Update README.md

README.md

@@ -7,12 +7,13 @@ colorFrom: yellow
 colorTo: indigo
 pinned: true
 sdk_version: 6.0.0
+short_description: A discovery engine
 ---
 # NexaSci Agent Kit
 
 A local-first scientific agent stack featuring the NexaSci Assistant (10B model), tool calling, Python sandbox execution, and scientific paper retrieval.
 
-## 🚀 Quick Start
+## Quick Start
 
 ### Prerequisites
 
@@ -78,7 +79,7 @@ A local-first scientific agent stack featuring the NexaSci Assistant (10B model)
    python examples/demo_agent.py --prompt "Your prompt here"
    ```
 
-## 📋 Components
+## Components
 
 - **NexaSci Assistant (LLM)**: 10B Falcon model post-trained for tool calling
 - **Model Server**: HTTP API for model inference (port 8001)
@@ -89,7 +90,7 @@ A local-first scientific agent stack featuring the NexaSci Assistant (10B model)
   - `papers.search_corpus`: Local corpus semantic search
 - **Agent Controller**: Orchestrates LLM ↔ tool server loop
 
-## 🛠️ Tools
+## Tools
 
 ### Python Sandbox
 Execute Python code with resource limits:
@@ -102,7 +103,7 @@ Execute Python code with resource limits:
 - **Paper Fetch**: Get detailed metadata
 - **Corpus Search**: Semantic search over local SPECTER2-embedded papers
 
-## 📝 Example Prompts
+## Example Prompts
 
 See `examples/sample_prompts.md` for example prompts that showcase:
 - Python code generation
@@ -110,7 +111,7 @@ See `examples/sample_prompts.md` for example prompts that showcase:
 - Experimental design
 - Combined reasoning workflows
 
-## 🔧 Configuration
+## Configuration
 
 Edit `agent/config.yaml` to configure:
 - Model paths and settings
@@ -118,7 +119,7 @@ Edit `agent/config.yaml` to configure:
 - Tool server URLs
 - Sandbox limits
 
-## 📚 Project Structure
+## Project Structure
 
 ```
 Agent_kit/
@@ -136,7 +137,7 @@ Agent_kit/
 └── docker-compose.yml  # Docker orchestration
 ```
 
-## 🐳 Docker Details
+## Docker Details
 
 The Docker setup includes:
 - **Base Image**: `nvidia/cuda:12.1.0-runtime-ubuntu22.04`
@@ -153,7 +154,7 @@ docker build -t nexasci-agent:latest .
 docker-compose up
 ```
 
-## 🔍 Troubleshooting
+## Troubleshooting
 
 ### GPU Not Available
 ```bash
@@ -175,13 +176,13 @@ pip install torch torchvision torchaudio --index-url https://download.pytorch.or
 - Verify model path in config
 - Check HuggingFace cache: `~/.cache/huggingface/`
 
-## 📖 Documentation
+## Documentation
 
 - **Quick Start**: See `QUICKSTART.md` for detailed setup
 - **Specification**: See `Spec.md` for architecture details
 - **Sample Prompts**: See `examples/sample_prompts.md`
 
-## 🙏 Acknowledgments
+## Acknowledgments
 
 - Model: `Allanatrix/Nexa_Sci_distilled_Falcon-10B`
 - SPECTER2: `allenai/specter2_base`