SymbolicAI explores a neurosymbolic approach to large language models.
Open source
24 alternativesAgentScope
AgentScope helps developers build and run AI agents with tools for understanding their behavior.
About AgentScope
AgentScope is an open-source framework for building and running AI agents with language models. It is published as a GitHub repository with Python code, documentation, and examples. The project focuses on making agent reasoning, tool calls, and outputs visible through a unified event system.
With it, developers can compose agents from building blocks such as a reasoning-acting loop, tool management for Python tools and MCP servers, and connections to models from several providers. It also provides context handling, memory backends, permission checks with human confirmation, and isolated execution in local or container-based sandboxes. Installation is via pip or from source, and requires Python 3.11 or higher.
AgentScope suits developers building Python-based agents who want to inspect behavior and manage tools, models, and multi-agent workflows.
Key features
- ReAct agent loop with structured output and tool use
- Toolkit for Python tools, MCP servers and skills
- Works with models from OpenAI, Anthropic, Gemini and others
- Context handling with compaction and memory injection
- Permission controls with confirmation for tool calls
- Isolated code execution in Docker and other sandboxes
Best for: Python developers building AI agents who need to observe reasoning and tool use.
Good for
- Open source with documentation and examples
- Supports multiple model providers
- Includes event streaming for reasoning and tool calls
Watch out for
- Requires Python 3.11 or higher
- Requires code setup and model API credentials
AgentScope at a glance
- Category
- AI & Machine Learning › AI Agents & Automation
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
AgentScope alternatives
Tools and sites you could use instead, ranked by how closely they match.
Dust provides a platform for teams to build custom AI agents for work tasks.
Open source
24 alternatives
An LLM-powered repository agent designed to assist developers and teams in generating documentation and understanding repositories quickly.
Open source
24 alternatives
AgentField lets developers build, run, and scale AI agents as APIs and microservices.
Open source
24 alternatives
This repository provides code for building agents controlled by large language models.
Open source
24 alternatives
AG2 offers open source tools for building and coordinating AI agent systems.
Open source
24 alternativesPopular in AI Agents & Automation
Well-known listings from the same topic.
Simsim.aiMaya AI.smartmaya.aiMakeformsmakeforms.ioAgent Skillsagentskills.ioGenFuse AIgenfuseai.comBeambeam.ai
AgentScope FAQ
What is AgentScope?
AgentScope is an open-source framework for building and running AI agents with language models and tools.
How do you install AgentScope?
You can install it with pip using uv pip install agentscope, or clone the GitHub repository and install from source. It requires Python 3.11 or higher.
Is AgentScope open source?
Yes, it is published as a public GitHub repository with source code, documentation, and examples.
Which models does AgentScope work with?
It lists support for models from providers including OpenAI, Anthropic, Gemini, DashScope, DeepSeek, Moonshot, Volcengine, xAI, and Ollama.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.