{"id":31681353,"url":"https://github.com/romanslack/simuverse-test-environment-v1","last_synced_at":"2026-02-19T22:34:03.635Z","repository":{"id":275346901,"uuid":"925818055","full_name":"RomanSlack/SimuVerse-Test-Environment-V1","owner":"RomanSlack","description":null,"archived":false,"fork":false,"pushed_at":"2025-04-25T14:25:16.000Z","size":384,"stargazers_count":4,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-10-08T07:48:52.621Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/RomanSlack.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-02-01T20:22:51.000Z","updated_at":"2025-07-25T20:16:39.000Z","dependencies_parsed_at":"2025-02-01T21:28:53.048Z","dependency_job_id":"3bc820a8-a395-496d-97fb-5ee8fa38e0c6","html_url":"https://github.com/RomanSlack/SimuVerse-Test-Environment-V1","commit_stats":null,"previous_names":["romanslack/simuverse-test-environment-v1"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/RomanSlack/SimuVerse-Test-Environment-V1","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RomanSlack%2FSimuVerse-Test-Environment-V1","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RomanSlack%2FSimuVerse-Test-Environment-V1/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RomanSlack%2FSimuVerse-Test-Environment-V1/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RomanSlack%2FSimuVerse-Test-Environment-V1/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/RomanSlack","download_url":"https://codeload.github.com/RomanSlack/SimuVerse-Test-Environment-V1/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RomanSlack%2FSimuVerse-Test-Environment-V1/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29635657,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-19T22:32:43.237Z","status":"ssl_error","status_checked_at":"2026-02-19T22:32:38.330Z","response_time":117,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-10-08T07:48:08.805Z","updated_at":"2026-02-19T22:34:03.616Z","avatar_url":"https://github.com/RomanSlack.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# SimuVerse: Multi-Agent Interactive Simulation Environment\n\nSimuVerse is a dynamic multi-agent simulation framework that enables AI agents to interact in a social environment, move around autonomously, and engage in conversations. The project creates a visual grid-based interface where different LLM-powered agents can form connections, communicate, and navigate their social world.\n\n## Features\n\n- **Interactive Agent Grid**: Visualize agents and their connections in real-time\n- **Dynamic Movement**: Agents autonomously move to meet new conversation partners\n- **Multi-LLM Support**: Use OpenAI, Claude, Hugging Face, and other LLM providers\n- **Conversation Tracking**: Monitor and visualize agent interactions\n- **Agent Personality Settings**: Adjust memory and personality strength parameters\n- **Movement Intent Detection**: Agents can explicitly request to move using commands\n\n## Installation\n\n1. Clone the repository:\n```bash\ngit clone https://github.com/yourusername/SimuVerse.git\ncd SimuVerse\n```\n\n2. Create a virtual environment (recommended):\n```bash\npython -m venv venv\nsource venv/bin/activate  # On Windows: venv\\Scripts\\activate\n```\n\n3. Install the required packages:\n```bash\npip install -r requirements.txt\n```\n\n4. Create a `.env` file with your API keys:\n```\nOPENAI_API_KEY=your_openai_api_key_here\nCLAUDE_API_KEY=your_claude_api_key_here\n```\n\n## Running the Simulation\n\nTo start the web-based simulation interface:\n\n```bash\npython simulation_grid_test.py\n```\n\nThen open your browser and navigate to `http://127.0.0.1:8050/` to view the simulation.\n\n## How It Works\n\n### Agent Framework\n\nThe core of SimuVerse is a flexible multi-agent framework that supports various LLM providers:\n\n- **BaseLLM Interface**: Abstract class for implementing different LLM backends\n- **Agent Class**: Manages agent state, conversation history, and movement requests\n- **MultiAgentFramework**: Container for managing multiple agents and their interactions\n\n### Simulation Environment\n\nThe simulation runs in a grid-based environment where:\n\n1. Agents are positioned on a 2D grid\n2. Connections form between agents based on proximity\n3. Connected agents exchange messages\n4. After 2-3 conversation rounds, agents may decide to move\n5. Movement can be triggered automatically or by agent request using `[MOVE]` command\n\n### User Interface\n\nThe web interface allows you to:\n\n- Visualize agent positions and connections\n- Track conversation logs between agents\n- Monitor movement probabilities and intentions\n- Step through the simulation\n- Manually reposition agents\n- Adjust agent memory and personality settings\n\n## Agent Movement Mechanisms\n\nAgents can move in two ways:\n\n1. **Autonomous Movement**: After 2-3 rounds of conversation, agents build up a probability of moving based on their personality and conversation duration.