From fe4eb7a0a89505fff6f5a4bee1a4524cd4a919db Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=96=B9=E5=BA=94?= Date: Thu, 27 Nov 2025 17:34:36 +0800 Subject: [PATCH] Add the description document about the op in working memory. --- docs/work_memory/message_offload.md | 26 +++++++++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-) diff --git a/docs/work_memory/message_offload.md b/docs/work_memory/message_offload.md index 063f8a5d..cff8e670 100644 --- a/docs/work_memory/message_offload.md +++ b/docs/work_memory/message_offload.md @@ -144,6 +144,7 @@ After Message Offload (100 tool calls): ReMe has fully implemented the above-mentioned message offload and reload mechanisms, inspired by [Context Engineering for AI Agents with LangChain and Manus](https://www.youtube.com/watch?v=6_BcCthVvb8). The implementation provides two core operation primitives: + ### (1) Message Offload Operations Operations for intelligently reducing context size through compaction and compression strategies. @@ -168,4 +169,27 @@ Key features: - Support for both absolute and relative paths - Complete working examples in test files -Both operation primitives are production-ready and can be integrated into your agent workflows. Refer to the linked documentation for API specifications, parameter details, and practical usage examples. \ No newline at end of file +Both operation primitives are production-ready and can be integrated into your agent workflows. Refer to the linked documentation for API specifications, parameter details, and practical usage examples. + +## 3. Integrating Working Memory with Agents + +ReMe provides a complete tutorial on integrating working memory mechanisms with agent workflows. This integration enables agents to handle long-running tasks efficiently while maintaining optimal context window usage. + +### Resources + +📖 **Tutorial Guide**: [Working Memory Quick Start](../cookbook/working/quick_start.md) +- Step-by-step guide on integrating working memory with agents +- Configuration examples and best practices +- Real-world usage scenarios + +💻 **Implementation Reference**: [react_agent_with_working_memory.py](../../cookbook/working_memory/react_agent_with_working_memory.py) +- Complete implementation of a ReAct agent with working memory +- Shows how to configure message offload and reload operations +- Production-ready code template + +🚀 **Demo Application**: [work_memory_demo.py](../../cookbook/working_memory/work_memory_demo.py) +- Runnable demonstration of working memory in action +- Practical examples with different scenarios +- Easy to adapt for your own use cases + +These resources provide everything you need to add intelligent working memory management to your agent applications. \ No newline at end of file