Update README.md

README.md

@@ -11,7 +11,38 @@ license: mit
 short_description: AI Knowledge Tree Builder AI
 ---
 
-AIKnowledgeTreeBuilder is designed with the following tenets: 
+# AI Knowledge Tree Builder with Agents 🌳✨
+
+An enhanced Streamlit app integrating Transformers Agents into a Mixture of Experts (MoE) system for smarter knowledge tree building! 🤓
+
+## Features 🎉
+- 9 Agents assisting ML tasks:
+  - **CodeCrafter 🖥️**: Writes code (CodeAgent).
+  - **StepSage 🧠**: Step-by-step reasoning (ReactCodeAgent).
+  - **JsonJugger 🤡**: JSON-based actions (ReactJsonAgent).
+  - **OutlineOracle 📋**: Builds outlines.
+  - **ToolTitan 🔧**: Lists tools.
+  - **SpecSpinner 📜**: Crafts specs.
+  - **ImageImp 🎨**: Generates image prompts.
+  - **VisualVortex 🖼️**: Creates visuals.
+  - **GlossGuru 📖**: Defines terms.
+- MoE system maps prompts to agents for dynamic task handling.
+- Witty, emoji-rich UI! 😂
+
+## Functions 📚
+- `run_agent(task, agent_name)`: Executes the specified agent’s `run` method.
+- `main()`: Orchestrates UI and agent interactions.
+
+## Setup 🛠️
+1. `pip install -r requirements.txt`
+2. `streamlit run app.py`
+3. Pick an MoE prompt and query away! 🚀
+
+## Notes 📝
+- Default LLM uses HF Inference API. Add a token for private models via `HF_TOKEN`.
+- Extends original SynapTree with agent-based MoE.
+
+AgentsKnowledgeTreeBuilder is designed with the following tenets: 
 1. Portability - Universal access via any device & link sharing 
 2. Speed of Build - Rapid deployments (< 2min to production) 
 3. Linkiness - Programmatic access to major AI knowledge sources