Sent – Messaging Infrastructure for Developers. One API for SMS, WhatsApp, and RCS across 190+ countries.

Agenta is an open-source LLMOps platform designed to help development teams build reliable LLM applications through structured workflows and collaborative processes.

Key Features:

Unified Playground: Compare prompts and models side-by-side with complete version history and model-agnostic support
Automated Evaluation: Create systematic processes to run experiments, track results, and validate changes with LLM-as-a-judge, built-in, or custom code evaluators
Full Observability: Trace every request to find exact failure points, annotate traces with team feedback, and monitor performance with live evaluations
Team Collaboration: Enable domain experts to safely edit prompts through UI while maintaining full API parity for developers

Benefits:

Centralized Management: Keep prompts, evaluations, and traces in one platform instead of scattered across tools
Evidence-Based Development: Replace guesswork with systematic evaluation and performance tracking
Cross-Functional Workflows: Bring product managers, domain experts, and developers into unified processes
Production Debugging: Turn production traces into tests with one click, closing the feedback loop

Sent – Messaging Infrastructure for Developers. One API for SMS, WhatsApp, and RCS across 190+ countries.

Learn More

Agenta

Open-source LLMOps platform providing prompt management, evaluation, and observability tools for building robust AI applications with team collaboration.

Open Source Alternative to:

LangSmith

Humanloop

Visit Agenta Host with Stellar Hosted

Sent

Messaging Infrastructure for Developers. One API for SMS, WhatsApp, and RCS across 190+ countries.

Get Started Free

Agenta is an open-source LLMOps platform designed to help development teams build reliable LLM applications through structured workflows and collaborative processes.

Key Features:

Unified Playground: Compare prompts and models side-by-side with complete version history and model-agnostic support
Automated Evaluation: Create systematic processes to run experiments, track results, and validate changes with LLM-as-a-judge, built-in, or custom code evaluators
Full Observability: Trace every request to find exact failure points, annotate traces with team feedback, and monitor performance with live evaluations
Team Collaboration: Enable domain experts to safely edit prompts through UI while maintaining full API parity for developers

Benefits:

Centralized Management: Keep prompts, evaluations, and traces in one platform instead of scattered across tools
Evidence-Based Development: Replace guesswork with systematic evaluation and performance tracking
Cross-Functional Workflows: Bring product managers, domain experts, and developers into unified processes
Production Debugging: Turn production traces into tests with one click, closing the feedback loop

Categories:

LLM Observability & Evaluation

Tags:

self-hosted open-source ai-agents mcp agents observability ai-agent agentic-ai llmops workflow-automation agentic-workflow llm-observability llm-evaluation

Built with:

Github Actions

JavaScript

NodeJS

CSS

Bash

Docker

Typescript

Eslint

JSX

Prettier

React

Tailwind

Sevalla

Deploy your app before your coffee gets cold. It’s that easy. Try Sevalla with $50 free credit.

Get started for free

Featured projects:

Similar open source projects

Check Agenta alternatives

Langfuse

Open source LLM engineering platform for AI-powered applications

Stars
32,435
Forks
3,485
Last commit
5 hours ago

Langfuse provides tracing, evaluations, prompt management, and analytics to debug and improve LLM applications.

Compare with

Agenta

Arize Phoenix

Open-source LLM tracing & evaluation for AI optimization

Stars
10,875
Forks
1,034
Last commit
5 hours ago

Open-source platform for LLM tracing, evaluation, and optimization. Features automatic instrumentation, prompt playground, and real-time AI application monitoring.

Compare with

Agenta

OpenLLMetry

Monitor LLM performance with open-source observability

Stars
7,352
Forks
1,041
Last commit
9 hours ago

Open-source observability platform for LLMs using OpenTelemetry. Monitor performance, track costs, and debug AI applications with just 2 lines of code.

Compare with

Agenta

Helicone

Build reliable AI apps with comprehensive observability

Stars
6,031
Forks
645
Last commit
10 days ago

Open-source platform for logging, monitoring, and debugging LLM applications. Route, debug, and analyze AI apps with comprehensive observability tools.

