From d9938c6a43e6ba437849b89688c457360b0af4ee Mon Sep 17 00:00:00 2001 From: "jinli.yl" Date: Wed, 22 Oct 2025 12:11:20 +0800 Subject: [PATCH] feat(docs): add tool memory documentation and update ReMe memory model - Introduce tool memory as a new memory type in ReMe framework - Update agent memory formula to include tool memory- Add comprehensive tool memory documentation with usage examples - Include tool memory API usage guides for Python, curl, and Node.js - Add tool memory benchmark results showing 14.88% improvement- Create new tool memory demo and benchmark resources - Update documentation structure to reflect three memory capabilities- Add TODO list with planned features including automatic tool exploration- Fix mermaid diagram numbering in tool memory documentation - Remove outdated latest updates section from main documentation - Update resource links to include tool memory references --- README.md | 4 +- README_ZH.md | 412 -------------------------------- docs/index.md | 190 +++++++++++++-- docs/todo.md | 25 ++ docs/tool_memory/tool_memory.md | 8 +- mkdocs.yml | 1 + 6 files changed, 199 insertions(+), 441 deletions(-) delete mode 100644 README_ZH.md create mode 100644 docs/todo.md diff --git a/README.md b/README.md index aa57e57f..db587c1a 100644 --- a/README.md +++ b/README.md @@ -1,5 +1,3 @@ -English | [**中文**](./README_ZH.md) -

ReMe Logo

@@ -551,6 +549,8 @@ You can find more details in [tool_bench.md](docs/tool_memory/tool_bench.md) and ## 📚 Resources - **[Quick Start](./cookbook/simple_demo)**: Get started quickly with practical examples + - [Tool Memory Demo](cookbook/simple_demo/use_tool_memory_demo.py): Complete lifecycle demonstration of tool memory + - [Tool Memory Benchmark](cookbook/tool_memory/run_reme_tool_bench.py): Evaluate tool memory effectiveness - **[Vector Storage Setup](docs/vector_store_api_guide.md)**: Configure local/vector databases and usage - **[MCP Guide](docs/mcp_quick_start.md)**: Create MCP services - **[Personal Memory](docs/personal_memory)**, **[Task Memory](docs/task_memory)** & **[Tool Memory](docs/tool_memory)**: Operators used in personal memory, task memory and tool memory. You can modify the config to customize the pipelines. diff --git a/README_ZH.md b/README_ZH.md deleted file mode 100644 index 3e3b15bb..00000000 --- a/README_ZH.md +++ /dev/null @@ -1,412 +0,0 @@ -中文 | [**English**](./README.md) - -

- ReMe Logo -

- -

- Python Version - PyPI Version - License - GitHub Stars -

- -

- ReMe (formerly MemoryScope)：为Agent设计的记忆管理框架
- Remember Me, Refine Me. -

- ---- -ReMe为AI智能体提供了统一的记忆与经验系统——在跨用户、跨任务、跨智能体下抽取、复用和分享记忆的能力。 - -``` -个性化记忆 (Personal Memory) + 任务经验 (Task Memory)= agent记忆 -``` - -个性化记忆能够"**理解用户偏好**"，任务记忆让agent"**做得更好**"， - ---- - -## 📰 最新动态 - -- **[2025-09]** 🎉 ReMe v0.1 - 正式发布，整合任务记忆与个人记忆。如果想使用原始的memoryscope项目，你可以在[MemoryScope](https://github.com/modelscope/Reme/tree/memoryscope_branch) - 中找到。 -- **[2025-09]** 🧪 我们在appworld, bfcl(v3) - 以及frozenlake环境验证了任务记忆抽取与复用在Agent中的效果，更多信息请查看 [appworld exp](docs/cookbook/appworld/quickstart.md), [bfcl exp](docs/cookbook/bfcl/quickstart.md) - 和 [frozenlake exp](docs/cookbook/frozenlake/quickstart.md)。 -- **[2025-08]** 🚀 MCP协议支持已上线-> [MCP指南](docs/mcp_quick_start.md)。 -- **[2025-06]** 🚀 多后端向量存储支持 (Elasticsearch & ChromaDB) -> [向量数据库指南](docs/vector_store_api_guide.md)。 -- **[2024-09]** 🧠 [MemoryScope](https://github.com/modelscope/Reme/tree/memoryscope_branch) v0.1 发布，个性化和时间感知的记忆存储与使用。 - ---- - -## ✨ 功能设计 - -

