Skip to main content

The SDK for agenta is an open-source LLMOps platform.

Project description

Shows the logo of agenta

The Open-source LLMOps Platform

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


Documentation โ€ข Website โ€ข Agenta Cloud


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

๐Ÿงช 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 โ†’

๐Ÿ“Š Evaluation & Testing

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

  • Flexible Testsets: Create testcases 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 โ†’

๐Ÿ“ก 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 โ†’

๐Ÿ“ธ Screenshots

Playground Prompt Management Evaluation Observability

๐Ÿš€ 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 --profile with-traefik 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.

๐Ÿ’ฌ Community

Find help, explore resources, or get involved:

๐Ÿงฐ Support

๐Ÿค Contribute

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

โญ Star Agenta

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

Star us

Contributors โœจ

All Contributors

Thanks goes to these wonderful people (emoji key):

Sameh Methnani
Sameh Methnani

๐Ÿ’ป ๐Ÿ“–
Suad Suljovic
Suad Suljovic

๐Ÿ’ป ๐ŸŽจ ๐Ÿง‘โ€๐Ÿซ ๐Ÿ‘€
burtenshaw
burtenshaw

๐Ÿ’ป
Abram
Abram

๐Ÿ’ป ๐Ÿ“–
Israel Abebe
Israel Abebe

๐Ÿ› ๐ŸŽจ ๐Ÿ’ป
Master X
Master X

๐Ÿ’ป
corinthian
corinthian

๐Ÿ’ป ๐ŸŽจ
Pavle Janjusevic
Pavle Janjusevic

๐Ÿš‡
Kaosi Ezealigo
Kaosi Ezealigo

๐Ÿ› ๐Ÿ’ป
Alberto Nunes
Alberto Nunes

๐Ÿ›
Maaz Bin Khawar
Maaz Bin Khawar

๐Ÿ’ป ๐Ÿ‘€ ๐Ÿง‘โ€๐Ÿซ
Nehemiah Onyekachukwu Emmanuel
Nehemiah Onyekachukwu Emmanuel

๐Ÿ’ป ๐Ÿ’ก ๐Ÿ“–
Philip Okiokio
Philip Okiokio

๐Ÿ“–
Abhinav Pandey
Abhinav Pandey

๐Ÿ’ป
Ramchandra Warang
Ramchandra Warang

๐Ÿ’ป ๐Ÿ›
Biswarghya Biswas
Biswarghya Biswas

๐Ÿ’ป
Uddeepta Raaj Kashyap
Uddeepta Raaj Kashyap

๐Ÿ’ป
Nayeem Abdullah
Nayeem Abdullah

๐Ÿ’ป
Kang Suhyun
Kang Suhyun

๐Ÿ’ป
Yoon
Yoon

๐Ÿ’ป
Kirthi Bagrecha Jain
Kirthi Bagrecha Jain

๐Ÿ’ป
Navdeep
Navdeep

๐Ÿ’ป
Rhythm Sharma
Rhythm Sharma

๐Ÿ’ป
Osinachi Chukwujama
Osinachi Chukwujama

๐Ÿ’ป
่Žซๅฐ”็ดข
่Žซๅฐ”็ดข

๐Ÿ“–
Agunbiade Adedeji
Agunbiade Adedeji

๐Ÿ’ป
Emmanuel Oloyede
Emmanuel Oloyede

๐Ÿ’ป ๐Ÿ“–
Dhaneshwarguiyan
Dhaneshwarguiyan

๐Ÿ’ป
Priyanshu Prajapati
Priyanshu Prajapati

๐Ÿ“–
Raviteja
Raviteja

๐Ÿ’ป
Arijit
Arijit

๐Ÿ’ป
Yachika9925
Yachika9925

๐Ÿ“–
Aldrin
Aldrin

โš ๏ธ
seungduk.kim.2304
seungduk.kim.2304

๐Ÿ’ป
Andrei Dragomir
Andrei Dragomir

๐Ÿ’ป
diego
diego

๐Ÿ’ป
brockWith
brockWith

๐Ÿ’ป
Dennis Zelada
Dennis Zelada

๐Ÿ’ป
Romain Brucker
Romain Brucker

๐Ÿ’ป
Heon Heo
Heon Heo

๐Ÿ’ป
Drew Reisner
Drew Reisner

๐Ÿ’ป
Ikko Eltociear Ashimine
Ikko Eltociear Ashimine

๐Ÿ“–
Vishal Vanpariya
Vishal Vanpariya

๐Ÿ’ป
Youcef Boumar
Youcef Boumar

๐Ÿ“–
LucasTrg
LucasTrg

๐Ÿ’ป ๐Ÿ›
Ashraf Chowdury
Ashraf Chowdury

๐Ÿ› ๐Ÿ’ป
jp-agenta
jp-agenta

๐Ÿ’ป ๐Ÿ›
Mr Unhappy
Mr Unhappy

๐Ÿ› ๐Ÿš‡
Moreno Bonaventura
Moreno Bonaventura

๐Ÿ›

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 AGENTA_TELEMETRY_ENABLED to false in your .env file.

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

agenta-0.86.1.tar.gz (334.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

agenta-0.86.1-py3-none-any.whl (677.4 kB view details)

Uploaded Python 3

File details

Details for the file agenta-0.86.1.tar.gz.

File metadata

  • Download URL: agenta-0.86.1.tar.gz
  • Upload date:
  • Size: 334.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.3.2 CPython/3.12.3 Linux/6.14.0-1017-azure

File hashes

Hashes for agenta-0.86.1.tar.gz
Algorithm Hash digest
SHA256 90f8c30b196da32c1249bec81c56a65216a7be47364f3d4db318335b8a0d68fc
MD5 a05897b5384f124f8893bcdba9a5960d
BLAKE2b-256 ac21b4cbbb342b5a3e72e7554f3f9706811e69bf943dc5a47865ff5ba65ae661

See more details on using hashes here.

File details

Details for the file agenta-0.86.1-py3-none-any.whl.

File metadata

  • Download URL: agenta-0.86.1-py3-none-any.whl
  • Upload date:
  • Size: 677.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.3.2 CPython/3.12.3 Linux/6.14.0-1017-azure

File hashes

Hashes for agenta-0.86.1-py3-none-any.whl
Algorithm Hash digest
SHA256 218cab2639d4fe1b29de4de1865764cc24a77fa4500b91f966f99aee4911d22d
MD5 48cfe3b50e2c3a0b8e753880d247ae38
BLAKE2b-256 e97230efde40003079dc9c9728181af9925f770c5078c8bf8a45492c67668865

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page