reme-ai 0.1.3__tar.gz → 0.1.4__tar.gz

{reme_ai-0.1.3/reme_ai.egg-info → reme_ai-0.1.4}/PKG-INFO

@@ -1,8 +1,8 @@
 Metadata-Version: 2.4
 Name: reme_ai
-Version: 0.1.3
+Version: 0.1.4
 Summary: Remember me
-Author-email: reme_team <reme_team@alibaba-inc.com>
+Author-email: "jinli.yl" <jinli.yl@alibaba-inc.com>, "dengjiaji.djj" <dengjiaji.djj@alibaba-inc.com>, "caozouying.czy" <caozouying.czy@alibaba-inc.com>
 License:                                  Apache License
                                    Version 2.0, January 2004
                                 http://www.apache.org/licenses/
@@ -205,132 +205,140 @@ License:                                  Apache License
            See the License for the specific language governing permissions and
            limitations under the License.
         
+Keywords: llm,memory,experience,memoryscope,ai,mcp,http
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Operating System :: OS Independent
-Requires-Python: >=3.12
+Requires-Python: >=3.11
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: flowllm>=0.1.3
 Dynamic: license-file
 
-# ReMe.ai
-
 <p align="center">
- <img src="doc/figure/logo.jpg" alt="ReMe.ai Logo" width="100%">
+ <img src="docs/figure/reme_logo.png" alt="ReMe Logo" width="50%">
 </p>
 
 <p align="center">
   <a href="https://pypi.org/project/reme-ai/"><img src="https://img.shields.io/badge/python-3.12+-blue" alt="Python Version"></a>
-  <a href="https://pypi.org/project/reme-ai/"><img src="https://img.shields.io/badge/pypi-v1.0.0-blue?logo=pypi" alt="PyPI Version"></a>
+  <a href="https://pypi.org/project/reme-ai/"><img src="https://img.shields.io/badge/pypi-v0.1.x-blue?logo=pypi" alt="PyPI Version"></a>
   <a href="./LICENSE"><img src="https://img.shields.io/badge/license-Apache--2.0-black" alt="License"></a>
-  <a href="https://github.com/modelscope/ReMe.ai"><img src="https://img.shields.io/github/stars/modelscope/ReMe.ai?style=social" alt="GitHub Stars"></a>
+  <a href="https://github.com/modelscope/ReMe"><img src="https://img.shields.io/github/stars/modelscope/ReMe?style=social" alt="GitHub Stars"></a>
 </p>
 
 <p align="center">
-  <strong>记忆驱动的AI智能体框架</strong><br>
-  <em>"如果说我比别人看得更远些，那是因为我站在了巨人的肩膀上。" —— 牛顿</em>
+  <strong>ReMe (formerly MemoryScope): Memory Management Framework for Agents</strong><br>
+  <em>Remember Me, Refine Me.</em>
 </p>
 
 ---
-
-Remember Everyone, Recreate Everything
-
-Remember Me, Reshape Me
-
-Remember Me, Refine Me
-
-Remember Me, Reinvent Me
-
-今天的每个AI智能体都在从零开始。每当智能体处理任务时，它都在重新发明无数其他智能体已经发现的解决方案。这就像要求每个人都从头发现火、农业和数学一样。
-
-ReMe.ai希望改变这一点。我们为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。
+ReMe provides AI agents with a unified memory system—enabling the ability to extract, reuse, and share memories across
+users, tasks, and agents.
 
 ```
-任务经验 (Task Memory) + 个人记忆 (Personal Memory) = agent的记忆管理
+Personal Memory + Task Memory = Agent Memory
 ```
 
-个人记忆回答"**如何理解用户需要**"，任务记忆回答"**如何做得更好**"，
+Personal memory helps "**understand user preferences**", while task memory helps agents "**perform better**".
 
 ---
 
-## 📰 最新动态
-- **[2025-09]** 🎉 ReMe.ai v1.0.0 正式发布，整合任务经验与个人记忆
-- **[2025-08]** 🚀 MCP协议支持已上线！→ [快速开始指南](./doc/mcp_quick_start.md)
-- **[2025-07]** 📚 完整文档和快速开始指南发布
-- **[2025-06]** 🚀 多后端向量存储支持 (Elasticsearch & ChromaDB)
+## 📰 Latest Updates
+
+- **[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](docs/mcp_quick_start.md).
+- **[2025-06]** 🚀 Multiple backend vector storage support (Elasticsearch &
+  ChromaDB) -> [Vector DB quick start](docs/vector_store_api_guide.md).
+- **[2024-09]** 🧠 [MemoryScope](https://github.com/modelscope/Reme/tree/memoryscope_branch) v0.1.x released,
+  personalized and time-aware memory storage and usage.
 
