{"id":29651366,"url":"https://github.com/cyberark/agentwatch","last_synced_at":"2025-07-22T05:06:45.480Z","repository":{"id":286104965,"uuid":"955225139","full_name":"cyberark/agentwatch","owner":"cyberark","description":"A powerful AI observability framework that provides comprehensive insights into agent interactions across platforms, enabling developers to monitor, analyze, and optimize AI-driven applications with minimal integration effort.","archived":false,"fork":false,"pushed_at":"2025-05-13T13:04:39.000Z","size":5070,"stargazers_count":75,"open_issues_count":0,"forks_count":2,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-13T14:26:59.242Z","etag":null,"topics":["agent","agentic","agentic-ai","ai","cybersecurity","large-language-models","llm","llm-framework","llm-observability","llm-tools","machine-learning","monitoring","observability","security"],"latest_commit_sha":null,"homepage":"https://www.cyberark.com","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/cyberark.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.MD","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-03-26T10:01:05.000Z","updated_at":"2025-05-13T13:04:42.000Z","dependencies_parsed_at":"2025-05-05T08:38:07.944Z","dependency_job_id":null,"html_url":"https://github.com/cyberark/agentwatch","commit_stats":null,"previous_names":["cyberark/agentwatch"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/cyberark/agentwatch","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cyberark%2Fagentwatch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cyberark%2Fagentwatch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cyberark%2Fagentwatch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cyberark%2Fagentwatch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/cyberark","download_url":"https://codeload.github.com/cyberark/agentwatch/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cyberark%2Fagentwatch/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266430660,"owners_count":23927169,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-07-22T02:00:09.085Z","response_time":66,"last_error":null,"robots_txt_status":null,"robots_txt_updated_at":null,"robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent","agentic","agentic-ai","ai","cybersecurity","large-language-models","llm","llm-framework","llm-observability","llm-tools","machine-learning","monitoring","observability","security"],"created_at":"2025-07-22T05:06:44.943Z","updated_at":"2025-07-22T05:06:45.447Z","avatar_url":"https://github.com/cyberark.png","language":"Python","funding_links":[],"categories":["*Ops for AI"],"sub_categories":["LLMOps"],"readme":"\u003cp align=\"center\"\u003e\n    \u003cimg src=\"resources/logo.png\" alt=\"agentwatch - AI Agent Observability Platform\" width=\"400\"/\u003e\n\u003c/p\u003e\n\u003ch3 align=\"center\" style=\"font-family: 'Fira Mono', Monospace;\"\u003eagentwatch\u003c/h3\u003e\n\u003ch3 align=\"center\" style=\"font-family: 'Fira Mono', Monospace;\"\u003ePlatform-Agnostic Agentic AI Runtime Observability Framework\u003c/h3\u003e\n\n\u003cp align=\"center\"\u003e\n    \u003ca href=\"https://github.com/cyberark/agentwatch/commits/main\"\u003e\n        \u003cimg alt=\"GitHub last commit\" src=\"https://img.shields.io/github/last-commit/cyberark/agentwatch\"\u003e\n    \u003c/a\u003e\n    \u003ca href=\"https://github.com/cyberark/agentwatch\"\u003e\n        \u003cimg alt=\"GitHub code size\" src=\"https://img.shields.io/github/languages/code-size/cyberark/agentwatch\"\u003e\n    \u003c/a\u003e\n    \u003ca href=\"https://github.com/cyberark/agentwatch/blob/main/LICENSE\"\u003e\n        \u003cimg alt=\"GitHub License\" src=\"https://img.shields.io/github/license/Cyberark/Agentwatch\" /\u003e\n    \u003c/a\u003e\n    \u003ca href=\"https://discord.gg/Zt297RAK\"\u003e\n        \u003cimg alt=\"Join Discord Community\" src=\"https://img.shields.io/discord/1330486843938177157\"\u003e\n    \u003c/a\u003e\n\u003c/p\u003e\n\n## 🌟 Overview\n\nagentwatch is a cutting-edge observability framework designed to provide deep insights into AI agent interactions across diverse platforms and frameworks. By seamlessly intercepting, logging, and analyzing interactions, agentwatch empowers developers to understand and optimize their AI-driven applications with unprecedented visibility.