Skip to main content
Helix AI
A 3D rainbow abstract generated graphic of a ribbon helix

helix

Private GenAI Platform

We make open source models work.
Build AI apps with tools, RAG and fine-tuning.
Deploy on-prem or in your VPC

Get Started Arrow right
1

Curated Models

The best open LLMs, secure, scalable & private. Optionally pass through to closed models

Mistral AI - makers of Mistral-7B and Mixtral
Meta - CodeLlama still winning coding benchmarks
Cohere - Command-R models winning in the LMSys arena
SDXL - high quality image generation and fine tuning
OpenAI - pass through to GPT-4 if you need it
Claude - new contender from Anthropic, available on AWS
Gemini from Google - good on Google Cloud
2

Helix API Tools

Connect and drive internal & external APIs with natural language, such as customer purchase histories

Connect with CRM APIs like Salesforce
Connect with CRM APIs like HubSpot
Connect with hiring systems like Greenhouse
Connect with HR systems like Bamboo
Connect with marketing systems like Marketo
Connect with product systems like JIRA
Connect with product systems like Asana
Connect with finance systems like Quickbooks
Connect with support systems like Zendesk
Connect with Oracle databases and products
Connect with any API with a Swagger/OpenAPI spec
3

Helix Assistants

Embed our widget into your websites / apps to add a chatbot specialized with tools and knowledge.   See also Helix Searchbots

Embed into Wordpress
Embed into Shopify
Embed into Wix
Embed into Squarespace
Embed in any HTML website!
4

Build AI Apps

Write application logic in natural language and deploy Javascript frontends for AI agents

Write gptscript for natural language AI powered apps
Run untrusted LLM generated code in a secure Firecracker microVM
Embed into React
Embed into Vue.js
Embed into any Javascript app
5

Better RAG

Innovative RAG system uses Q&A generation to augment vector graph database for better answers

Ingest from Slack
Ingest from Google Drive
Ingest from JIRA
Ingest from Notion
Ingest from GitHub
PGVector
Neo4j
6

Fine-tune models

Build your own smaller models, specialized in your domain and tooling to reduce energy and cost at scale

Fine-tune Mistral-7B on PDF
Fine-tune Mistral-7B on Word
Fine-tune Mistral-7B on Markdown
Fine-tune Mistral-7B on Text
Fine-tune Mistral-7B
7

Secure to operate

Deploy privately on Kubernetes or Docker and in any cloud. Attach hybrid runners flexibly

Deploy control plane and/or runners with Helm on Kubernetes
Deploy control plane easily with Docker Compose and GPU runners with Docker
Deploy on VMware
Deploy easily on AWS
Deploy easily on GCP
Deploy easily on Azure
Deploy low cost GPU runners from RunPod
A generated image of a swirling nebula

Pricing

Helix Cloud has free and premium tiers: $20/month which gives you GPU priority. We also offer the following tiers for deployment of our software in your own cloud or data center.

Try free

Personal

  • Individuals
  • Non–commercial, open source developers
  • Students and Educators
  • Companies with fewer than 250 employees & less than $10 million in annual revenue
Deploy Helix Arrow right
Go pro

Organization

  • Companies with more than 250 employees
  • Companies with more than $10 million annual revenue
  • Available in professional, team or business flavours, depending on your needs
Enquire

Take a look

Not convinced?

We’re always happy to help, but if you’ve got a burning question you need answering, try one of the following channels

FAQ Discord Newsletter Try it!