- ReMe Logo -

- -ReMe整合两种互补的记忆能力： - -#### 🧠 **任务经验 (Task Memory/Experience)** -跨智能体复用的程序性知识 -- **成功模式识别**：识别有效策略并理解其根本原理 -- **失败分析学习**：从错误中学习，避免重复同样的问题 -- **对比模式**：不同采样轨迹通过对比得到更有价值的经验 -- **验证模式**：经过验证模块确认抽取记忆的有效性 - -你可以从[task memory](docs/task_memory/task_memory.md)了解更多如何使用task memory的方法 - -#### 👤 **个人记忆 (Personal Memory)** -特定用户的情境化记忆 -- **个体偏好**：用户的习惯、偏好和交互风格 -- **情境适应**：基于时间和上下文的智能记忆管理 -- **渐进学习**：通过长期交互逐步建立深度理解 -- **时间感知**：检索和整合时都具备时间敏感性 - -你可以从[personal memory](docs/personal_memory/personal_memory.md)了解更多如何使用personal memory的方法 - - ---- - -## 🛠️ 安装 - -### 从PyPI安装（推荐） -```bash -pip install reme-ai -``` - -### 从源码安装 -```bash -git clone https://github.com/modelscope/ReMe.git -cd ReMe -pip install . -``` - -### 环境配置 - -复制 `example.env` 为 .env并修改其中对应参数： - -```bash -FLOW_APP_NAME=ReMe -FLOW_LLM_API_KEY=sk-xxxx -FLOW_LLM_BASE_URL=https://xxxx/v1 -FLOW_EMBEDDING_API_KEY=sk-xxxx -FLOW_EMBEDDING_BASE_URL=https://xxxx/v1 -``` - ---- - -## 🚀 快速开始 - -### HTTP服务启动 -```bash -reme \ - backend=http \ - http.port=8002 \ - llm.default.model_name=qwen3-30b-a3b-thinking-2507 \ - embedding_model.default.model_name=text-embedding-v4 \ - vector_store.default.backend=local -``` - -### MCP服务器支持 -```bash -reme \ - backend=mcp \ - mcp.transport=stdio \ - llm.default.model_name=qwen3-30b-a3b-thinking-2507 \ - embedding_model.default.model_name=text-embedding-v4 \ - vector_store.default.backend=local -``` - -### 核心API使用 - -#### 任务记忆管理 -```python -import requests - -# 经验总结器：从执行轨迹学习 -response = requests.post("http://localhost:8002/summary_task_memory", json={ - "workspace_id": "task_workspace", - "trajectories": [ - {"messages": [{"role": "user", "content": "帮我制定项目计划"}], "score": 1.0} - ] -}) - -# 经验检索器：获取相关经验 -response = requests.post("http://localhost:8002/retrieve_task_memory", json={ - "workspace_id": "task_workspace", - "query": "如何高效管理项目进度？", - "top_k": 1 -}) -``` - -
-curl 版本 - -```bash -# 经验总结器：从执行轨迹学习 -curl -X POST http://localhost:8002/summary_task_memory \ - -H "Content-Type: application/json" \ - -d '{ - "workspace_id": "task_workspace", - "trajectories": [ - {"messages": [{"role": "user", "content": "帮我制定项目计划"}], "score": 1.0} - ] - }' - -# 经验检索器：获取相关经验 -curl -X POST http://localhost:8002/retrieve_task_memory \ - -H "Content-Type: application/json" \ - -d '{ - "workspace_id": "task_workspace", - "query": "如何高效管理项目进度？", - "top_k": 1 - }' -``` -
- -
-Node.js 版本 - -```javascript -// 经验总结器：从执行轨迹学习 -fetch("http://localhost:8002/summary_task_memory", { - method: "POST", - headers: { - "Content-Type": "application/json", - }, - body: JSON.stringify({ - workspace_id: "task_workspace", - trajectories: [ - {messages: [{role: "user", content: "帮我制定项目计划"}], score: 1.0} - ] - }) -}) -.then(response => response.json()) -.then(data => console.log(data)); - -// 经验检索器：获取相关经验 -fetch("http://localhost:8002/retrieve_task_memory", { - method: "POST", - headers: { - "Content-Type": "application/json", - }, - body: JSON.stringify({ - workspace_id: "task_workspace", - query: "如何高效管理项目进度？", - top_k: 1 - }) -}) -.then(response => response.json()) -.then(data => console.log(data)); -``` -
