{"data":{"slug":"uptrain-ai-uptrain","name":"uptrain","tagline":"Unified platform for evaluating and improving Generative AI applications","github_url":"https://github.com/uptrain-ai/uptrain","owner":"uptrain-ai","repo":"uptrain","owner_avatar_url":"https://avatars.githubusercontent.com/u/114582870?v=4","primary_language":"Python","stars":2359,"forks":204,"topics":["autoevaluation","evaluation","experimentation","hallucination-detection","jailbreak-detection","llm-eval","llm-prompting","llm-test","llmops","machine-learning","monitoring","openai-evals","prompt-engineering","root-cause-analysis"],"archived":false,"github_pushed_at":"2024-08-18T13:30:44+00:00","maintenance_label":"Dormant","stars_delta_30d":4,"url":"https://www.graphcanon.com/tools/uptrain-ai-uptrain","markdown_url":"https://www.graphcanon.com/tools/uptrain-ai-uptrain.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/uptrain-ai-uptrain","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=uptrain-ai-uptrain","description":"UpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform root cause analysis on failure cases and give insights on how to resolve them.","homepage_url":"https://uptrain.ai/","license":"Apache-2.0","open_issues":58,"watchers":18,"ai_summary":"UpTrain offers preconfigured checks to evaluate various aspects of Generative AI such as language and code generation, embedding use-cases, and more. It provides insights into root cause analysis for failure cases.","readme_excerpt":"### Install the package through pip:\n```bash\npip install uptrain\n```\n\n---\n\n# License 💻\n\nThis repo is published under Apache 2.0 license and we are committed to adding more functionalities to the UpTrain open-source repo. We also have a managed version if you just want a more hands-off experience. Please book a [demo call here](https://calendly.com/uptrain-sourabh/30min).\n\n<br />","github_created_at":"2022-11-07T07:29:06+00:00","created_at":"2026-07-07T17:42:35.869986+00:00","updated_at":"2026-08-20T12:02:20.951074+00:00","categories":[{"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"}],"tags":[{"slug":"autoevaluation","name":"autoevaluation"},{"slug":"evaluation","name":"evaluation"},{"slug":"experimentation","name":"experimentation"},{"slug":"hallucination-detection","name":"hallucination-detection"},{"slug":"jailbreak-detection","name":"jailbreak-detection"},{"slug":"llm-eval","name":"llm-eval"},{"slug":"llm-prompting","name":"llm-prompting"},{"slug":"llm-test","name":"llm-test"}],"trust":{"provenance":{"is_fork":false,"github_id":562754304,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-20T12:02:20.150Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":731,"last_release_at":"2024-05-14T09:18:58Z","stars_delta_30d":4,"open_issues_delta_30d":3},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:21:26.628Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-20T12:02:20.608Z"},"deploy":{"source":"dockerfile:docker-compose.yml","self_host":true,"observed_at":"2026-08-20T12:02:20.608Z","managed_saas":false},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-08-20T12:02:20.608Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-08-20T12:02:20.608Z"},"has_docker":{"value":true,"source":"dockerfile:docker-compose.yml","observed_at":"2026-08-20T12:02:20.608Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-20T12:02:20.608Z"}},"decision_facts":{"hosting":{"model":"self_hosted","summary":"UpTrain can be installed on-premises using pip or accessed through a managed version."},"pricing":null,"requirements":null,"constraints":{"hosting_model":"self_hosted"},"when_to_use":["- When you need to evaluate Generative AI applications across various use-cases including language models, code generation, and embeddings.","- If your project requires automating the evaluation process with 20+ preconfigured checks designed for specific tasks like hallucination detection or jailbreak prevention."],"when_not_to_use":["- When your application does not require extensive monitoring or do not need insights into improving Generative AI performance through root cause analysis.","- If you prioritize a highly hands-off user experience without the capability to customize evaluation checks, consider using UpTrain's managed version instead of self-managing it."],"source":"enrich:decision_facts","observed_at":"2026-07-11T02:59:08.981Z"},"constraint_facets":{"hosting_model":"self_hosted"},"decision_summary":[{"label":"Hosting","value":"self hosted - UpTrain can be installed on-premises using pip or accessed through a managed version."},{"label":"Adopt for","value":"UpTrain, an open-source platform, evaluates and enhances Generative AI applications with preconfigured checks, root cause analysis, and actionable insights."},{"label":"License detail","value":"The tool is available under the Apache-2.0 license, suitable for both free and commercial use with appropriate attribution."}]}}