app.nzapp
AppsProjectsReposPullsChatIntegrationsGatewayModelsEvalsToolsDatasetsMCPDeploysPricingBlogDocsAssistantsCharactersArtMusic
Sign inStart building
Agent stack
Cloud coding agentAgents SDKIntegrationsBrowser agentMonitors & auto-agentsSchedulersAgent skillsMCP serversDeep research
Models & API
AI GatewayModel catalogModel evalsModel spacesPlaygroundText to imageImage to 3DText to 3DMusic & SFXAudio editorMedia optimizerAI art & libraryChatAPI referenceSchemaBecome a provider
Compute & hosting
DeploysAddonsPostgres hostinggobed vector searchSite hostingAnalyticsCog GPU hostingRL trainingBuilds & CIWorkersTask queuesDomainsGit hosting
Tools
AI toolsDrawDiffusion canvasLive DrawWriteSheetsArtifactsVideo studioNotebooksDatasets
Learn
DocsBlogEval guidesPrompt libraryCLIAlternativesPapersAI charactersArt gallerySecurityConsulting
Company
PricingEnterpriseSettingsBillingStatusInvestorsCreate accountTerms of ServicePrivacy Policy
app.nzapp.nz

AI agent cloud for coding, deploys, model routing, and research. Built for teams shipping software.

Built in New Zealand by App AI NZ.

Social
X / TwitterGitHubYouTube
The app.nz network
GpuBrainPapersReading TimeNetwrckText-Generator.ioCodex InfinityOpenPathsCuteDSLAI Art GeneratorAIArt-Generator.artSiteSimSimplexGenDictatorFlowWebFiddleRing.nzChatGibidyBitBankExperimentFlowEvangelerHires.nzHow.nzV5 GamesAddicting Word GamesBig Multiplayer ChessWord SmashingreWord GameMultiplication Master
© 2026 App AI NZ Ltd. All rights reserved.All systems normalTermsPrivacy

Blog

Building the AI agent cloud

Practical notes on agents, model routing, inference, deploys, GPU infrastructure, evals, and the systems work behind app.nz.

Jul 21, 2026·11 min read

Building Polygonalize: stable low-poly video with Go, WASM, Canvas, and Three.js

How we built a free open-source image and video polygonalizer: edge-aware meshes up to 20,000 triangles, custom transparent primitives, stable video topology, Go/WASM, Canvas, Three.js, a CLI, and an app.nz serverless fallback.

open-sourcegolangwasmvideothreejscreative-tools
Jul 20, 2026·6 min read

Throughput on a shared GPU: fused kernels and a priority scheduler

How we serve chat, image, video, TTS, STT and a LoRA army on shared GPUs — 2× LLM tok/s (fp8+MTP), a fused multi-LoRA kernel (up to 2.4×), a 10.4× admission gate, tier-based VRAM arbitration, and cheaper building blocks (916k embeds/sec, Gemini STT).

performancegpuinferenceschedulingkernels
Jul 20, 2026·6 min read

Packaging AlayaWorld: an interactive video world model as a self-hosted Cog

Wrapping AlayaLab’s autoregressive world model (LTX-2.3-derived DiT + gemma-3-12b + Depth-Anything-3) as a Cog: camera presets, a warm engine, and an honest look at the LTX-2 Community License.

open-sourcecogvideoworld-modelgpulicensing
Jul 20, 2026·8 min read

From Artificial Analysis to production: the useful eval loop

How to turn Artificial Analysis, Arena, LiveBench, SWE-bench, and open leaderboards into a runnable shortlist, workload eval, and production model decision.

evalsmodelsbenchmarksartificial-analysisgateway
Jul 20, 2026·7 min read

Comfy models: from media evals to working GPU inference

Connect image and video benchmark evidence to hosted FLUX, SDXL, LTX, and Wan workflows, reproducible JSON, model provenance, and a global R2 weight cache.

comfyevalsimagevideogpur2
Jul 20, 2026·9 min read

Anatomy of an AI compute marketplace: tokens, GPU-seconds, and agent-hours on one set of rails

