{"id":28753429,"url":"https://github.com/google-deepmind/simulation_streams","last_synced_at":"2025-10-26T17:14:48.730Z","repository":{"id":275561204,"uuid":"924041547","full_name":"google-deepmind/simulation_streams","owner":"google-deepmind","description":"Simulation Streams is a programming paradigm designed to efficiently control and leverage Large Language Models (LLMs) for complex, dynamic simulations and agentic workflows.","archived":false,"fork":false,"pushed_at":"2025-03-06T17:32:55.000Z","size":96,"stargazers_count":14,"open_issues_count":0,"forks_count":2,"subscribers_count":8,"default_branch":"main","last_synced_at":"2025-03-06T18:34:20.700Z","etag":null,"topics":["agents","ai","llms","simulations"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/google-deepmind.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","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}},"created_at":"2025-01-29T10:06:33.000Z","updated_at":"2025-03-06T17:32:59.000Z","dependencies_parsed_at":"2025-03-06T18:36:45.536Z","dependency_job_id":null,"html_url":"https://github.com/google-deepmind/simulation_streams","commit_stats":null,"previous_names":["google-deepmind/simulation_streams"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/google-deepmind/simulation_streams","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/google-deepmind%2Fsimulation_streams","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/google-deepmind%2Fsimulation_streams/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/google-deepmind%2Fsimulation_streams/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/google-deepmind%2Fsimulation_streams/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/google-deepmind","download_url":"https://codeload.github.com/google-deepmind/simulation_streams/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/google-deepmind%2Fsimulation_streams/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":260268635,"owners_count":22983601,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":["agents","ai","llms","simulations"],"created_at":"2025-06-17T00:40:04.236Z","updated_at":"2025-10-26T17:14:43.695Z","avatar_url":"https://github.com/google-deepmind.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# simulation_streams\n\n[Simulation Streams Tech Report](https://arxiv.org/abs/2501.18668)\n\nA development platform for simulations with large language models.\nIt comes with an Entity-Component-Systems approach and graphical editor.\n\nThe platform is a flask app most easily used locally in a venv,\nwhich can be started with source setup.sh (on linux). This sets up all\ndependencies and ends with instructions for the different commands for\nlaunching the editor or command line running. The editor is displayed in a\nbrowser.\n\nA library of simulation configs can be found under configs,\nincluding a market economy, a social simulation and 6 tasks from\nthe classical reinforcement learning literature.\n\n## Usage examples\n\n1 **source setup.sh**\n\n2a **To create the local server that runs the web app:**\n\n    ```\n    python app.py configs/social_catch_game.py --metrics=configs/metrics_social_catch_game.txt --web --model='gemini-2.0-flash-exp' --api_key='your_key'\n    ```\n\n2b **To run a number of steps from the command line and return the metrics:**\n\n    ```\n    python app.py configs/social_catch_game.py --metrics=configs/metrics_social_catch_game.txt --steps=10 --model='gemini-2.0-flash-exp' --api_key='your_key'\n    ```\n\n2c **To open the editor with an empty config:**\n\n    ```\n    python app.py --web --model='gemini-2.0-flash-exp' --api_key='your_key'\n    ```\n\n2d **To use the generic code_world config with task-specific functions:**\n\n    ```\n    python app.py configs/code_world.py --web --model='gemini-2.0-pro-exp' --api_key='your_key' --task_name='maze'\n    ```\n\nThis example demonstrates using the generic code_world configuration to run\na maze task. The task_name parameter imports task-specific functions from\nthe corresponding Python module, allowing you to implement custom\nenvironments in pure Python while leveraging the simulation streams\nframework.\n\n## Citing Simulation Streams\n\nIf you use Simulation Streams in your work,\nplease cite the accompanying article:\n\n```\n@article{sunehag2025simulation,\n  title={Simulation Streams: A Programming Paradigm for Controlling Large Language Models and Building Complex Systems with Generative AI.},\n  author={Sunehag, Peter and Leibo, Joel Z},\n  journal={arXiv preprint arXiv:2501.18668},\n  year={2025}\n}\n```\n\n## Disclaimer\n\nThis is not an officially supported Google product.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgoogle-deepmind%2Fsimulation_streams","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgoogle-deepmind%2Fsimulation_streams","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgoogle-deepmind%2Fsimulation_streams/lists"}