 ---
 
-## ✨ 架构设计
+## ✨ Architecture Design
+
+<p align="center">
+ <img src="docs/figure/reme_structure.jpg" alt="ReMe Logo" width="100%">
+</p>
+
+ReMe integrates two complementary memory capabilities:
+
+#### 🧠 **Task Memory/Experience**
 
-### 🎯 双模记忆系统
+Procedural knowledge reused across agents
 
-ReMe.ai整合两种互补的记忆能力：
+- **Success Pattern Recognition**: Identify effective strategies and understand their underlying principles
+- **Failure Analysis Learning**: Learn from mistakes and avoid repeating the same issues
+- **Comparative Patterns**: Different sampling trajectories provide more valuable memories through comparison
+- **Validation Patterns**: Confirm the effectiveness of extracted memories through validation modules
 
-#### 🧠 **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
-- **规划策略**：不同问题类型的规划策略
-- **工具使用模式**：经过验证的有效工具使用方法
-- **标准操作流程**：经过验证的方法论和流程
+Learn more about how to use task memory from [task memory](docs/task_memory/task_memory.md)
 
-你可以从[快速开始指南](./doc/task_memory_readme.md)了解更多如何使用task memory的方法
+#### 👤 **Personal Memory**
 
-#### 👤 **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
+Contextualized memory for specific users
 
-- 你可以从[快速开始指南](./doc/personal_memory_readme.md)了解更多如何使用personal memory的方法
+- **Individual Preferences**: User habits, preferences, and interaction styles
+- **Contextual Adaptation**: Intelligent memory management based on time and context
+- **Progressive Learning**: Gradually build deep understanding through long-term interaction
+- **Time Awareness**: Time sensitivity in both retrieval and integration
 
+Learn more about how to use personal memory from [personal memory](docs/personal_memory/personal_memory.md)
 
 ---
 
-## 🛠️ 安装
+## 🛠️ Installation
+
+### Install from PyPI (Recommended)
 
-### 从PyPI安装（推荐）
 ```bash
 pip install reme-ai
 ```
 
-### 从源码安装
+### Install from Source
+
 ```bash
-git clone https://github.com/modelscope/ReMe.ai.git
-cd ReMe.ai
+git clone https://github.com/modelscope/ReMe.git
+cd ReMe
 pip install .
 ```
 
-### 环境配置
-创建`.env`文件：
+### Environment Configuration
+
+Copy `example.env` to .env and modify the corresponding parameters:
+
 ```bash
-# 必需：LLM API配置
-LLM_API_KEY="sk-xxx"
-LLM_BASE_URL="https://xxx.com/v1"
+# Required: LLM API Configuration
+FLOW_LLM_API_KEY=sk-xxxx
+FLOW_LLM_BASE_URL=https://xxxx/v1
 
-# 必需：嵌入模型配置  
-EMBEDDING_MODEL_API_KEY="sk-xxx"
-EMBEDDING_MODEL_BASE_URL="https://xxx.com/v1"
+# Required: Embedding Model Configuration  
+FLOW_EMBEDDING_API_KEY=sk-xxxx
+FLOW_EMBEDDING_BASE_URL=https://xxxx/v1
 ```
 
 ---
 
-## 🚀 快速开始
+## 🚀 Quick Start
+
+### HTTP Service Startup
 
-### HTTP服务启动
 ```bash
 reme \
-  backend=http \ 
-  http.port=8001 \
+  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
+### MCP Server Support
+
 ```bash
 reme \
   backend=mcp \
@@ -340,147 +348,302 @@ reme \
   vector_store.default.backend=local
 ```
 
-### 核心API使用
+### Core API Usage
+
+#### Task Memory Management
 
-#### 任务经验管理
 ```python
 import requests
 
-# 经验总结器：从执行轨迹学习
+# Experience Summarizer: Learn from execution trajectories
 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}
+        {"messages": [{"role": "user", "content": "Help me create a project plan"}], "score": 1.0}
     ]
 })
 
