NewNew AI templates in the catalog: Flowise, Langflow, SearXNG, Text Embeddings Inference.See them →
Kilby byNeuramorphic

Public beta · free while it lasts

The cloud for AI apps, agents and models.

Deploy from Git, a container image or one of 17 templates. Kilby runs it on AWS with Postgres and pgvector, private networking and logs, plus an API and an MCP server your agents can drive.

Already have an account? Log in

kilby.neuramorphic.ai/dashboard
AI workspaceUS East (Ohio)
  • open-webuiWeb serviceLive
  • ollamaPrivate serviceLive
  • qdrantPrivate serviceLive
  • mainPostgres 17 · pgvectorAvailable
  • agent-apiWeb service · from GitDeploying
your agent, through Kilby's MCP server
# a recorded session
→ check_image ghcr.io/open-webui/open-webui:main
← Found · sha256:59b912d42461 · linux/arm64, linux/amd64 · 1.6 GB
→ deploy_template qdrant
← Other services in this workspace call it at http://qdrant:6333 and send the key in the api-key header.

Your stack

Whatever your AI stack, it runs on Kilby.

Bring a Dockerfile, Python, Node.js or Go, and the AI tools around them. Or start from one of 17 templates, with the price shown before you deploy.

View templates

Templates

Start from an AI template.

17 templates: open models on CPU, chat interfaces, vector databases and agent builders, each with its list price. Each one is a normal Kilby service you can change afterwards.

View all templates
AI apps NeuraTensor Serve your own NeuraTensor model, a spiking state-space sequence model, behind an API key. On CPU. 1 private service$26.25/mo list price AI apps Open WebUI A chat interface for language models, with accounts, history and document upload. 1 web service$26.25/mo list price AI apps Open WebUI with Ollama Open WebUI and a private Ollama server, wired together. llama3.2:1b fits in the model server's 2 GB; llama3.2:3b does not. 1 private service and 1 web service$53.75/mo list price AI apps LiteLLM Proxy One OpenAI-compatible API in front of OpenAI, Anthropic and more, with a single key. 1 web service$25/mo list price AI apps Ollama (CPU) Run small open models on CPU as a private service your other services call. llama3.2:1b fits in its 2 GB; llama3.2:3b does not. 1 private service$27.50/mo list price AI apps Flowise Build AI agents and chat flows on a canvas, and serve each one as an API.First visitor becomes admin 1 web service$26.25/mo list price AI apps Langflow Build AI agents and retrieval flows on a canvas, behind a sign-in, and serve each one as an API. 1 web service$26.25/mo list price AI apps SearXNG A private web search API for your agents and chat tools, without tracking. 1 private service$25/mo list price AI apps Text Embeddings Inference (CPU) An embeddings server for retrieval apps, as a private service with an API key. 1 private service$26.25/mo list price Vector databases Qdrant A vector database with a REST API and an API key, on its own disk. 1 private service$10.25/mo list price Vector databases Chroma A simple vector database for prototypes and small retrieval apps. 1 private service$10.25/mo list price Automation n8n Workflow automation with hundreds of integrations and AI nodes.First visitor becomes admin 1 web service$26.25/mo list price Data Valkey A Redis-compatible key-value store with a password and a disk. 1 private service$9.25/mo list price Web Static page (nginx) A web page served by nginx. The quickest way to see a deploy work. 1 web service$9/mo list price Web Uptime Kuma Monitor your sites and APIs and get alerts when they go down.First visitor becomes admin 1 web service$9.25/mo list price AI apps vLLM (GPU) A fast OpenAI-compatible server for open models, on a GPU. 1 private serviceNeeds a GPU · not available yet AI apps Ollama (GPU) Run open models on a GPU as a private service. 1 private serviceNeeds a GPU · not available yet

Prices are list prices per month for what each template creates (instances and disks). Public beta: nothing is charged.

AI

Models, your way.

Run open models next to your app, serve your own, or put one key in front of every provider.

Open models on CPU

Ollama with Open WebUI, and Text Embeddings Inference, as private services that only your workspace can reach. In our test, llama3.2:1b answered at about 12.7 tokens per second on one CPU core.

Open WebUI with Ollama
Neuramorphic

NeuraTensor

Neuramorphic's open-source SDK for neuromorphic sequence models in pure PyTorch: spiking neurons with selective state space models, on CPU, CUDA or Apple Silicon. Package it with a Dockerfile and serve it as a private service.

$ pip install neuratensor
from neuratensor import InferenceEngine
engine = InferenceEngine.from_preset("small")
result = engine.run(input_ids)
NeuraTensor on GitHub

Every provider, one key

LiteLLM in front of OpenAI, Anthropic and more: one OpenAI-compatible endpoint and a single key for all of your apps, with the provider keys kept in its environment.

LiteLLM Proxy

GPU instance types are not available yet: the vLLM and Ollama GPU templates show what they will run.

Agents

Your agents can ship, too.

Kilby's MCP server gives an agent 24 tools: plan and deploy from Git, read build logs, set environment variables, deploy a template, explain a failed deploy. The same actions are in the REST API and the kilby CLI.

plan_deploydeploy_from_gitget_build_logsexplain_deploydeploy_templateset_envredeploy_servicecheck_image+16 more
Read the docs
terminal
# paste an API key; the input is hidden
$ kilby login
# deploy a folder of a repository
$ kilby deploy --repo acme/agents --root api
# or let your coding agent do it
$ kilby mcp

Platform

Everything an AI product needs to run.

Push to deploy

From public or private GitHub repositories. A push that does not touch a service's folder does not rebuild it.

Postgres with pgvector

Managed Postgres 17 and 18, with backups you can restore to any point in the last 7 days.

Logs you can search

Every service's output is kept for 7 days, and a container that restarts is recorded with the reason.

Rollbacks

Go back to a version that ran. The dashboard shows what will change before you confirm.

Private by default

Each workspace runs isolated from the others. Private services are reachable only from inside it.

Your domains

Point a domain at a service and Kilby gets its certificate.

Workers, cron and disks

Background workers, scheduled jobs, persistent disks and autoscaling, next to your web services.

Prices before you click

Every form shows the list price of what you are about to create. Public beta: nothing is charged.

Ship your first AI app today.

Create an account, confirm your email and deploy. Kilby is in public beta and free while it lasts.