Skip to content
You signed in with another tab or window. to refresh your session.
You signed out in another tab or window. to refresh your session.
You switched accounts on another tab or window. to refresh your session.
π Welcome to AgentScope!
π ηζηζ¬v4
AgentScope is a production-ready, easy-to-use agent framework with essential abstractions that works with rising model capability and built-in support for finetuning.
We design for increasingly agentic LLMs. Our approach leverages the models' reasoning and tool-use abilities rather than constraining them with strict prompts and opinionated orchestrations.
Why use AgentScope?
- Simple yet powerful: start building your agents in 5 minutes with built-in ReAct agent, tools, skills, human-in-the-loop steering, memory, planning, realtime voice, evaluation, model finetuning, etc.
- Extensible: large number of ecosystem integrations for tools, memory and observability; built-in support for protocols such as MCP, A2A and agent skills; message hub for flexible multi-agent orchestration and workflows.
- Production-readyοΌdeploy and serve your agents locally, as serverless in the cloud, or on your K8s cluster with built-in OTel support and multi-language support.
From developing, observability to deployment, we provide an integrated suite of components:
- Copaw - Your Personal AI Assistant, supporting both local and cloud deployment.
- AgentScope - A flexible programming framework for building multi-agent applications with self-explanatory APIs.
- AgentScope-Runtime - Scalable deployment infrastructure for running agents reliably in production.
- AgentScope-Studio - Visual development environment for rapid prototyping, debugging, and monitoring your agents.
- AgentScope-Samples - A curated collection of ready-to-use agent examples and templates, from simple command-line tools to full-stack production-ready applications.
- Skills - A curated collection of skills around AgentScope ecosystem and CoPaw applications.
Popular repositories
Loading
-
Build and run agents you can see, understand and trust.
Python
23k
2.4k
-
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
14.4k
1.9k
-
An open-source Collaborative Multi-Agent OS for transparent, human-in-the-loop task coordination via Matrix rooms.
Shell
3.9k
432
-
ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.
Python
2.6k
213
-
AgentScope Java: Agent-Oriented Programming for Building LLM Applications
Java
2.4k
500
-
A production-ready runtime framework for agent apps with secure tool sandboxing, Agent-as-a-Service APIs, scalable deployment, full-stack observability, and broad framework compatibility.
Python
707
139
Repositories
Showing 10 of 19 repositories
-
agentscope-java
Public
AgentScope Java: Agent-Oriented Programming for Building LLM Applications
-
DojoZero
Public
A platform for running AI agents on realtime sport data and make predictions about game outcomes.
-
CoPaw
Public
Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.
-
-
HiClaw
Public
An open-source Collaborative Multi-Agent OS for transparent, human-in-the-loop task coordination via Matrix rooms.
-
-
OpenJudge
Public
OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards
-
agentscope
Public
Build and run agents you can see, understand and trust.
-
Trinity-RFT
Public
Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (LLM).
-
ReMe
Public
ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.
You canβt perform that action at this time.