-# 经验检索器：获取相关经验
+# Retriever: Get relevant memories
 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？",
+    "query": "How to efficiently manage project progress?",
     "top_k": 1
 })
 ```
 
-#### 个人记忆管理  
+<details>
+<summary>curl version</summary>
+
+```bash
+# Experience Summarizer: Learn from execution trajectories
+curl -X POST http://localhost:8002/summary_task_memory \
+  -H "Content-Type: application/json" \
+  -d '{
+    "workspace_id": "task_workspace",
+    "trajectories": [
+      {"messages": [{"role": "user", "content": "Help me create a project plan"}], "score": 1.0}
+    ]
+  }'
+
+# Retriever: Get relevant memories
+curl -X POST http://localhost:8002/retrieve_task_memory \
+  -H "Content-Type: application/json" \
+  -d '{
+    "workspace_id": "task_workspace",
+    "query": "How to efficiently manage project progress?",
+    "top_k": 1
+  }'
+```
+
+</details>
+
+<details>
+<summary>Node.js version</summary>
+
+```javascript
+// Experience Summarizer: Learn from execution trajectories
+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: "Help me create a project plan"}], score: 1.0}
+    ]
+  })
+})
+.then(response => response.json())
+.then(data => console.log(data));
+
+// Retriever: Get relevant memories
+fetch("http://localhost:8002/retrieve_task_memory", {
+  method: "POST",
+  headers: {
+    "Content-Type": "application/json",
+  },
+  body: JSON.stringify({
+    workspace_id: "task_workspace",
+    query: "How to efficiently manage project progress?",
+    top_k: 1
+  })
+})
+.then(response => response.json())
+.then(data => console.log(data));
+```
+
+</details>
+
+#### Personal Memory Management
+
 ```python
-# 记忆整合：从用户交互中学习
+# Memory Integration: Learn from user interactions
 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"}
+                {"role": "user", "content": "I like to drink coffee while working in the morning"},
+                {"role": "assistant",
+                 "content": "I understand, you prefer to start your workday with coffee to stay energized"}
             ]
         }
     ]
 })
 
-# 记忆检索：获取个人记忆片段
+# Memory Retrieval: Get personal memory fragments
 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？",
+    "query": "What are the user's work habits?",
     "top_k": 5
 })
 ```
 
----
-
-## 🧪 实验结果
+<details>
+<summary>curl version</summary>
 
-### Appworld基准测试
-使用qwen3-8b在Appworld上的测试结果：
-
-| 方法                         | pass@1    | pass@2      | pass@4    |
-|----------------------------|-----------|-------------|-----------|
-| 无记忆（基线）               | 0.083     | 0.140       | 0.228     |
-| **使用任务经验**            | **0.109** | **0.175**   | **0.281** |
+```bash
+# Memory Integration: Learn from user interactions
+curl -X POST http://localhost:8002/summary_personal_memory \
+  -H "Content-Type: application/json" \
+  -d '{
+    "workspace_id": "task_workspace",
+    "trajectories": [
+      {"messages": [
+        {"role": "user", "content": "I like to drink coffee while working in the morning"},
+        {"role": "assistant", "content": "I understand, you prefer to start your workday with coffee to stay energized"}
+      ]}
+    ]
+  }'
 
-详见：[quickstart.md](cookbook/appworld/quickstart.md)
+# Memory Retrieval: Get personal memory fragments
+curl -X POST http://localhost:8002/retrieve_personal_memory \
+  -H "Content-Type: application/json" \
+  -d '{
+    "workspace_id": "task_workspace",
+    "query": "What are the user's work habits?",
+    "top_k": 5
+  }'
+```
 
-### FrozenLake实验
-使用qwen3-8b在100个随机FrozenLake地图上测试：
+</details>
+
+<details>
+<summary>Node.js version</summary>
+
+```javascript
+// Memory Integration: Learn from user interactions
+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: "I like to drink coffee while working in the morning"},
+        {role: "assistant", content: "I understand, you prefer to start your workday with coffee to stay energized"}
+      ]}
+    ]
+  })
+})
+.then(response => response.json())
+.then(data => console.log(data));
+
+// Memory Retrieval: Get personal memory fragments
+fetch("http://localhost:8002/retrieve_personal_memory", {
+  method: "POST",
+  headers: {
+    "Content-Type": "application/json",
+  },
+  body: JSON.stringify({
+    workspace_id: "task_workspace",
+    query: "What are the user's work habits?",
+    top_k: 5
+  })
+})
+.then(response => response.json())
+.then(data => console.log(data));
+```
 
-| 方法                        | 通过率           | 
-|---------------------------|-----------------|
-| 无记忆（基线）              | 0.66            | 
-| **使用任务经验**           | 0.72 **(+9.1%)** |
+</details>
 
-|                            无经验                            |                  有经验                   |
-|:----------------------------------------------------------:|:---------------------------------------:|
-| <p align="center"><img src="doc/figure/frozenlake_failure.gif" alt="失败案例" width="30%"></p> | <p align="center"><img src="doc/figure/frozenlake_success.gif" alt="成功案例" width="30%"></p>
+---
 
-详见：[quickstart.md](cookbook/frozenlake/quickstart.md)
+## 📦 Ready-to-Use Libraries
 
----
+ReMe provides pre-built memory libraries that agents can immediately use with verified best practices:
 
-## 📦 即用型经验库
+### Available Libraries
 
-ReMe.ai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：
+- **`appworld.jsonl`**: Memory library for Appworld agent interactions, covering complex task planning and execution
+  patterns
+- **`bfcl_v3.jsonl`**: Working memory library for BFCL tool calls
 
-### 可用经验库
-- **`appworld_v1.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_v1.jsonl`**：BFCL工具调用的工作记忆库
+### Quick Usage
 
-### 快速使用
 ```python
-# 加载预构建经验
+# Load pre-built memories
 response = requests.post("http://localhost:8002/vector_store", json={
-    "workspace_id": "appworld_v1", 
+    "workspace_id": "appworld",
     "action": "load",
     "path": "./library/"
 })
 
