bub
★ 1.7k
vs
agentao
★ 310
bub vs agentao
bub: Bub is a small Python agent runtime built on agents.md and Agent Skills, where every stage of a turn is a pluggy hook that plugins can override. Context is rebuilt from append-only tape records, and the same pipeline serves the CLI, Telegram and custom channels.; agentao: Agentao is a governed agent runtime for Python, emphasizing local-first, private-first, and embeddable design. It provides comprehensive control over permissions, protocols, memory, plugins, and multi-session capabilities for AI agents.
01
TL;DR
bubDev Tooling · ★ 1.7k
Running an agent in a group chat shared by several people
agentaoMulti-Agent · ★ 310
Embedding AI agent capabilities into existing Python applications or frameworks.
02
Side-by-Side Comparison
Field
bubagentaoCategory
Dev Tooling
Multi-Agent
Stars
★ 1.7k
★ 310
License
Apache-2.0
MIT
Install Command
curl -fsSL https://bub.build/install.sh | bash
pip install 'agentao[cli]'
Updated
3d ago
3d ago
Open Source
Yes
Yes
Tags
agent-runtime, python, plugins
Agent Runtime, Python, LLM Agent
03
Features
bub01Turn pipeline where every stage, from resolve_session to dispatch_outbound, is a replaceable hook
02Tape context rebuilt from append-only records, easy to inspect and replay
03One runtime across CLI chat, one-shot runs and a Telegram gateway
04Agent Skills discovery and plugin packaging through Python entry points
agentao01Robust Governance: Features include tool confirmation, four permission modes (read-only, workspace-write, full-access, plan), and macOS sandbox execution.
02Persistent Memory: SQLite-backed memory with user/project scopes, automatic recall, and Jieba Chinese segmentation for enhanced context.
03Extensible Skills: Automatically discovered from local directories, installable from GitHub, and supports a `/crystallize` workflow for skill creation.
04Flexible Protocols: Implements MCP for tools (stdio, HTTP, SSE) and ACP (JSON-RPC) for full agents, with a comprehensive plugin lifecycle.
05Seamless Embedding: Offers a direct `Agentao(...)` constructor, event streams, active permissions management, and capability injection for integration.
04
Use Cases
bub↳Running an agent in a group chat shared by several people
↳Building a custom agent by overriding only the prompt or model stage
↳Experimenting with replayable, auditable agent context
agentao↳Embedding AI agent capabilities into existing Python applications or frameworks.
↳Developing and driving AI agents directly from the terminal using a comprehensive command-line interface.
↳Building custom AI agents with specific governance rules, persistent memory management, and flexible tool integration.
↳Creating and managing a library of reusable AI skills that can be installed and shared across different projects.
05
Best For
bubEssentialTrending
agentaoHidden Gem
FAQ
FAQ
What is the difference between bub and agentao?
Both bub and agentao are in the Dev Tooling category. bub has 1.7k stars, while agentao has 310 stars.
Which is better, bub or agentao?
The best choice depends on your use case. Choose bub if Running an agent in a group chat shared by several people, and agentao if Embedding AI agent capabilities into existing Python applications or frameworks..
Is bub free or open source?
Yes, bub is open source on GitHub (Apache-2.0).
Is agentao free or open source?
Yes, agentao is open source on GitHub (MIT).
Cloud Infrastructure
AdDeploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.
→