---
title: "agenta"
type: "tool"
slug: "agenta-ai-agenta"
canonical_url: "https://www.graphcanon.com/tools/agenta-ai-agenta"
github_url: "https://github.com/Agenta-AI/agenta"
homepage_url: "http://www.agenta.ai"
stars: 4271
forks: 561
primary_language: "TypeScript"
license: "Other"
categories: ["evaluation-observability", "llm-frameworks"]
tags: ["agents", "observation", "prompt-engineering", "llm-evaluation"]
updated_at: "2026-07-07T18:41:25.129876+00:00"
---

# agenta

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

Agenta is an open-source platform designed to facilitate the development of reliable applications based on large language models (LLMs). It encompasses functionalities such as prompt engineering, management, and ongoing assessment through a comprehensive suite of tools including playgrounds for experimentation, evaluation frameworks for assessing model performance, and observability features for monitoring LLM behavior.

## Facts

- Repository: https://github.com/Agenta-AI/agenta
- Homepage: http://www.agenta.ai
- Stars: 4,271 · Forks: 561 · Open issues: 158 · Watchers: 31
- Primary language: TypeScript
- License: Other
- Last pushed: 2026-07-07T17:37:23+00:00

## Categories

- [Evaluation & Observability](/categories/evaluation-observability.md)
- [LLM Frameworks](/categories/llm-frameworks.md)

## Tags

agents, observation, prompt-engineering, llm-evaluation

## Related tools

- [ollama](/tools/ollama-ollama.md) - Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. (★ 175,659)
- [prompts.chat](/tools/f-prompts-chat.md) - The world's largest open-source prompt library for AI (★ 165,019)
- [transformers](/tools/huggingface-transformers.md) - 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models (★ 162,347)
- [langflow](/tools/langflow-ai-langflow.md) - Langflow is a powerful platform for building and deploying AI-powered agents and workflows. (★ 151,298)
- [open-webui](/tools/open-webui-open-webui.md) - User-friendly AI Interface (Supports Ollama, OpenAI API, ...) (★ 144,575)
- [awesome-llm-apps](/tools/shubhamsaboo-awesome-llm-apps.md) - 100+ AI Agent & RAG apps you can actually run — clone, customize, ship. (★ 116,702)
- [LLMs-from-scratch](/tools/rasbt-llms-from-scratch.md) - Implement a ChatGPT-like LLM in PyTorch from scratch (★ 98,711)
- [TradingAgents](/tools/tauricresearch-tradingagents.md) - TradingAgents: Multi-Agents LLM Financial Trading Framework (★ 91,610)

## README (excerpt)

```text
<p align="center">
  <a href="https://agenta.ai?utm_source=github&utm_medium=referral&utm_campaign=readme">
      <picture >
        <source width="275" media="(prefers-color-scheme: dark)" srcset="https://github.com/user-attachments/assets/97e31bfc-b1fc-4d19-b443-5aedf6029017"  >
        <source width="275" media="(prefers-color-scheme: light)" srcset="https://github.com/user-attachments/assets/fdc5f23f-2095-4cfc-9511-14c6851c1262"  >
        <img alt="Shows the logo of agenta" src="https://github.com/user-attachments/assets/fdc5f23f-2095-4cfc-9511-14c6851c1262" >
      </picture>
  </a>
  
<div align="center">
  <strong> <h1> The Open-source LLMOps Platform </h1></strong>
  Build reliable LLM applications with prompt management, evaluation, and observability.
</div>


  <br />
      <div align="center" >
        <a href="https://www.youtube.com/watch?v=zZJfqkc608M" target="_blank">
          <picture >
            <img alt="Agenta platform walkthrough" src="https://github.com/user-attachments/assets/992d4880-86ce-44bc-bfe4-e9eae9b731c8" >
          </picture>
        </a>
    </div>
</div>

---

<h3 align="center">
  <a href="https://agenta.ai/docs/?utm_source=github&utm_medium=referral&utm_campaign=readme"><b>Documentation</b></a> &bull;
  <a href="https://agenta.ai?utm_source=github&utm_medium=referral&utm_campaign=readme"><b>Website</b></a> &bull;
  <a href="https://cloud.agenta.ai?utm_source=github&utm_medium=referral&utm_campaign=readme"><b>Agenta Cloud</b></a>
</h3>

---

<p align="center">
  <img src="https://img.shields.io/badge/license-MIT-blue.svg" alt="MIT license." />
  <a href="https://agenta.ai/docs/?utm_source=github&utm_medium=referral&utm_campaign=readme">
    <img src="https://img.shields.io/badge/Doc-online-green" alt="Doc">
  </a>
  <a href="https://github.com/Agenta-AI/agenta/blob/main/CONTRIBUTING.md">
    <img src="https://img.shields.io/badge/PRs-Welcome-brightgreen" alt="PRs welcome" />
  </a>
  <img src="https://img.shields.io/github/contributors/Agenta-AI/agenta" alt="Contributors">
  <a href="https://pypi.org/project/agenta/">
    <img src="https://img.shields.io/pypi/dm/agenta" alt="PyPI - Downloads">
  </a>
  <img src="https://img.shields.io/github/last-commit/Agenta-AI/agenta" alt="Last Commit">
</br>
</p>

<p align="center">
    <a href="https://join.slack.com/t/agenta-hq/shared_invite/zt-37pnbp5s6-mbBrPL863d_oLB61GSNFjw">
        <img src="https://img.shields.io/badge/JOIN US ON SLACK-4A154B?style=for-the-badge&logo=slack&logoColor=white" />
    </a>
    <a href="https://www.linkedin.com/company/agenta-ai/">
        <img src="https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white" />
    </a>
    <a  href="https://twitter.com/agenta_ai">
        <img src="https://img.shields.io/twitter/follow/agenta_ai?style=social" height="28" />
    </a>
</p>

<p align="center">
  <a href="https://cloud.agenta.ai?utm_source=github&utm_medium=referral&utm_campaign=readme">
      <picture >
        <source width="200" media="(prefers-color-scheme: dark)" srcset="https://github.com/user-attachments/assets/a2069e7b-c3e0-4a5e-9e41-8ddc4660d1f2"  >
        <source width="200" media="(prefers-color-scheme: light)" srcset="https://github.com/user-attachments/assets/a2069e7b-c3e0-4a5e-9e41-8ddc4660d1f2"  >
        <img alt="Try Agenta Live Demo" src="https://github.com/user-attachments/assets/a2069e7b-c3e0-4a5e-9e41-8ddc4660d1f2" >
      </picture>
  </a>
</p>

---

## 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

### 🧪 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 S
```

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/tools/agenta-ai-agenta`](/api/graphcanon/tools/agenta-ai-agenta)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_