Kkkirito-123

Kkkirito-123 / ZLAgent

Public

IM-first personal AI assistant for WeChat / WeCom / Webhook. Built-in long-term memory, skill system, GraphRAG, MCP tools. FastAPI + PostgreSQL/pgvector + Neo4j + Redis. Docker one-click. | 面向个人的 IM 优先 AI 助理,具有类似于hermes的记忆系统以及openclaw的工具使用能力，已经支持微信 / 企微 / Webhook；内置长期记忆、技能、GraphRAG、MCP 工具；FastAPI + pgvector + Neo4j + Redis，Docker 一键部署。

12
0
75% credibility
Found May 17, 2026 at 12 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

ZLAgent is an AI assistant platform that runs inside messaging apps like WeChat. It understands what you ask, pulls in relevant memories about you, picks the right skills to use, and executes tasks using built-in or plug-in tools. The system builds a knowledge map from your conversations, caches frequently-asked answers for speed, and can run scheduled tasks. You interact entirely through chat — no dashboards or configuration screens needed. It supports Docker one-click deployment and extends through the MCP tool standard.

How It Works

1
🎉 Discover ZLAgent

You find a smart assistant that lives inside your favorite chat app, ready to help with daily tasks like research, planning, and scheduling.

2
📦 Install with one click

You use Docker to launch ZLAgent and its supporting services — everything sets up automatically on your computer.

3
🔑 Connect your AI brain

You enter your AI service details so the assistant can think and respond to your messages.

4
📱 Link to your chat app

You scan a QR code with your phone to connect ZLAgent to your WeChat, so your conversations become the interface.

5
Start chatting
🧠
It remembers your preferences

The more you chat, the better it learns about your habits and likes.

🔧
It uses tools when needed

It searches the web, reads files, or schedules tasks automatically.

6
🧩 Add new abilities

You can say 'I need a tool for checking stocks' and it finds and installs new capabilities on its own.

✨ Your personal AI companion

From morning briefings to travel plans to research summaries, your AI assistant handles it all — quietly learning and improving over time.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 12 to 12 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is ZLAgent?

ZLAgent is an IM-first personal AI assistant that runs inside WeChat, WeCom, or custom webhooks. Built in Python with FastAPI, it combines long-term memory, a skill system, GraphRAG, and MCP tool support into a single deployable stack. The system handles paper research, travel planning, scheduled tasks, and knowledge organization through natural conversation.

Why is it gaining traction?

The project solves a real pain point: turning a personal LLM into a persistent assistant that remembers preferences across sessions. Unlike basic chatbot wrappers, it layers three knowledge systems -- short-term context, wiki-style caches, and Neo4j-powered knowledge graphs -- so answers improve over time. The Docker setup spins up PostgreSQL, Neo4j, and Redis alongside the agent with one command, eliminating the infrastructure headaches that kill side projects. MCP tool support means it can pull in external capabilities without rebuilding the core.

Who should use this?

Solo developers who want a research or productivity assistant running in WeChat. Researchers tracking papers and citations. Anyone tired of re-explaining context to AI tools every session. Not suitable for teams needing multi-user access control or high-throughput production systems.

Verdict

ZLAgent demonstrates sophisticated architecture for a 12-star project, but that visibility is the honest concern: with a 0.75% credibility score, it has not yet proven itself at scale. The documentation is thorough and the Docker setup lowers the barrier to entry, which helps. Worth experimenting with if you want a personal assistant with genuine memory, but treat it as an active development project rather than a production-grade system.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.