diff --git a/.github/workflows/python-publish.yml b/.github/workflows/python-publish.yml new file mode 100644 index 00000000..dc60503b --- /dev/null +++ b/.github/workflows/python-publish.yml @@ -0,0 +1,40 @@ +# This workflow will upload a Python Package using Twine when a release is created +# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python#publishing-to-package-registries + +# This workflow uses actions that are not certified by GitHub. +# They are provided by a third-party and are governed by +# separate terms of service, privacy policy, and support +# documentation. + +name: Publish Python Package to Pypi + +on: + workflow_dispatch: + release: + types: [published] + +permissions: + contents: read + +jobs: + deploy: + + runs-on: ubuntu-latest + + steps: + - uses: actions/checkout@v4 + - name: Set up Python + uses: actions/setup-python@v5 + with: + python-version: '3.10' + - name: Install dependencies + run: | + python -m pip install --upgrade pip + pip install setuptools wheel build + - name: Build package + run: python -m build + - name: Publish package to PyPI + uses: pypa/gh-action-pypi-publish@release/v1 + with: + user: __token__ + password: ${{ secrets.PYPI_API_TOKEN }} diff --git a/docs/cookbook/experiment_overview.md b/docs/cookbook/experiment_overview.md new file mode 100644 index 00000000..61a5cd6b --- /dev/null +++ b/docs/cookbook/experiment_overview.md @@ -0,0 +1,42 @@ +--- +order: 1 +--- + +### 🌍 [Appworld Experiment](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](appworld/quickstart.md). + +### 🧊 [Frozenlake Experiment](frozenlake/quickstart.md) + +| without ReMe | with ReMe | +|:---------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------:| +|

GIF 1

|

GIF 2

| + +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](frozenlake/quickstart.md). + +### 🔧 [BFCL-V3 Experiment](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%)** | diff --git a/docs/index.md b/docs/index.md index 222d74a2..8fe0b923 100644 --- a/docs/index.md +++ b/docs/index.md @@ -22,6 +22,7 @@ show_datetime: true

--- + ReMe provides AI agents with a unified memory system—enabling the ability to extract, reuse, and share memories across users, tasks, and agents. @@ -31,9 +32,7 @@ Personal Memory + Task Memory + Tool Memory = Agent Memory Personal memory helps "**understand user preferences**", task memory helps agents "**perform better**", and tool memory enables "**smarter tool usage**". ---- - -## ✨ Architecture Design +## Architecture Design

ReMe Logo @@ -41,27 +40,24 @@ Personal memory helps "**understand user preferences**", task memory helps agent ReMe integrates three complementary memory capabilities: -#### 🧠 **Task Memory/Experience** +!!! note "Task Memory/Experience" -Procedural knowledge reused across agents + --- -- **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 + Procedural knowledge reused across agents -Learn more about how to use task memory from [task memory](task_memory/task_memory.md) + - **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 -#### 👤 **Personal Memory** + Learn more about how to use task memory from [task memory](task_memory/task_memory.md) -Contextualized memory for specific users +!!! note "Personal Memory" -- **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](personal_memory/personal_memory.md) + Contextualized memory for specific users #### 🔧 **Tool Memory** @@ -76,7 +72,10 @@ Learn more about how to use tool memory from [tool memory](tool_memory/tool_memo --- -## 🛠️ Installation + Learn more about how to use personal memory from [personal memory](personal_memory/personal_memory.md) + + +## Installation ### Install from PyPI (Recommended) @@ -106,7 +105,7 @@ FLOW_EMBEDDING_BASE_URL=https://xxxx/v1 --- -## 🚀 Quick Start +## Quick Start ### HTTP Service Startup @@ -545,25 +544,7 @@ You can find more details in [tool_bench.md](tool_memory/tool_bench.md) and the --- -## 🤝 Contribution - -We believe the best memory systems come from collective wisdom. Contributions welcome 👉[Guide](contribution.md): - -### Code Contributions - -- New operation and tool development -- Backend implementation and optimization -- API enhancements and new endpoints - -### Documentation Improvements - -- Usage examples and tutorials -- Best practice guides - - ---- - -## 📄 Citation +## Citation ```bibtex @software{ReMe2025, @@ -573,16 +554,3 @@ We believe the best memory systems come from collective wisdom. Contributions we year = {2025} } ``` - ---- - -## ⚖️ License - -This project is licensed under the Apache License 2.0 - see the [LICENSE](https://github.com/modelscope/ReMe/blob/main/LICENSE) file for details. - ---- - -## Star History - -[![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/library/library.md b/docs/library/library.md index 9144a9cb..37c390ca 100644 --- a/docs/library/library.md +++ b/docs/library/library.md @@ -38,8 +38,18 @@ new: true -

+ + +