A deep tech dive on app.nz as a compute marketplace: 232 models across 24 providers with price-ordered self-healing failover, GPU placement that learns cold starts and arbitrages clouds under a fixed price, margins enforced as unit tests, and an agent layer that makes the whole market liquid.

infrastructuregpugatewayagentsmarketplacesinvestors
Jul 20, 2026·10 min read

The next ten years: minds as products, machine-speed markets, and why big labs are the new big tech

A ten-year thesis: AI minds with personality and skills become a product category, robots become software subscriptions, marketplaces go high-frequency and low-fee, humans and governments get augmented, and vertically integrated labs become the new big tech — with sources, and the app.nz strategy behind it.

futurismagentsroboticsmarketplacesinvestorsstrategy
Jul 19, 2026·7 min read

1ms web search: gobed int8 embeddings, a self-improving index, and agent tools for flash-tier models

How app.nz search answers repeat queries in ~1ms: int8-quantized gobed embeddings at ~600 bytes/doc, a learned index fed by every search and research run, and agent tool design that cheap fast models like DeepSeek actually use well.

searchembeddingsgobedagentsinfrastructure
Jul 18, 2026·6 min read

Five-minute training runs: capped QLoRA slices and autoresearch on RunPod

Why we cap every training run at 5 minutes: chained resumable QLoRA micro-runs, a GPU-minute budget ledger, a pod reaper, and a karpathy-style hyperparameter autoresearch loop.

trainingqlorarunpodautoresearchinfrastructure
Jul 17, 2026·5 min read

Designing animation asset galleries for agents

A stable search and download contract for motion, VFX, terrain, 3D objects, REST, CLI, and MCP clients.

agentsmcpanimationapiopen-source
Jul 17, 2026·5 min read

From reference image to indexed, downloadable 3D object

How the app.nz image-to-3D gallery connects reference images, reconstruction recipes, OBJ downloads, and production generation jobs.

image-to-3d3dobjectsapithreejs
Jul 17, 2026·6 min read

Opening the app.nz motion, VFX, and terrain commons

Three pose-capture backends, retargetable character motion, configurable Three.js effects, deterministic terrain, and procedural object generators — open, searchable, and available through web, CLI, API, desktop, and MCP.

animationvfx3dthreejsopen-sourcemcp
Jul 16, 2026·4 min read

Kimi K3: the largest open model, live on the app.nz gateway

Moonshot's 2.8T-parameter Kimi K3 with a flat-priced 1M context window is available now as kimi-k3 — direct Moonshot routing, automatic failover, one metered key.

modelskimimoonshotgatewayopen-source
Jul 15, 2026·7 min read

polyserve: in-process serverless that packs hundreds of apps into one process

Announcing polyserve, the open-source in-process serverless host behind app.nz: per-second billing via busy_ms and warm_s, hot-swap deploys, scale-to-zero, and autoscaling to Hetzner and RunPod GPUs.

polyserveserverlesshostingopen-source
Jul 15, 2026·8 min read

Inside the polyserve Go host: fasthttp, unix-socket slots, and zero-drop hot swaps

How one fasthttp process serves many compiled Go apps with microsecond proxy overhead, atomic generation swaps with a 5s drain, and Postgres addons via injected DATABASE_URL.

polyservegolangfasthttphosting
Jul 15, 2026·6 min read

Serving tiny ONNX models serverlessly, in-process

Why in-process beats a dedicated model server for small ONNX models: warm sessions in one asyncio host, sub-500ms cold starts, honest per-second metering, and RunPod GPU autoscaling for bigger models.

polyserveonnxpythongpu
Jul 15, 2026·5 min read

polyserve deploy docs: Go, Python, and Bun quickstarts

Per-language deploy quickstarts for polyserve spaces plus the full host control protocol: deploy, usage, health, routing, scale-to-zero, env vars, addons, and the autoscaler contract.

polyservedocshostingserverless
Jul 15, 2026·6 min read

Interactive world models on app.nz: GPU sessions, ABot-World, and ARDY

World models need a GPU that stays up and talks over a socket. How the new session-cog protocol works, the two open-source world models you can drive today, and the harness that keeps every cog README honest with real runs.

world-modelscogsgpusessionsopen-sourcerunpod
Jul 13, 2026·7 min read

What is an AI agent cloud?