- -#### 个人记忆管理 -```python -# 记忆整合：从用户交互中学习 -response = requests.post("http://localhost:8002/summary_personal_memory", json={ - "workspace_id": "task_workspace", - "trajectories": [ - {"messages": - [ - {"role": "user", "content": "我喜欢早上喝咖啡工作"}, - {"role": "assistant", "content": "了解，您习惯早上用咖啡提神来开始工作"} - ] - } - ] -}) - -# 记忆检索：获取个人记忆片段 -response = requests.post("http://localhost:8002/retrieve_personal_memory", json={ - "workspace_id": "task_workspace", - "query": "用户的工作习惯是什么？", - "top_k": 5 -}) -``` - -
-curl 版本 - -```bash -# 记忆整合：从用户交互中学习 -curl -X POST http://localhost:8002/summary_personal_memory \ - -H "Content-Type: application/json" \ - -d '{ - "workspace_id": "task_workspace", - "trajectories": [ - {"messages": [ - {"role": "user", "content": "我喜欢早上喝咖啡工作"}, - {"role": "assistant", "content": "了解，您习惯早上用咖啡提神来开始工作"} - ]} - ] - }' - -# 记忆检索：获取个人记忆片段 -curl -X POST http://localhost:8002/retrieve_personal_memory \ - -H "Content-Type: application/json" \ - -d '{ - "workspace_id": "task_workspace", - "query": "用户的工作习惯是什么？", - "top_k": 5 - }' -``` -
- -
-Node.js 版本 - -```javascript -// 记忆整合：从用户交互中学习 -fetch("http://localhost:8002/summary_personal_memory", { - method: "POST", - headers: { - "Content-Type": "application/json", - }, - body: JSON.stringify({ - workspace_id: "task_workspace", - trajectories: [ - {messages: [ - {role: "user", content: "我喜欢早上喝咖啡工作"}, - {role: "assistant", content: "了解，您习惯早上用咖啡提神来开始工作"} - ]} - ] - }) -}) -.then(response => response.json()) -.then(data => console.log(data)); - -// 记忆检索：获取个人记忆片段 -fetch("http://localhost:8002/retrieve_personal_memory", { - method: "POST", - headers: { - "Content-Type": "application/json", - }, - body: JSON.stringify({ - workspace_id: "task_workspace", - query: "用户的工作习惯是什么？", - top_k: 5 - }) -}) -.then(response => response.json()) -.then(data => console.log(data)); -``` -
- ---- - -## 📦 即用型经验库 - -ReMe提供预构建的经验库，智能体可以立即使用经过验证的最佳实践： - -### 可用经验库 - -- **`appworld.jsonl`**：Appworld智能体交互的记忆库，涵盖复杂任务规划和执行模式 -- **`bfcl_v3.jsonl`**：BFCL工具调用的工作记忆库 - -### 快速使用 -```python -# 加载预构建经验 -response = requests.post("http://localhost:8002/vector_store", json={ - "workspace_id": "appworld", - "action": "load", - "path": "./docs/library/" -}) - -# 查询相关经验 -response = requests.post("http://localhost:8002/retrieve_task_memory", json={ - "workspace_id": "appworld", - "query": "如何导航到设置并更新用户资料？", - "top_k": 1 -}) -``` - -## 🧪 实验 - -### 🌍 [Appworld 实验](docs/cookbook/appworld/quickstart.md) - -我们在 Appworld 上使用 qwen3-8b 测试 ReMe： - -| 方法 | pass@1 | pass@2 | pass@4 | -|--------------|-------------------|-------------------|-------------------| -| without ReMe | 0.083 | 0.140 | 0.228 | -| with ReMe | 0.109 **(+2.6%)** | 0.175 **(+3.5%)** | 0.281 **(+5.3%)** | - -Pass@K 衡量的是在生成的 K 个样本中，至少有一个成功完成任务（score=1）的概率。 -当前实验使用的是一个内部的 AppWorld 环境，可能存在轻微差异。 - -你可以在 [quickstart.md](docs/cookbook/appworld/quickstart.md) 中找到复现实验的更多细节。 - - -### 🧊 [Frozenlake 实验](docs/cookbook/frozenlake/quickstart.md) - -| 不使用ReMe | 使用ReMe | -|:--------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------:| -|

