freshcrate
Home > Frameworks > agenta

agenta

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

Description

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

README

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 Management & Prompt Engineering

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

  • Interactive LLM 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 LLM Evaluation

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 your 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 LLM Observability

Get visibility into your LLM applications in production.

  • Cost & Performance Tracking: Monitor spending, latency, and usage patterns
  • LLM 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. Copy configuration:

Before starting the services, create the environment file from the example:

cp hosting/docker-compose/oss/env.oss.gh.example hosting/docker-compose/oss/.env.oss.gh
  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 refer 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, from filing issues and sharing ideas to improving the codebase. Check out our CONTRIBUTING.md and:

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 ContributorsThanks 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›
Yoshiki Ozaki
Yoshiki Ozaki

๐Ÿ›
ahmed-agenta
ahmed-agenta

๐ŸŽจ
Vahant Sharma
Vahant Sharma

๐Ÿ“–
Muhammad Muzammil
Muhammad Muzammil

๐Ÿ’ป
Sirous Namjoo
Sirous Namjoo

๐Ÿ“– ๐Ÿ’ก
adityadewan22-hub
adityadewan22-hub

๐Ÿ’ป
lif
lif

๐Ÿ’ป
karim kohel
karim kohel

๐Ÿ’ก ๐Ÿ“–
Vishesh Paliwal
Vishesh Paliwal

๐Ÿ’ป
Eve
Eve

๐Ÿ’ป
Endoze
Endoze

๐Ÿš‡ 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.

Release History

VersionChangesUrgencyDate
v0.96.7## What's Changed * [release] v0.96.6 by @github-actions[bot] in https://github.com/Agenta-AI/agenta/pull/4162 * [docs] Update API reference docs by @github-actions[bot] in https://github.com/Agenta-AI/agenta/pull/4180 * [fix] Mislabeled annotations by @jp-agenta in https://github.com/Agenta-AI/agenta/pull/4192 * [feat] Add beautified JSON view mode with structured rendering for trโ€ฆ by @ardaerzin in https://github.com/Agenta-AI/agenta/pull/4189 * [fix] Resolve issue with updated Stripe fielHigh4/20/2026
v0.96.6## What's Changed * [docs] Update API reference docs by @github-actions[bot] in https://github.com/Agenta-AI/agenta/pull/4157 * docs(docs): v0.96.x REST API migration guide by @mmabrouk in https://github.com/Agenta-AI/agenta/pull/4164 * [chore] Clean up `/preview`, fix `api` tests, fix `api` bugs by @jp-agenta in https://github.com/Agenta-AI/agenta/pull/4163 * feat: updated `evaluator` selector ui by @ashrafchowdury in https://github.com/Agenta-AI/agenta/pull/4151 * [fix] Resolve cross-pollHigh4/17/2026
v0.96.4## What's Changed * Fix version type in legacy adapter for `/configs/fetch` **Full Changelog**: https://github.com/Agenta-AI/agenta/compare/v0.96.3...v0.96.4High4/15/2026
v0.96.1## What's Changed * Fix minor backward compatibility issues in web, sdk, api, services introduced in `v0.96.0` @junaway @bekossy **Full Changelog**: https://github.com/Agenta-AI/agenta/compare/v0.96.0...v0.96.1High4/14/2026
v0.96.0## What's Changed * [feat] Extend `runs` and `queues` with multi-inputs, caching, splitting by @jp-agenta in https://github.com/Agenta-AI/agenta/pull/4053 * [feat] Migrate workflows, registries, and playgrounds by @junaway @ardaerzin in https://github.com/Agenta-AI/agenta/pull/4117 * [test] Migrate workflows, registries, and playgrounds by @bekossy in https://github.com/Agenta-AI/agenta/pull/4118 * Test acceptance scenarios and flow fixes by @bekossy in https://github.com/Agenta-AI/agenta/puHigh4/13/2026
v0.95.7## What's Changed * [release] v0.95.6 by @github-actions[bot] in https://github.com/Agenta-AI/agenta/pull/4127 * (fix)[AGE-3727]: Prompt editor cursor jumps to top while typing by @bekossy in https://github.com/Agenta-AI/agenta/pull/4130 * fix(frontend): block deletion of app's last revision by @JasonOA888 in https://github.com/Agenta-AI/agenta/pull/3940 ## New Contributors * @JasonOA888 made their first contribution in https://github.com/Agenta-AI/agenta/pull/3940 **Full Changelog**: High4/10/2026
v0.95.5## What's Changed * [feat] Gate all web exports (not just traces) by @jp-agenta in https://github.com/Agenta-AI/agenta/pull/4120 * [feat] Add CDC to events: state and diff by @jp-agenta in https://github.com/Agenta-AI/agenta/pull/4113 **Full Changelog**: https://github.com/Agenta-AI/agenta/compare/v0.95.4...v0.95.5High4/8/2026

Dependencies & License Audit

Loading dependencies...

Similar Packages

langfuse๐Ÿชข Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. ๐ŸŠYC W23 v3.169.0
planning-with-files๐Ÿ“„ Transform your workflow with persistent markdown files for planning, tracking progress, and storing knowledge like a pro.master@2026-04-21
ai-video-generation-workflowGenerate reliable short finance explainer videos with script, slides, voice, subtitles, and batch-ready rendering in a stable, modular workflow.main@2026-04-21
AntennaSimSimulate antenna designs instantly in your browser using NEC2-powered, open-source software with WebAssembly and Docker support.main@2026-04-21
opikDebug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.2.0.6