\n\n\u003cp align=\"center\"\u003e\n    \u003cimg src=\"resources/agentwatch.gif\" alt=\"agentwatch Demonstration\" width=\"800\"/\u003e\n\u003c/p\u003e\n\n## ✨ Key Features\n\n- **A One-liner Observability Framework**: Get instant insights with just a single import\n- **Comprehensive Interaction Tracking**: Monitor LLM and tool calls in real-time\n- **Advanced Visualization**: Generate intuitive graphs for in-depth analysis\n- **Detailed Metadata Capture**: Log tool inputs, arguments, and performance metrics\n- **Multi-Framework Support**: Compatible with various AI development frameworks\n- **MCP Support**: Tracks tool calls over remote MCP servers (HTTP/SSE only atm)\n\n## 🚀 Supported Frameworks\n\n- Langgraph\n- Autogen\n- ...\n- Any other* framework or library which uses an LLM :D\n\nWe're working on updating our models to match the various providers - stay tuned!\n\n## 📦 Prerequisites\nTo ensure compatibility with agentwatch, your application must be written in Python. The visualization UI will be built locally on your endpoint using npm,\nso make sure you have the following installed:\n\n- Python 3.11+\n- npm\n\n## 🔧 Installation\n\nInstall agentwatch directly from GitHub:\n\n```bash\npip install git+https://github.com/cyberark/agentwatch.git\n```\n\n## 🖥️ Quick Start\n\n1. Import agentwatch in your main module:\n   ```python\n   import agentwatch\n   ```\n\n2. Ensure your entry point is within a `__main__` block:\n   ```python\n   if __name__ == \"__main__\":\n       # Your code execution starts here\n   ```\n\n3. Launch the UI:\n   ```bash\n   agentwatch ui\n   # (Take note this will open a new tab in your browser)\n   ```\n\nRun your main module - and AI agent interactions will now be automatically tracked and monitored in the UI!\n\n## 📌 Examples\nWe've included a few examples under the [examples/](https://github.com/cyberark/agentwatch/tree/main/examples) folder.\nTo use the examples, clone this repository, and follow these steps:\n\n1. Install python dependencies using poetry. If you don't have Poetry installed, get it [here](https://python-poetry.org/)\n   ```bash\n   poetry install --with dev\n   ```\n\n2. Run the UI\n   ```bash\n   ./run_ui.sh\n   ```\n\n3. Run one of the examples under examples/. Don't forget to set the necessary API keys in the [.env](https://pypi.org/project/python-dotenv/) file\n   ```bash\n   poetry run python examples/langgraph_example.py\n   ```\n\n## 📚 Documentation\n\nFor comprehensive guides and detailed usage instructions, visit our [GitHub Wiki](https://github.com/cyberark/agentwatch/wiki).\n\n## 🤝 Contributing\n\nWe welcome contributions! Please review our [CONTRIBUTING.md](https://github.com/cyberark/agentwatch/blob/main/CONTRIBUTING.md) for guidelines on how to get involved.\n\n## 📄 License\n\nagentwatch is released under the [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0).\n\n## 📧 Contact\n\nHave questions or suggestions? Reach out to us through LinkedIn: [Shai Dvash](https://www.linkedin.com/in/shaidv/) or join our [Discord Community](https://discord.gg/Zt297RAK).\n\n## 🌈 Powered By CyberArk\n\nA project from CyberArk, dedicated to advancing AI observability and security.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcyberark%2Fagentwatch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcyberark%2Fagentwatch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcyberark%2Fagentwatch/lists"}