GIF 1

|

GIF 2

| - -我们在 100 个随机 frozenlake 地图上使用 qwen3-8b 进行测试： - -| 方法 | pass rate | -|--------------|------------------| -| without ReMe | 0.66 | -| with ReMe | 0.72 **(+6.0%)** | - -你可以在 [quickstart.md](docs/cookbook/frozenlake/quickstart.md) 中找到复现实验的更多细节。 - -### 🔧 [BFCL-V3 实验](docs/cookbook/bfcl/quickstart.md) - -我们在 BFCL-V3 multi-turn-base (随机划分50train/150val) 上使用 qwen3-8b 测试 ReMe： - -| 方法 | pass@1 | pass@2 | pass@4 | -|--------------|---------------------|---------------------|---------------------| -| without ReMe | 0.2472 | 0.2733 | 0.2922 | -| with ReMe | 0.3061 **(+5.89%)** | 0.3500 **(+7.67%)** | 0.3888 **(+9.66%)** | - -## 📚 相关资源 - -- **[快速开始](./cookbook/simple_demo)**：通过实际示例快速上手 -- **[向量存储设置](docs/vector_store_api_guide.md)**：配置本地/向量数据库以及使用 -- **[mcp指南](docs/mcp_quick_start.md)**：创建mcp服务 -- **[个性化记忆](docs/personal_memory)** 与 [任务记忆](docs/task_memory): 个性化记忆与任务记忆中分别使用的算子及其含义，你可以修改config以自定义链路 -- **[示例集合](./cookbook)**：实际用例和最佳实践 - ---- - -## 🤝 贡献 - -我们相信最好的记忆系统来自集体智慧。欢迎贡献👉[指南](docs/contribution.md)： - -### 代码贡献 -- 新操作和工具开发 -- 后端实现和优化 -- API增强和新端点 - -### 文档改进 -- 使用示例和教程 -- 最佳实践指南 - ---- - -## 📄 引用 - -```bibtex -@software{ReMe2025, - title = {ReMe: Memory Management Framework for Agents}, - author = {Li Yu, Jiaji Deng, Zouying Cao}, - url = {https://github.com/modelscope/ReMe}, - year = {2025} -} -``` - ---- - -## ⚖️ 许可证 - -本项目采用Apache License 2.0许可证 - 详情请参阅[LICENSE](./LICENSE)文件。 - ---- - -## Star 历史 -[![Star History Chart](https://api.star-history.com/svg?repos=modelscope/ReMe&type=Date)](https://www.star-history.com/#modelscope/ReMe&Date) diff --git a/docs/index.md b/docs/index.md index 75a9894a..222d74a2 100644 --- a/docs/index.md +++ b/docs/index.md @@ -26,29 +26,10 @@ ReMe provides AI agents with a unified memory system—enabling the ability to e users, tasks, and agents. ``` -Personal Memory + Task Memory = Agent Memory +Personal Memory + Task Memory + Tool Memory = Agent Memory ``` -Personal memory helps "**understand user preferences**", while task memory helps agents "**perform better**". - ---- - -## 📰 Latest Updates - -- **[2025-09]** 🎉 ReMe v0.1.8 has been officially released, adding support for asynchronous operations. It has also been - integrated into the memory service of agentscope-runtime. -- **[2025-09]** 🎉 ReMe v0.1 officially released, integrating task memory and personal memory. If you want to use the - original memoryscope project, you can find it - in [MemoryScope](https://github.com/modelscope/Reme/tree/memoryscope_branch). -- **[2025-09]** 🧪 We validated the effectiveness of task memory extraction and reuse in agents in appworld, bfcl(v3), - and frozenlake environments. For more information, - check [appworld exp](./cookbook/appworld/quickstart.md), [bfcl exp](./cookbook/bfcl/quickstart.md), - and [frozenlake exp](./cookbook/frozenlake/quickstart.md). -- **[2025-08]** 🚀 MCP protocol support is now available -> [MCP Quick Start](mcp_quick_start.md). -- **[2025-06]** 🚀 Multiple backend vector storage support (Elasticsearch & - ChromaDB) -> [Vector DB quick start](vector_store_api_guide.md). -- **[2024-09]** 🧠 [MemoryScope](https://github.com/modelscope/Reme/tree/memoryscope_branch) v0.1 released, - personalized and time-aware memory storage and usage. +Personal memory helps "**understand user preferences**", task memory helps agents "**perform better**", and tool memory enables "**smarter tool usage**". --- @@ -58,7 +39,7 @@ Personal memory helps "**understand user preferences**", while task memory helps ReMe Logo

