AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompare
Home/
Multi-Agent/
agentao
agentao logo

agentao

Active·★ 310·MIT·Updated 2026-10-20
★ Hidden Gem

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.

agentao sits in the Multi-Agent category, so it is usually better judged by workflow fit, deployment style, and team needs than by isolated features alone. Based on the available metadata, it leans most clearly toward Robust Governance: Features include tool confirmation, four permission modes (read-only, workspace-write, full-access, plan), and macOS sandbox execution.. A representative use case is Embedding AI agent capabilities into existing Python applications or frameworks.. The listed license is MIT. GitHub stars are currently 309. Relevant tags include Agent Runtime, Python.

© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.

Guides

This write-up is based on the project's README and public repository data. We have not hand-tested the tool.

#Agent Runtime#Python#LLM Agent#Governance#Local-first#Embeddable#CLI#Plugins
$ Install
$ pip install 'agentao[cli]'
↗ Visit site★ GitHub
01

Features

01Robust 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.
02

Why choose it

+Robust Governance: Features include tool confirmation, four permission modes (read-only, workspace-write, full-access, plan), and macOS sandbox execution.
+Persistent Memory: SQLite-backed memory with user/project scopes, automatic recall, and Jieba Chinese segmentation for enhanced context.
+Embedding AI agent capabilities into existing Python applications or frameworks.
+Supports 5 platforms or runtime environments.
03

Trade-offs

!The final decision should still be made through side-by-side comparison with similar tools.
04

Compatibility

Python
Runtime
Verified via docs
OpenAI API
LLM Provider
Verified via docs
Anthropic API
LLM Provider
Verified via docs
OpenAI-compatible APIs
LLM Provider
Verified via docs
macOS
OS
Verified via docs
05

Quick start

1
$ pip install 'agentao[cli]'
06

Use cases

↳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.
07

Alternatives

⚡Top VS:
VSagy-mcp★25→VSbub★1.7k→VSomk★148→VStalon

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Compatibility05Quick start06Use cases
★79
→
agy-mcp logo
agy-mcp★ 25
Use Google Antigravity (agy) as an agent backend from Claude Code / OpenAI Codex / Cursor / any MCP client. MCP server with 10 typed tools + Skill bundles, hybrid backend, capability detection, long-task supervisor, worktree-isolated execute.
VSCompare→
bub logo
bub★ 1.7k
Bub it. Build it. A tiny agent runtime, composable with plugins.
VSCompare→
omk logo
omk★ 148
Evidence-gated runner for Codex, Claude Code, OpenCode, and local coding agents. Routes tasks into scoped DAG lanes with replayable artifacts.
VSCompare→
talon logo
talon★ 79
🦅 Multi-platform agentic AI harness — runs on Telegram, Discord, Teams & Terminal with a pluggable backend (Claude, Kilo, OpenCode, Codex, OpenAI Agents), full MCP tool access, and persistent background agents (Goals, Heartbeat, Dream).
VSCompare→
openmake_llm logo
openmake_llm★ 43
Open-source, self-hosted AI workspace for local and open-weight LLMs with vLLM, LiteLLM, autonomous agents, MCP tools, deep research, artifacts, and BYOK.
VSCompare→
Agentflow logo
Agentflow★ 27
Production-grade framework for building multi-agent AI systems. Graph-based orchestration, LLM-agnostic (OpenAI, Google GenAI, Anthropic), 3-layer memory (Redis cache + Postgres + vector store), live agents, parallel tool execution, and native MCP. Ships a full ecosystem: backend, REST API + CLI, TypeScript SDK, and React playground
VSCompare→
Microsoft AutoGen logo
Microsoft AutoGen★ 61.5k
A framework that enables the development of LLM applications using multiple agents that can converse with each other to solve tasks.
VSCompare→
CrewAI logo
CrewAI★ 60.0k
Framework for orchestrating role-playing, autonomous AI agents. By working together, your Crew can tackle complex tasks.
VSCompare→
See all alternatives →
07
Alternatives
jin-bo /
agentao
↗

Local-first, governed AI agent runtime for Python — embed it in your app, or run it as a CLI or ACP server. Permissions, MCP, memory and audit replay built in.

310MIT
Last commit3d ago
StatusActive
CategoryMulti-Agent
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit