Add model card and metadata

This PR adds a comprehensive model card for MemoBrain-8B, including:
- Metadata for `pipeline_tag` (`text-generation`) and `library_name` (`transformers`).
- A link to the paper: [MemoBrain: Executive Memory as an Agentic Brain for Reasoning](https://huggingface.co/papers/2601.08079).
- A link to the official GitHub repository.
- Detailed sample usage for both vLLM deployment and Python integration based on the provided documentation.

README.md

@@ -1,3 +1,84 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- memory
+- agent
+- reasoning
+- tool-use
+---
+
+# MemoBrain-8B: Executive Memory as an Agentic Brain for Reasoning
+
+MemoBrain is an executive memory model for tool-augmented agents that constructs a dependency-aware memory over reasoning steps, capturing salient intermediate states and their logical relations. Operating as a co-pilot alongside a reasoning agent, MemoBrain organizes reasoning progress without blocking execution and actively manages the working context.
+
+- **Paper:** [MemoBrain: Executive Memory as an Agentic Brain for Reasoning](https://huggingface.co/papers/2601.08079)
+- **Repository:** [https://github.com/qhjqhj00/MemoBrain](https://github.com/qhjqhj00/MemoBrain)
+
+## Overview
+
+MemoBrain introduces an **executive memory system** that acts as a cognitive co-pilot for reasoning agents. Unlike traditional approaches that passively accumulate context, MemoBrain actively manages the reasoning trajectory by:
+
+1. **Memory Construction**: Building a dependency-aware graph of reasoning steps.
+2. **Flush**: Removing invalid or redundant reasoning nodes.
+3. **Fold**: Compressing completed sub-trajectories into compact summaries.
+4. **Context Management**: Maintaining a fixed-size, high-salience reasoning backbone.
+
+## Usage
+
+### Deploy with vLLM
+
+The model can be served using [vLLM](https://github.com/vllm-project/vllm) to create an OpenAI-compatible API endpoint:
+
+```bash
+pip install vllm
+vllm serve TommyChien/MemoBrain-8B --port 8002
+```
+
+### Python API
+
+After installing the `memobrain` package from the [official repository](https://github.com/qhjqhj00/MemoBrain), you can use the model as follows:
+
+```python
+import asyncio
+from memobrain import MemoBrain
+
+async def main():
+    # Step 1: Initialize MemoBrain
+    # Note: vLLM doesn't require an actual API key
+    memory = MemoBrain(
+        api_key="EMPTY",  
+        base_url="http://localhost:8002/v1",
+        model_name="TommyChien/MemoBrain-8B"
+    )
+    
+    # Step 2: Initialize memory with your task
+    memory.init_memory("Solve a complex research problem")
+    
+    # Step 3: Memorize conversation interactions
+    # Recommended unit is an episode: thinking -> tool call -> tool response
+    await memory.memorize([
+        {"role": "assistant", "content": "I need to search for information about Paris..."},
+        {"role": "user", "content": "Search results: Paris is the capital of France..."}
+    ])
+    
+    # Step 4: Optimize memory (flush invalid steps & fold completed sub-trajectories)
+    optimized_messages = await memory.recall()
+    print(f"Memory optimized: {len(optimized_messages)} messages")
+
+asyncio.run(main())
+```
+
+## Citation
+
+If you find MemoBrain useful for your research, please cite:
+
+```bibtex
+@article{memobrain2026,
+  title={MemoBrain: Executive Memory as an Agentic Brain for Reasoning},
+  author={Hongjin Qian, Zhao Cao, Zheng Liu},
+  journal={arXiv preprint arXiv:2601.08079},
+  year={2026}
+}
+```