Open-source Braintrust alternatives

Langfuse is an open-source LLM engineering platform that helps teams develop, monitor, evaluate and debug AI applications together. You instrument your app, and Langfuse records traces of LLM calls and surrounding logic such as retrieval, embeddings and agent actions, so complex runs and user sessions can be inspected and debugged.

Prompt management lets you centrally version and iterate on prompts, with caching on server and client so that changes do not add latency to your app. Evaluation features cover LLM-as-a-judge, code evaluators, user feedback, manual labeling and custom pipelines through the API and SDKs. Datasets provide test sets and benchmarks, there is an LLM playground for trying prompts, and integrations exist for OpenAI, LangChain and LlamaIndex. It is built on the ClickHouse database, and the Langfuse team has been part of ClickHouse since January 2026.

You can use Langfuse Cloud or self-host it, which the maintainers say takes minutes. The repository license is listed as 'Other' because it combines open-source and enterprise components, so check the terms. It suits teams shipping production LLM features who need visibility into quality, latency and cost.

Promptfoo is an open-source command-line tool and library for testing applications built on large language models. Developers describe test cases and checks in declarative configuration files, run them against one or more models, and review the results, which replaces manual trial and error with repeatable evaluations. It is written in TypeScript and released under the MIT license.

Beyond quality testing, Promptfoo includes red teaming and vulnerability scanning for AI systems, probing prompts, agents, and retrieval-augmented generation (RAG) pipelines for security and safety weaknesses. It can compare models from providers such as OpenAI, Anthropic, Azure, Bedrock, and Ollama side by side, and it works with any LLM API or programming language. Its documentation also covers a code-scanning feature that reviews pull requests for LLM-related security and compliance issues.

The project is designed to run locally: the maintainers state that evaluations execute on the developer's own machine, so prompts only leave it when a chosen model provider receives them. It can be installed with Homebrew or pip, or run without installing via npx, and it plugs into CI/CD so checks run automatically on each change. The README notes that Promptfoo is now part of OpenAI while remaining open source and MIT licensed.

Opik is an open-source LLM observability and evaluation platform built by Comet. It covers the application lifecycle starting with early traces during development and ending with production monitoring, for teams that build LLM apps and AI agents. The code is Python, licensed under Apache-2.0, and the README says the full platform is free to self-host. The project documentation lives on the Comet site.

Capabilities include deep tracing of LLM calls and agent activity including complete trace trees for agents with several steps and tool calls, and evaluation with datasets, experiments and LLM-as-a-judge metrics for tasks like hallucination detection, moderation and RAG assessment. An Agent Optimizer SDK improves prompts and agents, dashboards and online evaluation rules support production monitoring, guardrails help with safe AI practices, and a PyTest integration tests LLM pipelines on each commit. Integrations include frameworks such as LangChain, LlamaIndex and OpenAI clients.

Arize Phoenix is an open-source AI observability platform for experimentation, evaluation and troubleshooting. It helps teams building applications on large language models understand what their systems are doing at runtime, measure quality and debug problems before and after release.

Tracing relies on OpenTelemetry-based instrumentation to record an LLM application's runtime behavior. Evaluation uses LLMs to benchmark an application's performance with response and retrieval evals, and datasets can be versioned. The topics point to integrations with OpenAI, Anthropic, LangChain, LlamaIndex and smolagents, as well as work on agents and prompt engineering.

Phoenix is written in Python and published under a license listed in the repository. For managed production workflows, Arize also offers a separate product called Arize AX. The README is available in English and Simplified Chinese, and the project documentation is hosted on the Arize site.

LangWatch is an Apache-2.0 platform for running AI in production. It lets teams trace, test, route and govern LLM calls across the company, covering both the agents they build themselves and the coding assistants their engineers use. The project is aimed at AI engineers and platform teams that need visibility and control over model usage.

Its feature areas include LLM operations such as observability, agent testing, evaluations and prompt management, plus tracking of coding agent sessions with cost per pull request and per team and privacy controls. An AI gateway offers a single endpoint compatible with the OpenAI and Anthropic APIs, with virtual keys, budgets and routing, and an AI governance layer sits on top. Repository topics mention DSPy, datasets, simulation testing and low-code evaluation.

LangWatch is written in TypeScript and can be used through LangWatch Cloud or self-hosted; the README says only Node.js is required to try it locally, with separate guidance for production deployments. It suits teams moving LLM prototypes into monitored, tested production systems.

Laminar is an open-source observability platform built for AI agents. It records what agents do during each run so that teams can debug failures, track behavior, and measure quality. The project is released under the Apache-2.0 license and the backend is written largely in Rust, with a TypeScript front end.

Tracing is based on OpenTelemetry, and a single line of SDK setup can automatically trace libraries such as the Vercel AI SDK, Browser Use, Stagehand, LangChain, OpenAI, Anthropic, and Gemini. Signals let you describe a behavior, such as an agent getting stuck in a loop, in plain English and be notified in Slack when it occurs. Evals run through an SDK and CLI locally or in CI, with a UI for comparing results, and SQL queries and dashboards cover traces, metrics, and events.

Coding agents can reach the data through MCP and CLI access to investigate issues themselves. Laminar can be self-hosted locally with Docker Compose, or used as the managed platform at laminar.sh. It suits teams building production agents who need tracing, evaluation datasets, and annotation in one place.

UpTrain is an open-source platform aimed at teams building generative AI applications who need a structured way to evaluate output quality rather than eyeballing responses manually. It targets common LLM reliability problems such as hallucination and jailbreak attempts, alongside more general prompt and output quality checks.

It provides grades for more than 20 preconfigured checks covering language, code and embedding-based use cases, and when a check fails, it performs root cause analysis on the failure case and gives insights on how to resolve it, rather than just reporting a pass/fail score. Its topics also cover experimentation, prompt engineering support, and comparisons to tools such as OpenAI Evals, positioning it within the broader LLMOps evaluation space.

UpTrain is written in Python and released under the Apache-2.0 license, so it can be run and self-hosted as part of an existing ML or LLM pipeline. It is aimed at developers integrating evaluation directly into their generative AI development and monitoring workflow.