, authenticity and genuine connection, with long-term memory and personalized conversation.

Key Features

Pursues natural human conversational style, rejecting mechanical GPT-like replies with casual varied chat
Imitates different speaking styles in group conversations, autonomously learns slang and in-group language
Long-term memory based on psychology personality theory, continuously building understanding of user preferences
Intelligent awareness of chat atmosphere, knowing when to speak and when to stay quiet
Powerful plugin system and event API with virtually unlimited extension possibilities
Supports QQ group chat and other social platforms as a digital lifeform for genuine interaction

Use Cases

💡 Companion digital lifeform in QQ/WeChat group chats providing warm and authentic conversation

💡 Personalized chat partner that adapts interaction style based on user personality and preferences

💡 Plugin developers building custom interaction scenarios and functional extensions

💡 Intelligent participation in multi-person social scenarios, naturally blending into group conversations

Strengths & Limitations

✅ Strengths

• Actively maintained, recent updates
• High community interest (5.9k stars)

⚠️ Limitations

• Restrictive license (GPL-3.0)

Quick Start

Download the latest release from GitHub Releases and follow the deployment guide at docs.mai-mai.org/manual/deployment/. Requires Python 3.10+, primarily runs on the QQ platform. Join community QQ groups for technical support.

Visit GitHub Visit Website

Related Projects

MemMachine

3.2k · Python

Active A

Universal memory layer for AI Agents providing scalable, extensible, and interoperable memory storage and retrieval to streamline agent state management for autonomous systems.

pythonagentmemory +2

· Three-tier memory: episodic (graph), profile (SQL), and working memory
· LLM-agnostic design supporting OpenAI, Anthropic, Bedrock, Ollama
· Integrations with LangChain, LangGraph, CrewAI, LlamaIndex, and n8n

View on GitHub

MaxKB

22.7k · Python

Active A+

MaxKB is an open-source knowledge base Q&A and agent building platform powered by LLMs, with vector retrieval, workflow orchestration, and multi-model support out of the box.

knowledge-baseragchatbot +3

· RAG Pipeline — Document upload and online crawling with automatic splitting and vectorization to reduce hallucinations
· Agentic Workflow — Powerful workflow engine, function library and MCP tool-use for complex business scenarios
· Zero-code Integration — Seamlessly integrate into third-party business systems for smart Q&A capabilities

View full details → View on GitHub

MemAgent

1.1k · Python

Stale B

A MemAgent framework that can extrapolate to 3.5M context tokens, along with a training framework for RL training of any agent workflow.

memoryagentrag +2

· Ultra-Long Context Processing: Extrapolate from 8K training context to 3.5M tokens with performance loss under 5%
· Reinforcement Learning Driven: Trained with RLVR (Reinforcement Learning from Verifiable Rewards), extends DAPO algorithm for end-to-end multi-turn conversation optimization
· Linear Time Complexity: Breaks through computational bottlenecks in long-text processing with linear resource scaling

View on GitHub

Memori

16.3k · Python