-ReMe integrates two complementary memory capabilities: +ReMe integrates three complementary memory capabilities: #### 🧠 **Task Memory/Experience** @@ -82,6 +63,17 @@ Contextualized memory for specific users Learn more about how to use personal memory from [personal memory](personal_memory/personal_memory.md) +#### 🔧 **Tool Memory** + +Data-driven tool selection and usage optimization + +- **Historical Performance Tracking**: Success rates, execution times, and token costs from real usage +- **LLM-as-Judge Evaluation**: Qualitative insights on why tools succeed or fail +- **Parameter Optimization**: Learn optimal parameter configurations from successful calls +- **Dynamic Guidelines**: Transform static tool descriptions into living, learned manuals + +Learn more about how to use tool memory from [tool memory](tool_memory/tool_memory.md) + --- ## 🛠️ Installation @@ -320,6 +312,140 @@ fetch("http://localhost:8002/retrieve_personal_memory", { +#### Tool Memory Management + +```python +import requests + +# Record tool execution results +response = requests.post("http://localhost:8002/add_tool_call_result", json={ + "workspace_id": "tool_workspace", + "tool_call_results": [ + { + "create_time": "2025-10-21 10:30:00", + "tool_name": "web_search", + "input": {"query": "Python asyncio tutorial", "max_results": 10}, + "output": "Found 10 relevant results...", + "token_cost": 150, + "success": True, + "time_cost": 2.3 + } + ] +}) + +# Generate usage guidelines from history +response = requests.post("http://localhost:8002/summary_tool_memory", json={ + "workspace_id": "tool_workspace", + "tool_names": "web_search" +}) + +# Retrieve tool guidelines before use +response = requests.post("http://localhost:8002/retrieve_tool_memory", json={ + "workspace_id": "tool_workspace", + "tool_names": "web_search" +}) +``` + +
+curl version + +```bash +# Record tool execution results +curl -X POST http://localhost:8002/add_tool_call_result \ + -H "Content-Type: application/json" \ + -d '{ + "workspace_id": "tool_workspace", + "tool_call_results": [ + { + "create_time": "2025-10-21 10:30:00", + "tool_name": "web_search", + "input": {"query": "Python asyncio tutorial", "max_results": 10}, + "output": "Found 10 relevant results...", + "token_cost": 150, + "success": true, + "time_cost": 2.3 + } + ] + }' + +# Generate usage guidelines from history +curl -X POST http://localhost:8002/summary_tool_memory \ + -H "Content-Type: application/json" \ + -d '{ + "workspace_id": "tool_workspace", + "tool_names": "web_search" + }' + +# Retrieve tool guidelines before use +curl -X POST http://localhost:8002/retrieve_tool_memory \ + -H "Content-Type: application/json" \ + -d '{ + "workspace_id": "tool_workspace", + "tool_names": "web_search" + }' +``` + +
+ +
+Node.js version + +```javascript +// Record tool execution results +fetch("http://localhost:8002/add_tool_call_result", { + method: "POST", + headers: { + "Content-Type": "application/json", + }, + body: JSON.stringify({ + workspace_id: "tool_workspace", + tool_call_results: [ + { + create_time: "2025-10-21 10:30:00", + tool_name: "web_search", + input: {query: "Python asyncio tutorial", max_results: 10}, + output: "Found 10 relevant results...", + token_cost: 150, + success: true, + time_cost: 2.3 + } + ] + }) +}) +.then(response => response.json()) +.then(data => console.log(data)); + +// Generate usage guidelines from history +fetch("http://localhost:8002/summary_tool_memory", { + method: "POST", + headers: { + "Content-Type": "application/json", + }, + body: JSON.stringify({ + workspace_id: "tool_workspace", + tool_names: "web_search" + }) +}) +.then(response => response.json()) +.then(data => console.log(data)); + +// Retrieve tool guidelines before use +fetch("http://localhost:8002/retrieve_tool_memory", { + method: "POST", + headers: { + "Content-Type": "application/json", + }, + body: JSON.stringify({ + workspace_id: "tool_workspace", + tool_names: "web_search" + }) +}) +.then(response => response.json()) +.then(data => console.log(data)); +``` + +
