TensorZero

TensorZero

Open-source stack for industrial-grade LLM applications

4.5
4 reviews

546 followers

Build industrial-grade LLM applications: one API for every LLM, observability, optimization (prompts, models, etc.), evaluations, and A/B testing — all open source. Turn metrics and human feedback into smarter, faster, and cheaper LLMs. Get started in minutes.
TensorZero gallery image
TensorZero gallery image
TensorZero gallery image
TensorZero gallery image
TensorZero gallery image
TensorZero gallery image
Free
Launch Team / Built With
agent by Firecrawl
agent by Firecrawl
Gather structured data wherever it lives on the web
Promoted

What do you think? …

Gabriel Bianconi

Hi Product Hunt - we're the team behind TensorZero, an open-source LLM infrastructure project.

What is TensorZero?

TensorZero is an open-source stack for industrial-grade LLM applications:

  • Gateway: access every LLM provider through a unified API, built for performance (<1ms p99 latency)

  • Observability: store inferences and feedback in your database, available programmatically or in the UI

  • Optimization: collect metrics and human feedback to optimize prompts, models, and inference strategies

  • Evaluation: benchmark individual inferences or end-to-end workflows using heuristics, LLM judges, etc.

  • Experimentation: ship with confidence with built-in A/B testing, routing, fallbacks, retries, etc.

Take what you need, adopt incrementally, and complement with other tools.

https://github.com/tensorzero/tensorzero

Why should you use a tool like this?

Over time, these components enable you to set up a principled feedback loop for your LLM application. The data you collect is tied to your KPIs, ports across model providers, and compounds into a competitive advantage for your business.

Here are some recent blog posts we wrote that illustrate some of the benefits:

We hope TensorZero will be useful to many of you Hunters!

How is TensorZero different from other tools?

1. TensorZero enables you to optimize complex LLM applications based on production metrics and human feedback.

2. TensorZero supports the needs of industrial-grade LLM applications: low latency (thanks to Rust 🦀), high throughput, type safety, self-hosted, GitOps, customizability, etc.

3. TensorZero unifies the entire LLMOps stack, creating compounding benefits. For example, LLM evaluations can be used for fine-tuning models alongside AI judges.

And it's all open source!

How much does TensorZero cost?

Nothing. TensorZero is 100% self-hosted and open-source (Apache 2.0). There are no paid features.

("But really, how do you plan to make money?" PH sneak peek: next year, we're planning to launch an optional, complementary paid service focused on automated LLM optimization, abstracting away all the GPUs needed to handle that. The developer tool we're working on today will remain open source.)

How can I help?

We'd love to get your feedback: features you like, features that are missing, anything confusing in the docs, etc.

TensorZero is 100% open source, so feedback from the builder community helps us prioritize the roadmap, improve the developer experience, fill any gaps in the docs, and so on.

Thank you! Please let us know if you have any questions or feedback.

Kevin Kelleher

Congrats on the launch! It's cool how easy TensorZero makes fine tuning - I think a lot of people skip fine tuning today because setting up data collection/curation/evaluation is such a headache.

Gabriel Bianconi

@k_kelleher Thank you! Yes, we often hear people want to fine-tune but struggle to do it. TensorZero makes it super easy. And results can be very good!

Fine-tuned Small LLMs Can Beat Large Ones at 5-30x Lower Cost with Programmatic Data Curation

Cruise Chen

Unifying all LLM providers into one super-fast API is just genius, tbh—no more hacky integrations or crazy latency. Open-source too? This is wild, team!

Gabriel Bianconi

@cruise_chen Thank you! Hope this is helpful for Agnes AI.

JaredL

Really impressive open-source stack — the unified Gateway plus observability and A/B testing feels very production-ready. Curious: how easy is it to plug TensorZero into an existing CI/CD/GitOps pipeline, and do you provide examples for Kubernetes Helm or Argo workflows?

Gabriel Bianconi

@jaredl Thank you!

It should be straightforward. Here's an example for Kubernetes + Helm:

https://github.com/tensorzero/tensorzero/tree/main/examples/production-deployment-k8s-helm

There are multiple companies using Kubernetes/Helm/Argo.

Danylo Kramin
This looks really promising! Having a unified API for different LLM providers with observability, optimization, and A/B testing built-in is super valuable. I especially like the open-source approach — makes it much easier to adopt incrementally. Curious: do you also plan to support fine-tuning workflows or mainly focus on inference optimization?
Gabriel Bianconi

@cacti We already support fine-tuning! We provide fine-tuning in the UI, programmatically, and in Jupyter notebooks. We also support RLHF and other techniques programmatically (& planning to bring them to the UI soon!).

Andrew Jesson

@cacti Thanks! I recently built new implementations for supervised fine-tuning (SFT) with OpenAI, Google, Fireworks AI, and Together AI. I'm currently working on reinforcement fine-tuning (RFT) with a couple of providers as well, with a lot more on the way! The experiments in our recent blog post utilized these implementations: Fine-tuned Small LLMs Can Beat Large Ones at 5-30x Lower Cost with Programmatic Data Curation

Matt Turck
The feedback loop is what will build long term compounding and defensible advantage for AI applications - and separate winners from losers. Congrats team, very exciting.
Gabriel Bianconi

@mattturck Thanks Matt! Appreciate you supporting TensorZero!

A.Laksir

Congrats on launch! Can I swap model providers per request and get latency/cost dashboards out of the box?

Gabriel Bianconi

@anwarlaksir You can swap model providers per request by changing the `model_name` during inference!

We're about to ship a latency/cost dashboard as well! Latency should come out very soon, we have an internal version already. Thanks!

123
•••
Next
Last