{"data":{"slug":"expectedparrot-edsl","name":"edsl","tagline":"Framework for designing and analyzing AI-powered surveys and experiments","github_url":"https://github.com/expectedparrot/edsl","owner":"expectedparrot","repo":"edsl","owner_avatar_url":"https://avatars.githubusercontent.com/u/101932709?v=4","primary_language":"Python","stars":491,"forks":79,"topics":["anthropic","data-labeling","deepinfra","domain-specific-language","experiments","llama2","llm","llm-agent","llm-framework","llm-inference","market-research","mixtral","open-source","openai","python","social-science","surveys","synthetic-data"],"archived":false,"github_pushed_at":"2026-08-23T13:51:41+00:00","maintenance_label":"Very active","stars_delta_30d":8,"url":"https://www.graphcanon.com/tools/expectedparrot-edsl","markdown_url":"https://www.graphcanon.com/tools/expectedparrot-edsl.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/expectedparrot-edsl","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=expectedparrot-edsl","description":"Design, conduct and analyze results of AI-powered surveys and experiments. Simulate social science and market research with large numbers of AI agents and LLMs.","homepage_url":"https://docs.expectedparrot.com","license":"MIT","open_issues":51,"watchers":7,"ai_summary":"expectedparrot/edsl is a Python-based platform to design, conduct, and analyze results of AI-powered surveys and experiments, particularly useful in social science and market research through simulation with large numbers of AI agents and LLMs.","readme_excerpt":"## Getting started\n\n1. Run `pip install edsl` to install the package. See <a href=\"https://www.expectedparrot.com/getting-started\" target=\"_blank\" rel=\"noopener noreferrer\">instructions</a>.\n\n2. <a href=\"https://www.expectedparrot.com/login\" target=\"_blank\" rel=\"noopener noreferrer\">Create an account</a> to run surveys at the Expected Parrot server and access a <a href=\"https://docs.expectedparrot.com/en/latest/remote_caching\" target=\"_blank\" rel=\"noopener noreferrer\">universal remote cache</a> of stored responses for reproducing results.\n\n3. Choose whether to use your own keys for language models or get an Expected Parrot key to access all available models at once. Securely <a href=\"https://www.expectedparrot.com/getting-started/edsl-api-keys\" target=\"_blank\" rel=\"noopener noreferrer\">manage keys</a>,  expenses and usage for your team from your account.\n\n4. Run the <a href=\"https://docs.expectedparrot.com/en/latest/starter_tutorial\" target=\"_blank\" rel=\"noopener noreferrer\">starter tutorial</a> and explore other demo notebooks for a variety of use cases. \n\n5. Share workflows and survey results at <a href=\"https://www.expectedparrot.com/login\" target=\"_blank\" rel=\"noopener noreferrer\">Coop</a>: a free platform for creating and sharing AI research.\n\n6. Join our <a href=\"https://discord.com/invite/mxAYkjfy9m\" target=\"_blank\" rel=\"noopener noreferrer\">Discord</a> for updates and discussions!\n\n---\n\n## Requirements\n- Python 3.9 - 3.13\n- API keys for language models. You can use your own keys or an Expected Parrot key that provides access to all available models.\nSee instructions on <a href=\"https://docs.expectedparrot.com/en/latest/api_keys\" target=\"_blank\" rel=\"noopener noreferrer\">managing keys</a> and <a href=\"https://www.expectedparrot.com/models\" target=\"_blank\" rel=\"noopener noreferrer\">model pricing and performance</a> information.","github_created_at":"2024-01-02T22:18:47+00:00","created_at":"2026-07-11T11:46:02.607724+00:00","updated_at":"2026-08-25T12:00:58.448658+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"anthropic","name":"anthropic"},{"slug":"data-labeling","name":"data-labeling"},{"slug":"domain-specific-language","name":"domain-specific-language"},{"slug":"llm-agent","name":"llm-agent"},{"slug":"market-research","name":"market-research"},{"slug":"social-science","name":"social-science"},{"slug":"surveys","name":"surveys"},{"slug":"synthetic-data","name":"synthetic-data"}],"trust":{"provenance":{"is_fork":false,"github_id":738290765,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-25T12:00:57.463Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":0,"days_since_push":1,"last_release_at":"2026-03-13T08:40:15Z","stars_delta_30d":8,"open_issues_delta_30d":9},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:46:03.739Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-25T12:00:58.129Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-08-25T12:00:58.129Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-08-25T12:00:58.129Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-08-25T12:00:58.129Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When conducting complex simulations of social science studies that require the use of multiple AI agents or interactions with LLMs.","For market research scenarios where the design calls for analysis using a high volume of synthetic data generated by different levels of language models."],"when_not_to_use":["If your project requires real human responses and feedback in experiments, edsl is a system designed around AI agents rather than living participants.","In cases where the scope of the experiment does not involve social science or require significant simulation capabilities with large numbers of AI entities."],"source":"enrich:decision_facts","observed_at":"2026-07-15T10:08:45.110Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"edsl stands out for designing AI-powered surveys and experiments in social science and market research by letting users simulate large-scale studies involving multiple AI agents and LLMs."}]}}