Skip to content

The open-source LLMOps platform: prompt playground, prompt management, LLM evaluation, and LLM observability all in one place.

License

Notifications You must be signed in to change notification settings

Agenta-AI/agenta

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

Shows the logo of agenta

The Open-source LLMOps Platform

Build reliable LLM applications faster with integrated prompt management, evaluation, and observability.



MIT license. Doc PRs welcome Contributors PyPI - Downloads Last Commit

Try Agenta Live Demo


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

πŸ§ͺ Prompt Engineering & Management

Collaborate with Subject Matter Experts (SMEs) on prompt engineering and make sure nothing breaks in production.

  • Interactive Playground: Compare prompts side by side against your test cases
  • Multi-Model Support: Experiment with 50+ LLM models or bring-your-own models
  • Version Control: Version prompts and configurations with branching and environments
  • Complex Configurations: Enable SMEs to collaborate on complex configuration schemas beyond simple prompts

Explore prompt management β†’

πŸ“Š Evaluation & Testing

Evaluate your LLM applications systematically with both human and automated feedback.

  • Flexible Test Sets: Create test cases from production data, playground experiments, or upload CSVs
  • Pre-built and Custom Evaluators: Use LLM-as-judge, one of our 20+ pre-built evaluators, or you custom evaluators
  • UI and API Access: Run evaluations via UI (for SMEs) or programmatically (for engineers)
  • Human Feedback Integration: Collect and incorporate expert annotations

Explore evaluation frameworks β†’

πŸ“‘ Observability & Monitoring

Get visibility into your LLM applications in production.

  • Cost & Performance Tracking: Monitor spending, latency, and usage patterns
  • Tracing: Debug complex workflows with detailed traces
  • Open Standards: OpenTelemetry native tracing compatible with OpenLLMetry, and OpenInference
  • Integrations: Comes with pre-built integrations for most models and frameworks

Learn about observability β†’

πŸ“Έ Screenshots

Playground

Prompt Management

Evaluation

Observability

πŸš€ Getting Started

Agenta Cloud (Recommended):

The easiest way to get started is through Agenta Cloud. Free tier available with no credit card required.

Try Agenta Live Demo

Self-hosting Agenta

  1. Clone Agenta:
git clone https://github.com/Agenta-AI/agenta && cd agenta
  1. Start Agenta services:
docker compose -f hosting/docker-compose/oss/docker-compose.gh.yml --env-file hosting/docker-compose/oss/.env.oss.gh --profile with-web up -d
  1. Access Agenta at http://localhost.

For deploying on a remote host, or using different ports refers to our self-hosting and remote deployment documentation.

πŸ’¬ Community

Find help, explore resources, or get involved:

🧰 Support

🀝 Contribute

We welcome contributions of all kinds β€” from filing issues and sharing ideas to improving the codebase.

⭐ Star Agenta

Consider giving us a star! It helps us grow our community and gets Agenta in front of more developers.

Star us

Contributors ✨

All Contributors

Thanks goes to these wonderful people (emoji key):

Sameh Methnani
Sameh Methnani

πŸ’» πŸ“–
Suad Suljovic
Suad Suljovic

πŸ’» 🎨 πŸ§‘β€πŸ« πŸ‘€
burtenshaw
burtenshaw

πŸ’»
Abram
Abram

πŸ’» πŸ“–
Israel Abebe
Israel Abebe

πŸ› 🎨 πŸ’»
Master X
Master X

πŸ’»
corinthian
corinthian

πŸ’» 🎨
Pavle Janjusevic
Pavle Janjusevic

πŸš‡
Kaosi Ezealigo
Kaosi Ezealigo

πŸ› πŸ’»
Alberto Nunes
Alberto Nunes

πŸ›
Maaz Bin Khawar
Maaz Bin Khawar

πŸ’» πŸ‘€ πŸ§‘β€πŸ«
Nehemiah Onyekachukwu Emmanuel
Nehemiah Onyekachukwu Emmanuel

πŸ’» πŸ’‘ πŸ“–
Philip Okiokio
Philip Okiokio

πŸ“–
Abhinav Pandey
Abhinav Pandey

πŸ’»
Ramchandra Warang
Ramchandra Warang

πŸ’» πŸ›
Biswarghya Biswas
Biswarghya Biswas

πŸ’»
Uddeepta Raaj Kashyap
Uddeepta Raaj Kashyap

πŸ’»
Nayeem Abdullah
Nayeem Abdullah

πŸ’»
Kang Suhyun
Kang Suhyun

πŸ’»
Yoon
Yoon

πŸ’»
Kirthi Bagrecha Jain
Kirthi Bagrecha Jain

πŸ’»
Navdeep
Navdeep

πŸ’»
Rhythm Sharma
Rhythm Sharma

πŸ’»
Osinachi Chukwujama
Osinachi Chukwujama

πŸ’»
θŽ«ε°”η΄’
θŽ«ε°”η΄’

πŸ“–
Agunbiade Adedeji
Agunbiade Adedeji

πŸ’»
Emmanuel Oloyede
Emmanuel Oloyede

πŸ’» πŸ“–
Dhaneshwarguiyan
Dhaneshwarguiyan

πŸ’»
Priyanshu Prajapati
Priyanshu Prajapati

πŸ“–
Raviteja
Raviteja

πŸ’»
Arijit
Arijit

πŸ’»
Yachika9925
Yachika9925

πŸ“–
Aldrin
Aldrin

⚠️
seungduk.kim.2304
seungduk.kim.2304

πŸ’»
Andrei Dragomir
Andrei Dragomir

πŸ’»
diego
diego

πŸ’»
brockWith
brockWith

πŸ’»
Dennis Zelada
Dennis Zelada

πŸ’»
Romain Brucker
Romain Brucker

πŸ’»
Heon Heo
Heon Heo

πŸ’»
Drew Reisner
Drew Reisner

πŸ’»
Ikko Eltociear Ashimine
Ikko Eltociear Ashimine

πŸ“–
Vishal Vanpariya
Vishal Vanpariya

πŸ’»
Youcef Boumar
Youcef Boumar

πŸ“–
LucasTrg
LucasTrg

πŸ’» πŸ›
Ashraf Chowdury
Ashraf Chowdury

πŸ› πŸ’»
jp-agenta
jp-agenta

πŸ’» πŸ›
Mr Unhappy
Mr Unhappy

πŸ› πŸš‡
Moreno Bonaventura
Moreno Bonaventura

πŸ›

This project follows the all-contributors specification. Contributions of any kind are welcome!

Disabling Anonymized Tracking

By default, Agenta automatically reports anonymized basic usage statistics. This helps us understand how Agenta is used and track its overall usage and growth. This data does not include any sensitive information. To disable anonymized telemetry set TELEMETRY_ENABLED to false in your .env file.