agentscope
Build and run agents you can see, understand and trust.
Explore AgentScope evaluation frameworks for agent benchmarking. Discover parallel benchmarking, sequential debugging, ACEBench, and custom metrics for robust AI agent evaluation.
How the Embedding Module in AgentScope Works: Vector Storage and Retrieval ExplainedUnderstand AgentScope's embedding module for seamless text to vector conversion. Discover efficient vector storage and retrieval with built-in caching to optimize API costs and reduce latency.
Stateful vs Stateless MCP Clients in AgentScope: Architecture and Usage GuideUnderstand stateful vs stateless MCP clients in AgentScope. Learn how each handles sessions for tool discovery and execution through explicit connect/close or automatic cleanup.
How to Implement Memory Compression in AgentScope for Long ConversationsImplement AgentScope memory compression to manage token limits and extend agent conversations. Automatically summarize old dialogue, preserving recent interactions for smooth, long-running chats.
What Are AgentScope Hooks and How They Integrate With AgentScope StudioDiscover AgentScope hooks, injection points for custom logic before and after agent operations. Learn how they integrate with AgentScope Studio for seamless workflow enhancement.
How to Deploy AgentScope Agents as a Serverless Service or on KubernetesDeploy AgentScope agents to serverless platforms or Kubernetes using the official Docker image. Learn how to package your agent code for easy deployment and scalability.
Session Module in AgentScope: Managing Conversation State PersistenceExplore the AgentScope Session module for seamless conversation state persistence. Learn how it manages state across JSON or Redis for robust conversation logic.
How AgentScope Supports Model Finetuning with Reinforcement Learning: A Complete Guide to the Tuner Sub‑PackageAgentScope enables model finetuning with reinforcement learning using its tuner sub-package. Learn how to leverage its components and the Trinity-RFT engine for efficient RL.
What Are Formatters in AgentScope and How Do They Shape Model Input/Output?Explore AgentScope formatters, adapter classes that transform Msg objects into LLM API payloads. Learn how they manage input/output, validation, multimodal content, and token limits.
How to Configure Token Counting and Usage Tracking in AgentScopeLearn to configure token counting and usage tracking in AgentScope. Leverage its pluggable architecture for seamless integration and OpenTelemetry tracing of chat usage metrics.
ReMe vs Mem0 Long-Term Memory in AgentScope: Architecture and Usage GuideExplore ReMe vs Mem0 long-term memory in AgentScope. Discover ReMe's structured cloud memory and Mem0's local vector store for semantic search.
How to Use the Tracing Module to Observe and Debug Agent Executions in AgentScopeDebug agent executions in AgentScope with the tracing module. Easily observe agent interactions by enabling and applying tracing decorators for comprehensive debugging.
Have a question about this repo?
These articles cover the highlights, but your codebase questions are specific. Give your agent direct access to the source. Share this with your agent to get started:
curl -s "https://instagit.com/install.md" 
Maintain an open-source project? Get it listed too →