Compare with

Agenta

Latitude

Full observability for AI agents in production

Stars
4,552
Forks
374
Last commit
5 hours ago

Open-source platform for monitoring AI agents: captures traces, surfaces failure patterns, alerts on issues, and helps you verify fixes with automated evals.

Compare with

Agenta

OpenLIT

Monitor, debug, and scale LLM applications with ease

Stars
2,668
Forks
343
Last commit
12 hours ago

Open-source observability platform for GenAI and LLM applications. Real-time monitoring, distributed tracing, prompt management, and AI model evaluation built on OpenTelemetry.

Compare with

Agenta

Spanlens

LLM observability: cost, latency, and traces in one place

Stars
11
Forks
0
Last commit
17 hours ago

Drop-in observability platform for OpenAI, Anthropic, and Gemini that logs every request, tracks costs, traces agent workflows, and flags anomalies and PII.

Compare with

Agenta

Activity score
89/100
Stars
4,426
Forks
606
Last commit
5 hours ago
Repository age
3 years
Version
v0.108.0
License
MIT
Self-hosted
Yes
Repository
agenta-ai/agenta

Activity score
89/100
Stars
4,426
Forks
606
Last commit
5 hours ago
Repository age
3 years
Version
v0.108.0
License
MIT
Self-hosted
Yes
Repository
agenta-ai/agenta

Subscribe to our newsletter

Every Sunday we deconstruct one proprietary app and pick the best open source alternatives worth switching to.

Similar open source projects

Stars
Forks
Last commit

Stars
Forks
Last commit

Stars
Forks
Last commit

Sevalla

Deploy your app before your coffee gets cold. It’s that easy. Try Sevalla with $50 free credit.

Get started for free

Featured projects:

Sent

Messaging Infrastructure for Developers. One API for SMS, WhatsApp, and RCS across 190+ countries.

Get Started Free

Similar open source projects

Check Agenta alternatives

Langfuse

Open source LLM engineering platform for AI-powered applications

Stars
32,435
Forks
3,485
Last commit
5 hours ago

Langfuse provides tracing, evaluations, prompt management, and analytics to debug and improve LLM applications.

Compare with

Agenta

Arize Phoenix

Open-source LLM tracing & evaluation for AI optimization

Stars
10,875
Forks
1,034
Last commit
5 hours ago

Open-source platform for LLM tracing, evaluation, and optimization. Features automatic instrumentation, prompt playground, and real-time AI application monitoring.

Compare with

Agenta

OpenLLMetry

Monitor LLM performance with open-source observability

Stars
7,352
Forks
1,041
Last commit
9 hours ago

Open-source observability platform for LLMs using OpenTelemetry. Monitor performance, track costs, and debug AI applications with just 2 lines of code.

Compare with

Agenta

Helicone

Build reliable AI apps with comprehensive observability

Stars
6,031
Forks
645
Last commit
10 days ago

Open-source platform for logging, monitoring, and debugging LLM applications. Route, debug, and analyze AI apps with comprehensive observability tools.

Compare with

Agenta

Latitude

Full observability for AI agents in production

Stars
4,552
Forks
374
Last commit
5 hours ago

Open-source platform for monitoring AI agents: captures traces, surfaces failure patterns, alerts on issues, and helps you verify fixes with automated evals.

Compare with

Agenta

OpenLIT

Monitor, debug, and scale LLM applications with ease

Stars
2,668
Forks
343
Last commit
12 hours ago

Open-source observability platform for GenAI and LLM applications. Real-time monitoring, distributed tracing, prompt management, and AI model evaluation built on OpenTelemetry.

Compare with

Agenta

Spanlens

LLM observability: cost, latency, and traces in one place

Stars
11
Forks
0
Last commit
17 hours ago

Drop-in observability platform for OpenAI, Anthropic, and Gemini that logs every request, tracks costs, traces agent workflows, and flags anomalies and PII.

Compare with

Agenta