Add model card with paper and code links

README.md

@@ -1,3 +1,69 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+# MemoBrain: 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 the reasoning agent, MemoBrain organizes reasoning progress without blocking execution and actively manages the working context. Specifically, it prunes invalid steps, folds completed sub-trajectories, and preserves a compact, high-salience reasoning backbone under a fixed context budget.
+
+- **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)
+
+## Model Description
+
+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
+
+The model can be deployed using [vLLM](https://github.com/vllm-project/vllm) and utilized via the `memobrain` Python package.
+
+### Basic Usage
+
+```python
+import asyncio
+from memobrain import MemoBrain
+
+async def main():
+    # Step 1: Initialize MemoBrain
+    # Assuming model is deployed via vLLM: vllm serve TommyChien/MemoBrain-8B --port 8002
+    memory = MemoBrain(
+        api_key="EMPTY",  # vLLM doesn't require API key
+        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
+    # Episodic unit: 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}
+}
+```