+ --- ## 📦 Ready-to-Use Libraries @@ -391,12 +517,30 @@ We tested ReMe on BFCL-V3 multi-turn-base (randomly split 50train/150val) using | without ReMe | 0.2472 | 0.2733 | 0.2922 | | with ReMe | 0.3061 **(+5.89%)** | 0.3500 **(+7.67%)** | 0.3888 **(+9.66%)** | +### 🛠️ [Tool Memory Benchmark](tool_memory/tool_bench.md) + +We evaluated Tool Memory effectiveness using a controlled benchmark with three mock search tools using Qwen3-30B-Instruct: + +| Scenario | Avg Score | Improvement | +|-----------------------|-----------|--------------------| +| Train (No Memory) | 0.650 | - | +| Test (No Memory) | 0.672 | Baseline | +| **Test (With Memory)** | **0.772** | **+14.88%** | + +**Key Findings:** +- Tool Memory enables data-driven tool selection based on historical performance +- Success rates improved by ~15% with learned parameter configurations + +You can find more details in [tool_bench.md](tool_memory/tool_bench.md) and the implementation at [run_reme_tool_bench.py](https://github.com/modelscope/ReMe/tree/main/cookbook/tool_memory/run_reme_tool_bench.py). + ## 📚 Resources - **[Quick Start](https://github.com/modelscope/ReMe/tree/main/cookbook/simple_demo)**: Get started quickly with practical examples + - [Tool Memory Demo](https://github.com/modelscope/ReMe/tree/main/cookbook/simple_demo/use_tool_memory_demo.py): Complete lifecycle demonstration of tool memory + - [Tool Memory Benchmark](https://github.com/modelscope/ReMe/tree/main/cookbook/tool_memory/run_reme_tool_bench.py): Evaluate tool memory effectiveness - **[Vector Storage Setup](vector_store_api_guide.md)**: Configure local/vector databases and usage - **[MCP Guide](mcp_quick_start.md)**: Create MCP services -- **[personal memory](personal_memory/personal_memory.md)** & **[task memory](task_memory/task_memory.md)** : Operators used in personal memory and task memory, You can modify the config to customize the pipelines. +- **[Personal Memory](personal_memory/personal_memory.md)**, **[Task Memory](task_memory/task_memory.md)** & **[Tool Memory](tool_memory/tool_memory.md)**: Operators used in personal memory, task memory and tool memory. You can modify the config to customize the pipelines. - **[Example Collection](./cookbook/appworld/quickstart.md)**: Real use cases and best practices --- diff --git a/docs/todo.md b/docs/todo.md new file mode 100644 index 00000000..8e44c695 --- /dev/null +++ b/docs/todo.md @@ -0,0 +1,25 @@ +# TODO + +## Planned Features + +### 1. Automatic Tool Exploration Mode +Add an automatic tool exploration mode that generates tool memory by: +- Automatically discovering and testing available tools +- Learning tool usage patterns and best practices +- Building a comprehensive tool memory database from exploration results + +### 2. Desktop Pet Personal Assistant +Build a desktop pet personal assistant with: +- Interactive desktop companion interface +- Personalized assistance capabilities +- Integration with ReMe's memory system + +### 3. Task Memory Research Implementation +We are currently working on implementing features based on task memory research papers. Coming soon. + +### 4. Mem-Agent Exploration +We are exploring mem-agent to implement agentic memory pathways: +- Investigating agent-driven memory management +- Developing autonomous memory retrieval and storage mechanisms +- Building more intelligent memory update strategies + diff --git a/docs/tool_memory/tool_memory.md b/docs/tool_memory/tool_memory.md index 8c6d2fe9..3d1df28c 100644 --- a/docs/tool_memory/tool_memory.md +++ b/docs/tool_memory/tool_memory.md @@ -194,14 +194,14 @@ Tool Memory operates through three complementary operations that work together t ```mermaid graph LR - A[Agent] -->|1. retrieve_tool_memory| B[(Vector Store)] + A[Agent] -->|1 retrieve_tool_memory| B[(Vector Store)] B -->|Guidelines| A - A -->|Execute Tool| C[Tool] + A -->|2 Execute Tool| C[Tool] C -->|Result| A - A -->|add_tool_call_result| D[LLM Evaluate] + A -->|3 add_tool_call_result| D[LLM Evaluate] D -->|Store| B B -->|Periodic| E[summary_tool_memory] - E -->|Update Guidelines| B + E -->|4 Update Guidelines| B ``` ### Operation Flow diff --git a/mkdocs.yml b/mkdocs.yml index f885c4c6..e1839772 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -43,6 +43,7 @@ nav: - BFCL: cookbook/bfcl/quickstart.md - FrozenLake: cookbook/frozenlake/quickstart.md + - TODO: todo.md - Contributions: contribution.md