personal AI agent framework / self-hosted assistant
An ultra-lightweight, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat app integrations.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
Python personal AI assistant with multi-chat-app support and easy deploy; direct nanobot replacement.
Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.
Python multi-channel assistant with memory/tools/self-evolution; direct nanobot alternative with one-line install.
Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-model, multi-channel. Lightweight, extensible, one-line install. (formerly chatgpt-on-wechat)
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Python multi-agent SDK without UI or chat integrations; use when you need a minimal OpenAI-compatible agent library.
A lightweight, powerful framework for multi-agent workflows
LangChain-based harness; use when you need deep ecosystem integration rather than a turnkey assistant.
The batteries-included agent harness.
Google's code-first agent toolkit with evaluation focus; use for building/testing agents from scratch.
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
Meta-harness orchestrating external CLIs (Claude Code, Codex); use when you need to manage multiple coding agents.
Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.
Java enterprise workflow platform; use for commercial Java environments, not Python personal assistants.
Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.
Go personal AI assistant with computer/browser use; choose if you prefer Go and native concurrency.
⚡️next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting computer-use, browser-use and coding agent, demo: https://demo.openagentai.org
Java distributed agent framework; use for long-running production agents in Java.
Build distributed, production-grade, long-running agents.
Memory-first self-improving harness on EverOS; use for deep research/reasoning, not lightweight chat.
The memory-first, self-improving agent harness built on EverOS, with MiroThinker-powered deep research and reasoning.
Go reimplementation of OpenClaw with multi-tenant isolation; choose for Go and secure multi-agent deployments.
GoClaw - GoClaw is OpenClaw rebuilt in Go — with multi-tenant isolation, 5-layer security, and native concurrency. Deploy AI agent teams at scale without compromising on safety.
TypeScript platform for managing AI agents; use if you're building in Node.js ecosystem.
Evo AI is an open-source platform for creating and managing AI agents, enabling integration with different AI models and services.
Rust-core agent framework with Python wrapper; use for high-performance enterprise multi-agent workflows.
GraphBit is the world’s first enterprise-grade Agentic AI framework, built on a Rust core with a Python wrapper for unmatched speed, security, and scalability. It enables reliable multi-agent workflows with minimal CPU and memory usage, making it production-ready for real-world enterprise environments.
Go event-driven agent framework with MCP; use for Go-based MCP-centric agents.
Open-source Agentic AI framework in Go for building, orchestrating, and deploying intelligent agents. LLM-agnostic, event-driven, with multi-agent workflows, MCP tool discovery, and production-grade observability.
LangGraph-based orchestrated agent loops with Dify DSL support; use for graph workflows, not personal assistant.
Graph-Orchestrated Agent Loop — a production-grade framework on LangGraph. Combine workflow graphs and agent loops, transpile Dify DSL to runnable code, swap wire protocols (Dify/OpenAI).
Self-improving agent from NousResearch; use if you want an agent that adapts over time, lacks built-in chat apps.
The agent that grows with you
Python framework for autonomous AI workforce; use for multi-agent task execution rather than personal assistant.
PraisonAI 🦞 — Hire a 24/7 AI Workforce. Stop writing boilerplate and start shipping autonomous self-improving agents that research, plan, code, and execute tasks. Deployed in 5 lines of code with built-in memory, RAG, and support for 100+ LLMs.
Managed TypeScript platform for deploying agents/workflows; use if you want cloud-managed event-driven agents.
Trigger.dev – build and deploy fully‑managed AI agents and workflows
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
Local-first desktop/TUI agent workspace; a GUI app, not embeddable in your codebase.
Local-first AI agent workspace for coding, writing, design, research, and automation — one runtime for desktop GUI and TUI.
Desktop agent app built on OpenClaw; use as a ready-made end-user assistant, not a framework.
Open-source, desktop-grade AI agent that gets real work done — data analysis, slides, docs, video & web research. Built on OpenClaw; runs tools on your real desktop and takes commands from your phone via WeChat, Feishu, DingTalk & Telegram.
Consumer smart assistant app; end-user tool, not a development framework.
🐬DeepChat - A smart assistant that connects powerful AI to your personal world
Self-hosted AI workspace application; use as a turnkey workspace, not a library you integrate.
Self-hosted AI workspace.
These projects were analysed and named nanobot among their alternatives. The relationship is not symmetric — how nanobot rates them is a separate judgement, made when nanobot is analysed in its own right.
calls nanobot “Python, MIT, ultra-lightweight self-hosted personal agent with WebUI and memory; choose for a minimal footprint without Hermes's full skill loop.”
The agent that grows with you
calls nanobot “choose if you want an even smaller, self-hosted agent framework with WebUI and multi-agent workflows, easy to embed.”
Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-model, multi-channel. Lightweight, extensible, one-line install. (formerly chatgpt-on-wechat)
calls nanobot “Choose when you want a lightweight self-hosted personal AI agent with WebUI, memory, and MCP rather than a general multi-agent framework.”
A lightweight, powerful framework for multi-agent workflows
calls nanobot “lighter-weight personal agent framework with WebUI; suitable for self-hosted personal use, not enterprise orchestration.”
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
calls nanobot “Self-hosted personal assistant with WebUI and chat; choose it for an ultra-lightweight ready-to-use assistant.”
The batteries-included agent harness.