TensorZero – open-source data and learning flywheel for LLMs
Hi HN! We're Gabriel & Viraj, and we're excited to open source TensorZero. To be a little cheeky, TensorZero is an open-source platform that helps LLM applications graduate from API wrappers into defensible AI products. 1. Integrate our model gateway 2. Send metrics or feedback 3. Unlock compounding improvements in quality, cost, and latency It enables a data & learning flywheel for LLMs by unifying: • Inference: one API for all LLMs, with <1ms P99 overhead • Observability: inference & feedback → your database • Optimization: better prompts, models, inference strategies • Experimentation:…
In plain words
TensorZero is an open-source platform that helps developers build and optimize LLM applications beyond simple API wrappers. It provides a unified gateway for accessing multiple LLMs with minimal latency, tracks inference metrics and feedback, and enables continuous improvement through prompt optimization, model selection, and experimentation features like A/B testing. The platform creates a feedback loop that compounds improvements in quality, cost, and latency for AI applications that learn from real-world usage.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi HN! We're Gabriel & Viraj, and we're excited to open source TensorZero. To be a little cheeky, TensorZero is an open-source platform that helps LLM applications graduate from API wrappers into defensible AI products. 1. Integrate our model gateway 2. Send metrics or feedback 3. Unlock compounding improvements in quality, cost, and latency It enables a data & learning flywheel for LLMs by unifying: • Inference: one API for all LLMs, with <1ms P99 overhead • Observability: inference & feedback → your database • Optimization: better prompts, models, inference strategies • Experimentation: built-in A/B testing, routing, fallbacks Our goal is to help engineers build, manage, and optimize the next generation of LLM applications: AI systems that learn from real-world experience. In addition to a Quick Start (5min) [1] and a Tutorial (30min) [2], we've also published a series of complete runnable examples illustrating TensorZero's data & learning flywheel. • Writing Haikus to Satisfy a Judge with Hidden Preferences [3] – my personal favorite • Fine-Tuning TensorZero JSON Functions for Named Entity Recognition (CoNLL++) [4] • Automated Prompt Engineering for Math Reasoning (GSM8K) with a Custom Recipe (DSPy) [5] ___ [1] https://www.tensorzero.com/docs/gateway/quickstart [2] https://www.tensorzero.com/docs/gateway/tutorial [3] https://github.com/tensorzero/tensorzero/tree/main/examples/... [4] https://github.com/tensorzero/tensorzero/tree/main/examples/... [5] https://github.com/tensorzero/tensorzero/tree/main/examples/... We hope you find TensorZero useful! Feedback and questions are very welcome. If you're interested in using it at work, we'd be happy to set up a Slack channel with your team (free).
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, September 2024
the whole month →
BeforeSunset AI 2.0▲1,267Personalized AI daily planning that suits your life
AI · 2024 · beforesunset.ai