\n\n2. **Explicit Movement Requests**: Agents can include `[MOVE]` in their responses to explicitly request movement to meet someone new.\n\n## Next Steps: Taking SimuVerse to the Next Level\n\nHere are some exciting directions for future development:\n\n### 1. Enhanced Environment\n\n- **Multiple Rooms/Zones**: Create distinct areas with different conversation topics or themes\n- **Environmental Factors**: Introduce noise, crowding, or other factors that affect communication\n- **Resource Management**: Add resources agents must gather, share, or compete for\n- **Day/Night Cycles**: Implement time progression affecting agent behavior\n- **Weather/Conditions**: Environmental factors that influence mood or behavior\n\n### 2. Advanced Agent Capabilities\n\n- **Goal-Directed Behavior**: Allow agents to form and pursue goals\n- **Learning \u0026 Memory**: Implement more sophisticated memory models and learning from interactions\n- **Emotional States**: Track agent emotions and have them affect interactions\n- **Relationship Development**: Track relationship status between agent pairs\n- **Tool Usage**: Allow agents to use various tools in the environment\n- **Advanced Movement Commands**: Let agents specify direction, destination, or companions\n\n### 3. Improved Visualization \u0026 Analysis\n\n- **Network Analysis**: Add social network metrics and visualization\n- **Conversation Heatmaps**: Show areas with most active conversations\n- **Time-series Analysis**: Track and visualize how relationships evolve over time\n- **Agent Journey Maps**: Trace paths of agents through social space\n- **3D Visualization**: Upgrade to a 3D visualization for more immersive experience\n\n### 4. System Architecture Improvements\n\n- **Scalability**: Optimize for hundreds or thousands of agents\n- **Distributed Computation**: Allow simulation to run across multiple machines\n- **Persistent Storage**: Save simulation states to database for long-running experiments\n- **API Integration**: Connect with external systems and data sources\n- **Containerization**: Package the system in Docker for easy deployment\n\n### 5. User Experience Enhancements\n\n- **Interactive Timeline**: Scroll through simulation history\n- **Agent Configuration UI**: More detailed controls for agent creation and modification\n- **Scenario Builder**: Create pre-defined scenarios and experiments\n- **Mobile-Friendly Design**: Better support for mobile devices\n- **Real-time Intervention**: Allow users to send messages or commands to agents during simulation\n\n### 6. Research Applications\n\n- **Sociological Modeling**: Study emergent social behaviors\n- **Communication Patterns**: Analyze how information spreads through agent networks\n- **Group Formation**: Study how cliques, communities, and hierarchies form\n- **Cultural Evolution**: Model how cultural norms develop and spread\n- **Misinformation Studies**: Track how false information propagates through networks\n\n### 7. Integration with Unity or Game Engines\n\n- **Upgrade to Unity**: Move the visualization layer to Unity for more sophisticated rendering\n- **VR Support**: Enable virtual reality viewing of the simulation\n- **Interactive Objects**: Add interactive objects and environments within the simulation\n- **Physics-Based Movement**: Implement realistic movement with collision detection\n- **Advanced Animation**: Add character models and animations for more realistic representation\n\n## Contributing\n\nContributions are welcome! Please feel free to submit a Pull Request.\n\n## License\n\nThis project is licensed under the MIT License - see the LICENSE file for details.\n\n## Acknowledgments\n\n- This project uses [Dash](https://dash.plotly.com/) for the web interface\n- Agent networks are visualized using [Cytoscape.js](https://js.cytoscape.org/)\n- LLM capabilities are provided by OpenAI and Anthropic APIs","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fromanslack%2Fsimuverse-test-environment-v1","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fromanslack%2Fsimuverse-test-environment-v1","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fromanslack%2Fsimuverse-test-environment-v1/lists"}