Updated

Agenta

Was an open-source LLMOps platform for managing prompts, running evaluations and tracing LLM apps. Since July 2026 it has been a workspace for building agents ("AI coworkers" in Slack and Telegram). Tracing still exists inside it.

Open sourceSelf-hostable

Shut down / archived · Jul 2026: Pivoted on 21 July 2026: "Agenta Is Now a Workspace for Building Agents". It started as a platform for managing and evaluating prompts. It is no longer an LLM observability product, though its tracing remains. Source ↗

Profile checked

Ask your AI about this, with this page as the source:ChatGPT ↗Claude ↗Perplexity ↗

How makers use Agenta

What Agenta is used for

LLM Observability & Evals · Open-source platform →An open-source, self-hostable place to manage prompts, run evaluations and trace LLM apps.Trade-off: Pivoted on 2026-07-21 to a workspace for building agents; no longer an observability product.
Datadog50Langfuse35Helicone13LangSmith11Braintrust6Agenta0Makers' products on each, for LLM observability & evals

Agenta vs the alternatives makers chose

OptionMakers' productsFree forAt 10,000 usersOpen source
Datadog50 43%——No
Langfuse35 30%~5,000 users$29/mo · CoreYes
Helicone13 11%~1,000 users$116/mo · ProYes
LangSmith11 9%~520 users$475/mo · DeveloperNo
Braintrust6 5%——No
Weights & Biases3 3%——No
Agenta0 0%——Yes

For LLM observability & evals: how many of the 117 makers' products we know the LLM observability & evals of chose each option, and what each costs at 10,000 users.

Costs are the cheapest plan that fits, from each vendor's pricing page, at the usage our stack planner assumes for a product with that many users. Free for: the users its cheapest plan a business can use stays free for.

When to use Agenta, and when not

Something else fits better if

  • You want tracing, prompts and evals in one tool you can self-host for free: Langfuse.
  • You already use OpenTelemetry or want vendor-neutral instrumentation: Arize Phoenix.
  • You want request logs and costs today by changing one base URL: Helicone.
  • Your app is built on LangChain or LangGraph: LangSmith.
  • Your main question is whether a prompt or model change made outputs better or worse: Braintrust.
From each decision's guide, written from what makers' products chose and why.

How Agenta itself is built

4 tools, from its own code, website and Product Hunt page.

Who uses it

No maker's live product on record yet.

We haven't found a product that uses Agenta yet.

Alternatives to Agenta

All alternatives by situation →

Questions makers ask about Agenta

What are the alternatives to Agenta?

For LLM observability & evals, the other options makers' products we track chose most are Datadog (50), Langfuse (35), Helicone (13), LangSmith (11), Braintrust (6), Weights & Biases (3). Open source or self-hostable among them: Langfuse, Helicone, Weights & Biases. Each alternative, with the situation it fits, is on the Agenta alternatives page.

Is Agenta open source or self-hostable?

Open source, and you can self-host it. source ↗

Can AI coding agents work with Agenta?

No llms.txt, official MCP server or CLI found yet.

Who uses Agenta?

No tracked product yet. source ↗