- ReMe: 为agent设计的记忆管理框架
+ ReMe: 为Agent设计的记忆管理框架 Remember Me, Refine Me
---
-
-agent时代的记忆不单是用于保存个性化的用户信息。agent在完成任务时，我们希望它能够有区分性地记住用户的偏好，以及如何正确地行动。
-
-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。
```
@@ -34,12 +29,15 @@ ReMe为AI智能体提供了统一的记忆与经验系统——在跨用户、
## 📰 最新动态
-- **[2025-09]** 🧪 我们在appworld, bfcl(v3) 以及frozenlake环境验证了记忆抽取与复用在agent中的效果，更多信息请查看 [appworld exp](./cookbook/appworld/quickstart.md), [bfcl exp](./cookbook/bfcl/quickstart.md) & [frozenlake exp](./cookbook/frozenlake/quickstart.md)
-- **[2025-09]** 🎉 ReMe(formerly [MemoryScope](./memoryscope/README.md)) v1.0 正式发布，整合任务经验与个人记忆。 如果想使用原始的memoryscope项目，你可以在[MemoryScope](./memoryscope)找到
-- **[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) -> [快速开始指南](./doc/vector_store_api_guide.md)
-- **[2024-09]** 🧠 MemoryScope v0.1.1.0 发布，个性化和时间感知的记忆存储与使用
+- **[2025-09]** 🎉 ReMe v0.1.x
+ 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](./cookbook/appworld/quickstart.md), [bfcl exp](./cookbook/bfcl/quickstart.md)
+ and [frozenlake exp](./cookbook/frozenlake/quickstart.md)。
+- **[2025-08]** 🚀 MCP协议支持已上线-> [快速开始指南](./doc/mcp_quick_start.md)。
+- **[2025-06]** 🚀 多后端向量存储支持 (Elasticsearch & ChromaDB) -> [快速开始指南](./doc/vector_store_api_guide.md)。
+- **[2024-09]** 🧠 [MemoryScope](https://github.com/modelscope/Reme/tree/memoryscope_branch) v0.1.x 发布，个性化和时间感知的记忆存储与使用。
---
@@ -58,7 +56,7 @@ ReMe整合两种互补的记忆能力：
你可以从[task memory](./doc/task_memory/task_memory.md)了解更多如何使用task memory的方法
-#### 👤 **个人记忆 (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
@@ -124,7 +122,7 @@ reme \
### 核心API使用
-#### 任务经验管理
+#### 任务记忆管理
```python
import requests
@@ -174,21 +172,22 @@ response = requests.post("http://localhost:8002/retrieve_personal_memory", json=
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_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
+
+- **`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_v1",
+ "workspace_id": "appworld",
"action": "load",
"path": "./library/"
})
# 查询相关经验
response = requests.post("http://localhost:8002/retrieve_task_memory", json={
- "workspace_id": "appworld_v1",
+ "workspace_id": "appworld",
"query": "如何导航到设置并更新用户资料？",
"top_k": 1
})
@@ -200,11 +199,10 @@ response = requests.post("http://localhost:8002/retrieve_task_memory", json={
我们在 Appworld 上使用 qwen3-8b 测试 ReMe：
-| 方法 | pass@1 | pass@2 | pass@4 |
-|---------------------|-----------|-------------|-----------|
-| 不使用 ReMe (baseline) | 0.083 | 0.140 | 0.228 |
-| **使用 ReMe** | | | |
-| w/ memory(直接使用) | **0.109** | **0.175** | **0.281** |
+| 方法 | pass@1 | pass@2 | pass@4 |
+|--------------|-----------|-----------|-----------|
+| without Reme | 0.083 | 0.140 | 0.228 |
+| with Reme | **0.109** | **0.175** | **0.281** |
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。
@@ -220,11 +218,10 @@ 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
我们在 100 个随机 frozenlake 地图上使用 qwen3-8b 进行测试：
-| 方法 | pass rate |
-|---------------------|----------------|
-| 不使用 ReMe (baseline) | 0.66 |
-| **使用 ReMe** | |
-| w/ memory (直接使用) | 0.72 **(+9.1%)** |
+| 方法 | pass rate |
+|--------------|------------------|
+| without Reme | 0.66 |
+| with Reme | 0.72 **(+9.1%)** |
你可以在 [quickstart.md](cookbook/frozenlake/quickstart.md) 中找到复现实验的更多细节。
@@ -267,7 +264,7 @@ 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
```bibtex
@software{ReMe2025,
title = {ReMe: Memory Framework for AI Agent},
- author = {The ReMe Team},
+ author = {jinli.yl, dengjiaji.djj, caozouying.czy},
url = {https://github.com/modelscope/ReMe},
year = {2025}
}
diff --git a/cookbook/appworld/quickstart.md b/cookbook/appworld/quickstart.md
index dd759eb3..639c4182 100644
--- a/cookbook/appworld/quickstart.md
+++ b/cookbook/appworld/quickstart.md
@@ -56,10 +56,11 @@ Launch the ReMe service to enable memory library functionality:
```bash
reme \
- http_service.port=8001 \
+ backend=http \
+ http.port=8001 \
llm.default.model_name=qwen-max-latest \
embedding_model.default.model_name=text-embedding-v4 \
- vector_store.default.backend=local_file
+ vector_store.default.backend=local
```
add memories for appworld:
diff --git a/cookbook/bfcl/init_task_memory_pool.py b/cookbook/bfcl/init_task_memory_pool.py
index 5f4d9021..8c00d4a6 100644
--- a/cookbook/bfcl/init_task_memory_pool.py
+++ b/cookbook/bfcl/init_task_memory_pool.py
@@ -147,7 +147,7 @@ def process_trajectories_with_threads(grouped_trajectories: List[List[Any]],
def main():
parser = argparse.ArgumentParser(description='Convert JSONL to memories using ReMe service')
parser.add_argument('--jsonl_file', type=str, required=True, help='Path to the JSONL file')
- parser.add_argument('--service_url', type=str, default='http://localhost:8001', help='Reme service URL')
+ parser.add_argument('--service_url', type=str, default='http://localhost:8001', help='ReMe service URL')
