Olla v0.0.28
The latest stable build of our open-source LLM proxy and load balancer.
Deploy LLMs on Your Own Infrastructure.
From Lab to Enterprise.
We build the foundational tools and platforms that empower organisations to deploy, manage and scale AI applications with confidence on their own terms.
LATEST FROM THE FOUNDRY
What's new
Fresh releases, announcements and writing from the workshop.
Olla v0.0.28: Native oMLX Support, Per-Endpoint Auth & CORS
Olla v0.0.28 is a big release: native oMLX support for fast multi-model inference on Apple Silicon with Anthropic passthrough, per-endpoint authentication for local backends, opt-in CORS for browser clients, and a round of Anthropic translation and reliability hardening.
Run MLX Behind Olla on Your Mac
Put oMLX and your other Mac inference backends behind one OpenAI endpoint with Olla - model unification across MLX and GGUF naming, Anthropic passthrough and failover.
PRODUCT ECOSYSTEM
From user to backend - every layer
TensorFoundry covers the full LLM stack. Pick the layers you need.
FEATURED PRODUCTS
Start with what you need
From open-source tools to enterprise platforms
OUR JOURNEY
Building Data-led AI Innovation for 10+ Years
From ML pipelines to enterprise orchestration - a snapshot of our team's journey.
Why Local AI?
Deploy AI where it matters most - at the edge or closer to you, on your own terms.
Privacy First
Keep sensitive data on-premises. Finely tune models and maintain complete sovereignty without Cloud.
Low Latency
Sub-millisecond response times with edge deployment. Eliminate network overhead for real-time AI.
Cost Effective
Reduce cloud API costs by 90%. Pay once for hardware, run inference & training indefinitely.
Optimised Performance
Hardware-accelerated inference with support for CUDA, Metal and custom accelerators.
OPEN SOURCE
Join the Olla Community
Open-source AI inference proxy perfect for small businesses and development teams. Unified interface for Ollama, LM Studio, vLLM and others with load balancing and failover.
20K+
Container Pulls
200+
GitHub Stars
Apache 2.0
Open Source
EARLY ACCESS
Get Early Access to the Full Stack
Join the waitlist for priority access to Alloy, FoundryOS, Pivotal and Forge as they launch through 2026.
Get exclusive updates, beta access and founding member pricing.
Priority Beta Access
Up to 50% Off Licensing
Direct Engineering Access
Now Olla + Kaizen
Q2 2026 Alloy + FoundryOS + Pivotal
Q3 2026 Forge Preview
Ready to deploy AI at the edge?
Let TensorFoundry build your AI Inference & Training Lab for you.