{"data":{"slug":"agenta-ai-agenta","name":"agenta","tagline":"The open-source LLMOps platform for prompt management, evaluation, and observability.","github_url":"https://github.com/Agenta-AI/agenta","owner":"Agenta-AI","repo":"agenta","owner_avatar_url":"https://avatars.githubusercontent.com/u/127993667?v=4","primary_language":"TypeScript","stars":4445,"forks":609,"topics":["agent-builder","agent-observability","agent-orchestration","agent-workspace","agentic-ai","ai-agent","ai-agents","ai-automation","ai-skills-manager","ai-workflow-builder","harness","mcp","open-source","self-hosted","workflow-automation"],"archived":false,"github_pushed_at":"2026-08-07T10:41:36+00:00","maintenance_label":"Very active","stars_delta_30d":170,"url":"https://www.graphcanon.com/tools/agenta-ai-agenta","markdown_url":"https://www.graphcanon.com/tools/agenta-ai-agenta.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/agenta-ai-agenta","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=agenta-ai-agenta","description":"Agenta is a workspace where you and your team build agents and automations.","homepage_url":"http://www.agenta.ai","license":"Other","open_issues":270,"watchers":31,"ai_summary":"Agenta provides a comprehensive platform that includes features such as a prompt playground, prompt management tools, LLM evaluation capabilities, and monitoring solutions all integrated into one system.","readme_excerpt":"### Use your Claude or ChatGPT subscription\n\nWhen you self-host Agenta, you can run agents locally with your existing Claude or ChatGPT subscription. You do not need to move every task to metered API billing.\n\n---\n\n### Self-host Agenta\n\nPaste this into your agent and it will walk you through setup and testing:\n\n```text\n1. Install the Agenta self-hosting skill: npx skills add Agenta-AI/agenta-skills\n2. Help me self-host Agenta with its repository.\n```\n\nFor more details, read the [self-hosting documentation](https://agenta.ai/docs/self-host/quick-start?utm_source=github&utm_medium=referral&utm_campaign=readme).","github_created_at":"2023-04-26T09:54:28+00:00","created_at":"2026-07-07T17:42:13.687891+00:00","updated_at":"2026-08-07T12:01:14.743864+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"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"}],"tags":[{"slug":"agents","name":"agents"},{"slug":"evaluation","name":"evaluation"},{"slug":"llm-as-a-judge","name":"llm-as-a-judge"},{"slug":"llm-evaluation","name":"llm-evaluation"},{"slug":"llm-monitoring","name":"llm-monitoring"},{"slug":"llm-playground","name":"llm-playground"},{"slug":"prompt-management","name":"prompt management"},{"slug":"prompt-engineering","name":"prompt-engineering"}],"trust":{"provenance":{"is_fork":false,"github_id":632871628,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-07T12:01:13.715Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":30,"days_since_push":0,"last_release_at":"2026-08-05T12:30:18Z","stars_delta_30d":170,"open_issues_delta_30d":109},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T10:39:07.140Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-07T12:01:14.181Z"},"languages":{"value":["typescript"],"source":"github.language","observed_at":"2026-08-07T12:01:14.181Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-08-07T12:01:14.181Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["Need a self-hosted solution with built-in prompt playground and LLM evaluation capabilities","Want integrated tools for prompt engineering in one place"],"when_not_to_use":["Looking for a service without the need to manage self-hosting setup","Require real-time collaboration features that are not provided within this platform's scope"],"source":"enrich:decision_facts","observed_at":"2026-07-12T16:06:57.422Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Agenta, an open-source LLMOps platform for prompt management, evaluation, and observability."}]}}