parser.add_argument('--workspace_id', type=str, required=True, help='Workspace ID for the task memory pool')
parser.add_argument('--output_file', type=str, help='Output file to save results (optional)')
parser.add_argument('--n_threads', type=int, default=4, help='Number of threads for processing')
diff --git a/cookbook/bfcl/quickstart.md b/cookbook/bfcl/quickstart.md
index 213760df..c5a66a5f 100644
--- a/cookbook/bfcl/quickstart.md
+++ b/cookbook/bfcl/quickstart.md
@@ -55,7 +55,7 @@ After collecting trajectories, Launch the ReMe service (make sure you have insta
```bash
reme \
backend=http \
- http.port=8001 \
+ http.port=8002 \
llm.default.model_name=qwen-max-2025-01-25 \
embedding_model.default.model_name=text-embedding-v4 \
vector_store.default.backend=local
@@ -69,14 +69,14 @@ python init_exp_pool.py
**Configuration options in `init_exp_pool.py`:**
- `jsonl_file`: Path to the collloaded trajectories
-- `service_url`: ReMe service URL (default: `http://localhost:8001`)
+- `service_url`: ReMe service URL (default: `http://localhost:8002`)
- `workspace_id`: Workspace ID for the task memory pool (default: `bfcl_test`)
- `n_threads`: Number of threads for processing (default: `4`)
- `output_file`: Output file to save results (optional)
-Now you have inited the task memory pool using `local` backend (start on `http://localhost:8001`). Then, use `local_file_to_library.py` script to convert the local file to the memory library or run the following `curl` command:
+Now you have inited the task memory pool using `local` backend (start on `http://localhost:8002`). Then, use `local_file_to_library.py` script to convert the local file to the memory library or run the following `curl` command:
```bash
-curl -X POST "http://0.0.0.0:8001/vector_store" \
+curl -X POST "http://0.0.0.0:8002/vector_store" \
-H "Content-Type: application/json" \
-d '{
"workspace_id": "bfcl_test",
@@ -88,7 +88,7 @@ to dump the memory library (default in `./library/bfcl_test.jsonl`).
Next time, you can import this previously exported task memory data to populate the new started workspace with existing knowledge:
```bash
-curl -X POST "http://0.0.0.0:8001/vector_store" \
+curl -X POST "http://0.0.0.0:8002/vector_store" \
-H "Content-Type: application/json" \
-d '{
"workspace_id": "bfcl_test",
diff --git a/doc/contribution.md b/doc/contribution.md
new file mode 100644
index 00000000..fd1328b2
--- /dev/null
+++ b/doc/contribution.md
@@ -0,0 +1,36 @@
+# Contribute to ReMe
+Our community thrives on the diverse ideas and contributions of its members. Whether you're fixing a bug, adding a new feature, improving the documentation, or adding examples, your help is welcome. Here's how you can contribute:
+## Report Bugs and Ask For New Features?
+Did you find a bug or have a feature request? Please first check the issue tracker to see if it has already been reported. If not, feel free to open a new issue. Include as much detail as possible:
+- A descriptive title
+- Clear description of the issue
+- Steps to reproduce the problem
+- Version of the ReMe you are using
+- Any relevant code snippets or error messages
+## Contribute to Codebase
+### Fork and Clone the Repository
+To work on an issue or a new feature, start by forking the ReMe repository and then cloning your fork locally.
+```bash
+git clone https://github.com/your-username/ReMe.git
+cd ReMe
+```
+### Create a New Branch
+Create a new branch for your work. This helps keep proposed changes organized and separate from the `main` branch.
+```bash
+git checkout -b your-feature-branch-name
+```
+### Making Changes
+With your new branch checked out, you can now make your changes to the code. Remember to keep your changes as focused as possible. If you're addressing multiple issues or features, it's better to create separate branches and pull requests for each.
+
+### Commit Your Changes
+Once you've made your changes, it's time to commit them. Write clear and concise commit messages that explain your changes.
+```bash
+git add -A
+git commit -m "A brief description of the changes"
+```
+
+### Submit a Pull Request
+When you're ready for feedback, submit a pull request to the ReMe `main` branch. In your pull request description, explain the changes you've made and any other relevant context.
+We will review your pull request. This process might involve some discussion, additional changes on your part, or both.
+### Code Review
+Wait for us to review your pull request. We may suggest some changes or improvements. Keep an eye on your GitHub notifications and be responsive to any feedback.
\ No newline at end of file
diff --git a/library/index.html b/doc/index.html
similarity index 99%
rename from library/index.html
rename to doc/index.html
index 44643474..6636a102 100644
--- a/library/index.html
+++ b/doc/index.html
@@ -3,7 +3,7 @@
- Reme - Memory Library
+ ReMe - Memory Library
-
+ 
