{"data":{"slug":"nvidia-nemo-guardrails","name":"Guardrails","tagline":"Open-source toolkit for adding programmable guardrails to LLM-based conversational systems","github_url":"https://github.com/NVIDIA-NeMo/Guardrails","owner":"NVIDIA-NeMo","repo":"Guardrails","owner_avatar_url":"https://avatars.githubusercontent.com/u/213689629?v=4","primary_language":"Python","stars":7101,"forks":831,"topics":["agents","generative-ai","guardrails","llm-safety","llm-security","llms","nvidia","python","safety"],"archived":false,"github_pushed_at":"2026-09-10T20:29:26+00:00","maintenance_label":"Very active","stars_delta_30d":206,"url":"https://www.graphcanon.com/tools/nvidia-nemo-guardrails","markdown_url":"https://www.graphcanon.com/tools/nvidia-nemo-guardrails.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/nvidia-nemo-guardrails","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=nvidia-nemo-guardrails","description":"NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.","homepage_url":"https://docs.nvidia.com/nemo/guardrails/latest/index.html","license":"Other","open_issues":228,"watchers":43,"ai_summary":"NVIDIA-NeMo/Guardrails is an open-source project aimed at providing a framework to add programmable guardrails in LLM-based conversational applications.","readme_excerpt":"## Requirements\n\nPython 3.10, 3.11, 3.12 or 3.13.\n\n---\n\n## Installation\n\nTo install using pip:\n\n```bash\n> pip install nemoguardrails\n```\n\nFor more detailed instructions, see the [Installation Guide](https://docs.nvidia.com/nemo/guardrails/get-started/installation-guide).\n\n---\n\n## License\n\nThe NeMo Guardrails library is licensed under the [Apache License, Version 2.0](http://www.apache.org/licenses/LICENSE-2.0).","github_created_at":"2023-04-18T12:32:47+00:00","created_at":"2026-07-15T10:42:10.101339+00:00","updated_at":"2026-09-20T04:25:43.032082+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"}],"tags":[{"slug":"agents","name":"agents"},{"slug":"generative-ai","name":"generative-ai"},{"slug":"guardrails","name":"guardrails"},{"slug":"llm-safety","name":"llm-safety"},{"slug":"llm-security","name":"llm-security"},{"slug":"llms","name":"llms"},{"slug":"nvidia","name":"nvidia"},{"slug":"python","name":"python"}],"trust":{"provenance":{"is_fork":false,"github_id":629494390,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-11T06:00:30.268Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":2,"days_since_push":0,"last_release_at":"2026-08-26T19:31:04Z","stars_delta_30d":206,"open_issues_delta_30d":23},"security_summary":{"status":"ok","scanner":"osv@v1","low_count":0,"high_count":0,"last_scan_at":"2026-07-15T10:42:11.494Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-09-11T06:00:30.765Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-09-11T06:00:30.765Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-09-11T06:00:30.765Z","managed_saas":false},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-09-11T06:00:30.765Z"},"languages":{"value":["python","javascript"],"source":"github.language+package.json+pyproject.toml","observed_at":"2026-09-11T06:00:30.765Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-09-11T06:00:30.765Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-09-11T06:00:30.765Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Requires Python versions between 3.10 to 3.13."],"min_ram_gb":null,"requires_docker":false},"constraints":{"min_ram_gb":null,"requires_docker":false},"when_to_use":["You are working within the NVIDIA ecosystem and would benefit from its extensive support for AI applications.","Your project requires a Python-based solution with compatibility for versions 3.10 through 3.13."],"when_not_to_use":["If your development does not leverage NVIDIA's technologies, using Guardrails may not provide the expected ease of integration.","For projects that cannot use Python or require support outside of versions 3.10 to 3.13, this tool would be unsuitable."],"source":"enrich:decision_facts","observed_at":"2026-07-17T01:10:35.048Z"},"constraint_facets":{"min_ram_gb":null,"requires_docker":false},"decision_summary":[{"label":"Requirements","value":"Requires Python versions between 3.10 to 3.13."},{"label":"Adopt for","value":"Guardrails offers an open-source toolkit from NVIDIA for programmers to set safety constraints in conversational systems built on large language models."},{"label":"License detail","value":"The Apache License, Version 2.0 allows for free use and modification provided that the original license is included in any distribution."}]}}