{"data":{"slug":"raga-ai-hub-ragaai-catalyst","name":"RagaAI-Catalyst","tagline":"Python SDK for AI agent observability and evaluation","github_url":"https://github.com/raga-ai-hub/RagaAI-Catalyst","owner":"raga-ai-hub","repo":"RagaAI-Catalyst","owner_avatar_url":"https://avatars.githubusercontent.com/u/161833182?v=4","primary_language":"Python","stars":16148,"forks":3565,"topics":["agentic-ai","agentic-ai-development","agentneo","agents","ai-agent-monitoring","ai-application-debugging","ai-evaluation-tools","ai-performance-optimization","ai-tool-interaction-monitoring","llm-testing","llm-tracing","llmops"],"archived":false,"github_pushed_at":"2026-02-11T14:43:33+00:00","maintenance_label":"Slowing","stars_delta_30d":5,"url":"https://www.graphcanon.com/tools/raga-ai-hub-ragaai-catalyst","markdown_url":"https://www.graphcanon.com/tools/raga-ai-hub-ragaai-catalyst.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/raga-ai-hub-ragaai-catalyst","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=raga-ai-hub-ragaai-catalyst","description":"Python SDK for Agent AI Observability, Monitoring and Evaluation Framework. Includes features like agent, llm and tools tracing, debugging multi-agentic system, self-hosted dashboard and advanced analytics with timeline and execution graph view ","homepage_url":"https://catalyst.raga.ai/","license":"Apache-2.0","open_issues":34,"watchers":37,"ai_summary":"RagaAI-Catalyst is a Python-based framework that provides tools for the monitoring, tracing, debugging, and evaluation of AI agents and multi-agentic systems. It includes features such as self-hosted dashboard support with advanced analytics and visualization.","readme_excerpt":"## Installation\n\nTo install RagaAI Catalyst, you can use pip:\n\n```bash\npip install ragaai-catalyst\n```\n\n---\n\n# Get specific deployment id with guardrails information\ndeployment_id_detail = gdm.get_deployment(17)\nprint('deployment_id_detail:', deployment_id_detail)\n\n---\n\n# Add guardrails to a deployment id\nguardrails_config = {\"guardrailFailConditions\": [\"FAIL\"],\n                     \"deploymentFailCondition\": \"ALL_FAIL\",\n                     \"alternateResponse\": \"Your alternate response\"}\n\nguardrails = [\n    {\n      \"displayName\": \"Response_Evaluator\",\n      \"name\": \"Response Evaluator\",\n      \"config\":{\n          \"mappings\": [{\n                        \"schemaName\": \"Text\",\n                        \"variableName\": \"Response\"\n                    }],\n          \"params\": {\n                    \"isActive\": {\"value\": False},\n                    \"isHighRisk\": {\"value\": True},\n                    \"threshold\": {\"eq\": 0},\n                    \"competitors\": {\"value\": [\"Google\",\"Amazon\"]}\n                }\n      }\n    },\n    {\n      \"displayName\": \"Regex_Check\",\n      \"name\": \"Regex Check\",\n      \"config\":{\n          \"mappings\": [{\n                        \"schemaName\": \"Text\",\n                        \"variableName\": \"Response\"\n                    }],\n          \"params\":{\n              \"isActive\": {\"value\": False},\n              \"isHighRisk\": {\"value\": True},\n              \"threshold\": {\"lt1\": 1}\n          }\n      }\n    }\n]\n\ngdm.add_guardrails(deployment_id, guardrails, guardrails_config)","github_created_at":"2024-08-26T12:13:15+00:00","created_at":"2026-07-07T17:41:36.433231+00:00","updated_at":"2026-08-20T06:01:23.580222+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":"agentic-ai","name":"agentic-ai"},{"slug":"agentic-ai-development","name":"agentic-ai-development"},{"slug":"agentneo","name":"agentneo"},{"slug":"agents","name":"agents"},{"slug":"ai-agent-monitoring","name":"ai-agent-monitoring"},{"slug":"ai-application-debugging","name":"ai-application-debugging"},{"slug":"ai-evaluation-tools","name":"ai-evaluation-tools"},{"slug":"ai-performance-optimization","name":"ai-performance-optimization"}],"trust":{"provenance":{"is_fork":false,"github_id":847717439,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-20T06:01:22.853Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":189,"last_release_at":"2025-06-23T05:59:19Z","stars_delta_30d":5,"open_issues_delta_30d":0},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":159,"high_count":0,"last_scan_at":"2026-07-11T11:19:19.678Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-20T06:01:23.288Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-08-20T06:01:23.288Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-20T06:01:23.288Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need comprehensive tools for the observability of complex multi-agentic systems.","If your project involves detailed execution graph views and timeline analyses within a Python environment.","For teams looking to integrate sophisticated guardrails configuration directly into their deployment management.","To leverage self-hosted dashboards for advanced analytics on agent behavior, including LLM and tool interactions."],"when_not_to_use":["When you prefer a language-agnostic solution or require support outside of the Python ecosystem.","If your primary need is focused solely on basic monitoring without advanced debugging and evaluation features.","For projects that do not utilize multi-agentic systems or do not benefit from timeline and execution graph visualizations.","In scenarios where a fully managed service with no self-hosting requirements is preferred."],"source":"enrich:decision_facts","observed_at":"2026-07-11T14:47:39.459Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"RagaAI-Catalyst emerges as a specialized Python framework designed for monitoring and evaluating AI agents, with unique features around self-hosted dashboards, advanced analytics, and support for tracing and debugging LL"}]}}