Agenta-AI / agenta
The open-source LLMOps platform: prompt playground, prompt management, LLM evaluation, and LLM observability all in one place.
AI Architecture Analysis
This repository is indexed by RepoMind. By analyzing Agenta-AI/agenta in our AI interface, you can instantly generate complete architecture diagrams, visualize control flows, and perform automated security audits across the entire codebase.
Our Agentic Context Augmented Generation (Agentic CAG) engine loads full source files into context on-demand, avoiding the fragmentation of traditional RAG systems. Ask questions about the architecture, dependencies, or specific features to see it in action.
Repository Overview (README excerpt)
Crawler viewThe Open-source LLMOps Platform Build reliable LLM applications faster with integrated prompt management, evaluation, and observability. --- Documentation • Website • Agenta Cloud --- --- What is Agenta? Agenta is a platform for building production-grade LLM applications. It helps **engineering** and **product teams** create reliable LLM apps faster through integrated prompt management, evaluation, and observability. Core Features ๐งช Prompt Management & Prompt Engineering Collaborate with Subject Matter Experts (SMEs) on prompt engineering and make sure nothing breaks in production. โข **Interactive LLM Playground**: Compare prompts side by side against your test cases โข **Multi-Model Support**: Experiment with 50+ LLM models or bring-your-own models โข **Version Control**: Version prompts and configurations with branching and environments โข **Complex Configurations**: Enable SMEs to collaborate on complex configuration schemas beyond simple prompts Explore prompt management โ ๐ LLM Evaluation Evaluate your LLM applications systematically with both human and automated feedback. โข **Flexible Testsets**: Create testcases from production data, playground experiments, or upload CSVs โข **Pre-built and Custom Evaluators**: Use LLM-as-judge, one of our 20+ pre-built evaluators, or you custom evaluators โข **UI and API Access**: Run evaluations via UI (for SMEs) or programmatically (for engineers) โข **Human Feedback Integration**: Collect and incorporate expert annotations Explore evaluation frameworks โ ๐ก LLM Observability Get visibility into your LLM applications in production. โข **Cost & Performance Tracking**: Monitor spending, latency, and usage patterns โข **LLM Tracing**: Debug complex workflows with detailed traces โข **Open Standards**: OpenTelemetry native tracing compatible with OpenLLMetry, and OpenInference โข **Integrations**: Comes with pre-built integrations for most models and frameworks Learn about observability โ ๐ธ Screenshots ๐ Getting Started Agenta Cloud (Recommended): The easiest way to get started is through Agenta Cloud. Free tier available with no credit card required. Self-hosting Agenta โข Clone Agenta: โข Copy configuration: Before starting the services, create the environment file from the example: โข Start Agenta services: โข Access Agenta at . For deploying on a remote host, or using different ports refers to our self-hosting and remote deployment documentation. ๐ฌ Community Find help, explore resources, or get involved: ๐งฐ Support โข **๐ Documentation** โ Full guides and API reference โข **๐ Changelog** โ Track recent updates โข **๐ฌ Slack Community** โ Ask questions and get support ๐ค Contribute We welcome contributions of all kinds, from filing issues and sharing ideas to improving the codebase. Check out our CONTRIBUTING.md and: โข **๐ Report bugs** โ Help us by reporting problems you encounter โข **๐ก Share ideas and feedback** โ Suggest features or vote on ideas โข **๐ง Contribute to the codebase** โ Read the guide and open a pull request โญ Star Agenta **Consider giving us a star!** It helps us grow our community and gets Agenta in front of more developers. Contributors โจ Thanks goes to these wonderful people (emoji key): Sameh Methnani ๐ป ๐ Suad Suljovic ๐ป ๐จ ๐งโ๐ซ ๐ burtenshaw ๐ป Abram ๐ป ๐ Israel Abebe ๐ ๐จ ๐ป Master X ๐ป corinthian ๐ป ๐จ Pavle Janjusevic ๐ Kaosi Ezealigo ๐ ๐ป Alberto Nunes ๐ Maaz Bin Khawar ๐ป ๐ ๐งโ๐ซ Nehemiah Onyekachukwu Emmanuel ๐ป ๐ก ๐ Philip Okiokio ๐ Abhinav Pandey ๐ป Ramchandra Warang ๐ป ๐ Biswarghya Biswas ๐ป Uddeepta Raaj Kashyap ๐ป Nayeem Abdullah ๐ป Kang Suhyun ๐ป Yoon ๐ป Kirthi Bagrecha Jain ๐ป Navdeep ๐ป Rhythm Sharma ๐ป Osinachi Chukwuja _...truncated for preview_