-# 查询相关经验
+# Query relevant memories
 response = requests.post("http://localhost:8002/retrieve_task_memory", json={
-    "workspace_id": "appworld_v1",
-    "query": "如何导航到设置并更新用户资料？",
+    "workspace_id": "appworld",
+    "query": "How to navigate to settings and update user profile?",
     "top_k": 1
 })
 ```
 
-## 📚 相关资源
+## 🧪 Experiments
 
-- **[快速开始](./cookbook/simple_demo/quick_start.md)**：通过实际示例快速上手
-- **[向量存储设置](./doc/vector_store_setup.md)**：生产部署指南  
-- **[配置指南](./doc/configuration_guide.md)**：详细配置参考
-- **[操作文档](./doc/operations_documentation.md)**：操作配置说明
-- **[示例集合](./cookbook)**：实际用例和最佳实践
+### 🌍 [Appworld Experiment](./cookbook/appworld/quickstart.md)
+
+We tested ReMe on Appworld using qwen3-8b:
+
+| Method       | 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 measures the probability that at least one of the K generated samples successfully completes the task (
+score=1).  
+The current experiment uses an internal AppWorld environment, which may have slight differences.
+
+You can find more details on reproducing the experiment in [quickstart.md](cookbook/appworld/quickstart.md).
+
+### 🧊 [Frozenlake Experiment](./cookbook/frozenlake/quickstart.md)
+
+|                                         without ReMe                                         |                                          with ReMe                                           |
+|:--------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------:|
+| <p align="center"><img src="docs/figure/frozenlake_failure.gif" alt="GIF 1" width="30%"></p> | <p align="center"><img src="docs/figure/frozenlake_success.gif" alt="GIF 2" width="30%"></p> |
+
+We tested on 100 random frozenlake maps using qwen3-8b:
+
+| Method       | pass rate        |
+|--------------|------------------|
+| without ReMe | 0.66             |
+| with ReMe    | 0.72 **(+6.0%)** |
+
+You can find more details on reproducing the experiment in [quickstart.md](cookbook/frozenlake/quickstart.md).
+
+### 🔧 [BFCL-V3 Experiment](./cookbook/bfcl/quickstart.md)
+
+We tested ReMe on BFCL-V3 multi-turn-base (randomly split 50train/150val) using qwen3-8b:
+
+| Method       | 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%)** |
+
+## 📚 Resources
+
+- **[Quick Start](./cookbook/simple_demo)**: Get started quickly with practical examples
+- **[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)** : Operators used in personal memory and task memory, You can modify the config to customize the pipelines.
+- **[Example Collection](./cookbook)**: Real use cases and best practices
 
 ---
 
-## 🤝 贡献
+## 🤝 Contribution
+
+We believe the best memory systems come from collective wisdom. Contributions welcome 👉[Guide](docs/contribution.md):
+
+### Code Contributions
+
+- New operation and tool development
+- Backend implementation and optimization
+- API enhancements and new endpoints
 
-我们相信最好的记忆系统来自集体智慧。欢迎贡献：
+### Documentation Improvements
 
-### 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
+- Usage examples and tutorials
+- Best practice guides
 
-### 文档改进
-- 使用示例和教程
-- 最佳实践指南
-- 翻译和本地化
 
 ---
 
-## 📄 引用
+## 📄 Citation
 
 ```bibtex
 @software{ReMe2025,
-  title = {ReMe.ai: Memory-Driven AI Agent Framework},
-  author = {The ReMe.ai Team},
-  url = {https://github.com/modelscope/ReMe.ai},
+  title = {ReMe: Memory Framework for AI Agent},
+  author = {Li Yu, Jiaji Deng, Zouying Cao},
+  url = {https://github.com/modelscope/ReMe},
   year = {2025}
 }
 ```
 
 ---
 
-## ⚖️ 许可证
+## ⚖️ License
 
-本项目采用Apache License 2.0许可证 - 详情请参阅[LICENSE](./LICENSE)文件。
+This project is licensed under the Apache License 2.0 - see the [LICENSE](./LICENSE) file for details.
 
 ---