| | --- |
| | title: 'RFT Agent Simulation Engine ' |
| | emoji: 🌖 |
| | colorFrom: yellow |
| | colorTo: green |
| | sdk: gradio |
| | sdk_version: 6.6.0 |
| | app_file: app.py |
| | pinned: false |
| | license: other |
| | short_description: Agent drift, torque & coherence simulator. |
| | --- |
| | |
| |
|
| | RFT Agent Simulation Engine — MVP Release |
| |
|
| | A symbolic multi‑agent simulation engine built to model drift, stability, coherence, and emergent behaviour in complex systems. |
| | Developed as the first operational software implementation of the Rendered Frame Theory (RFT) agent architecture. |
| |
|
| | This MVP provides a clean, modular, reproducible simulation environment that runs entirely in Python and is fully compatible with Google Colab and Hugging Face Spaces. |
| |
|
| | --- |
| |
|
| | 🚀 Features |
| |
|
| | ✔ Multi‑Agent Simulation |
| |
|
| | Each agent evolves over time through: |
| |
|
| | • Awareness field updates (Φ) |
| | • Collapse‑torque dynamics (τ_eff) |
| | • Mutation |
| | • Drift |
| | • Fitness scoring |
| | • Tier‑independent behaviour |
| | |
| | |
| | ✔ System‑Level Metrics |
| | |
| | The engine computes: |
| | |
| | • Coherence (average Φ across agents) |
| | • Stability (variance of Φ) |
| | • Emergent divergence patterns |
| | |
| | |
| | ✔ Full Visualization Suite |
| | |
| | Automatically generates and saves: |
| | |
| | • phi_plot.png |
| | • tau_plot.png |
| | • fitness_plot.png |
| | • coherence_plot.png |
| | • stability_plot.png |
| |
|
| |
|
| | All plots are high‑resolution (300 dpi). |
| |
|
| | ✔ JSON Export |
| |
|
| | Final agent states are exported to: |
| |
|
| | • final_agent_states.json |
| |
|
| |
|
| | ✔ One‑Click Packaging |
| |
|
| | A built‑in ZIP builder creates: |
| |
|
| | • rft_simulation_engine.zip |
| | containing all project files and generated artifacts. |
| |
|
| |
|
| | ✔ Colab‑Optimized Dev Mode |
| |
|
| | When running in Google Colab: |
| |
|
| | • Gradio UI is bypassed |
| | • Simulation runs automatically |
| | • Plots display inline |
| | • All files save to disk |
| |
|
| |
|
| | --- |
| |
|
| | 📦 Project Structure |
| |
|
| | agent.py # RFTAgent class |
| | simulation.py # RFTSimulation engine |
| | visualization.py # Plotting utilities |
| | utils.py # JSON export + ZIP builder |
| | app.py # Gradio UI + Colab dev mode |
| | test_runner.py # Automated test simulation |
| | requirements.txt # Dependencies |
| | README.md # Documentation |
| | |
| | |
| | --- |
| | |
| | ▶️ Running the Simulation (Colab) |
| | |
| | To run the engine in Google Colab: |
| | |
| | from test_runner import run_test_simulation |
| | run_test_simulation() |
| |
|
| |
|
| | This will: |
| |
|
| | • Run a 3‑agent, 100‑step simulation |
| | • Display all plots inline |
| | • Save all PNGs |
| | • Export final_agent_states.json |
| | • Print file paths |
| |
|
| |
|
| | --- |
| |
|
| | 🌐 Running the Gradio App (Hugging Face Space) |
| |
|
| | When deployed on Hugging Face: |
| |
|
| | python app.py |
| |
|
| |
|
| | The UI allows you to configure: |
| |
|
| | • Number of agents |
| | • Number of steps |
| | • Mutation rate |
| | • Drift rate |
| | • Random seed |
| |
|
| |
|
| | And outputs: |
| |
|
| | • All plots |
| | • JSON export |
| | • Downloadable results |
| |
|
| |
|
| | --- |
| |
|
| | 🧪 Example Output |
| |
|
| | The engine produces: |
| |
|
| | • Divergent agent trajectories |
| | • Torque evolution curves |
| | • Fitness progression |
| | • System coherence decay |
| | • Stability variance growth |
| |
|
| |
|
| | These behaviours emerge naturally from the agent update rules. |
| |
|
| | --- |
| |
|
| | 📁 Packaging the Project |
| |
|
| | To generate a ZIP containing all files and outputs: |
| |
|
| | from utils import zip_project |
| | zip_project() |
| |
|
| |
|
| | This creates: |
| |
|
| | • rft_simulation_engine.zip |
| | ready for download or distribution. |
| |
|
| |
|
| | --- |
| |
|
| | 🛠 Requirements |
| |
|
| | numpy |
| | matplotlib |
| | gradio |
| |
|
| |
|
| | --- |
| |
|
| | 📣 About This Project |
| |
|
| | This MVP demonstrates the first operational implementation of the RFT agent architecture. |
| | It is designed for: |
| |
|
| | • AI researchers |
| | • Complex systems modellers |
| | • Simulation engineers |
| | • Worldbuilders |
| | • Anyone exploring emergent behaviour |
| |
|
| |
|
| | Future versions will introduce: |
| |
|
| | • Agent packs |
| | • Mutation packs |
| | • Universe packs |
| | • Codex integration |
| | • Long‑run simulations |
| | • Advanced metrics |
| |
|
| |
|
| | --- |
| |
|
| | Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference |
| |
|