Why app.nz is broader than a coding agent, model gateway, inference provider, or app host—and how one integrated loop changes the work of shipping AI software.

agentscloudgatewaydeploysinferenceplatform
Jul 7, 2026·4 min read

Hardening route HTML, desktop deep links, and notebook paths

A small production hardening pass: serving generated SEO HTML, keeping desktop notebook paths inside the workspace, and fixing one-pass deep-link URL encoding.

desktopsecurityseoengineering
Jul 7, 2026·7 min read

How app.nz hosted training works

The control plane behind app.nz fine-tuning: model catalogues, hardware offers, durable jobs, signed trainer specs, progress callbacks, R2 artifacts, publishing, and deploys.

traininggpurunpodinfrastructure
Jul 7, 2026·6 min read

Keeping training GPUs busy without wasting memory

The app.nz training worker checklist: conservative VRAM floors, bf16/TF32 defaults, efficient attention, dataloaders, direct artifact I/O, torch.compile tradeoffs, and phase-by-phase memory release.

traininggpuperformancepytorch
Jul 7, 2026·7 min read

Deploying Rust in under five seconds

Fast Rust deploys come from separating build time from release time: compile once, push a small runtime image or static bundle, then publish by swapping bytes or image refs.

deploysrustcontainersperformance
Jul 7, 2026·7 min read

How we built isolated containers for agents and CI

The app.nz isolation model: per-run Docker networks, per-step containers, service sidecars, temp Docker auth, label cleanup, timeouts, and remote machines for bigger blast-radius boundaries.

containersagentscisecurity
Jul 7, 2026·8 min read

How app.nz runs GPUs on demand

Inside the GPU lifecycle: hardware catalogues with VRAM and compute capability, Cog cold starts, local GPU headroom, RunPod pods, schema introspection, metering, and idle reaping.

gpucogsrunpodinference
Jul 7, 2026·7 min read

Why Docker cold starts are slow

A cold start is scheduling, image pull, Python import, CUDA init, weight loading, compilation, readiness, and first inference. Here is how app.nz reduces each part.

containersgpuperformanceinference
Jul 7, 2026·8 min read

Dynamic routing across model providers

How the app.nz gateway resolves aliases, classifies auto routes, chooses BYOK or platform keys, walks fallback chains, adapts provider APIs, and meters usage from one catalogue.

gatewaymodelsroutingproviders
Jul 7, 2026·7 min read

Serverless vs serverful GPU inference

The GPU router behind app.nz cogs and Comfy deployments: local headroom, RunPod serverless, dedicated pods, hysteresis, single-flight cold starts, and when each tier wins.

gpuserverlessroutinginference
Jul 7, 2026·6 min read

Serving static sites from R2 and a database

The fast path behind app.nz static deploys: upload changed files, prune removed paths, index them in the database, and serve bytes directly from R2 or local storage.

sitesr2deploysperformance
Jul 7, 2026·6 min read

Build Studio: private container builds for app.nz

How app.nz turns a Dockerfile and build context into a private registry image, with scoped Docker auth, namespaced image refs, redacted logs, and a clean release boundary.

buildscontainersregistrydeploys
Jul 7, 2026·5 min read

appnz.yaml: the runtime contract

Why app.nz separates static and server runtimes with a small config file instead of guessing forever from package.json, Cargo.toml, dist folders, or Dockerfiles.

deploysconfigruntimebuilds
Jul 7, 2026·6 min read

CI service containers without shared state

Inside app.nz CI: per-run Docker networks, Postgres/Redis/Mongo service aliases, per-step containers, readiness checks, timeouts, and label-based cleanup.

cicontainerspostgresredis
Jul 7, 2026·6 min read

How coding agents become durable worker jobs

A coding-agent prompt becomes a stored task, a leased worker job, an event stream, and durable artifacts instead of a long HTTP request that disappears on failure.

agentsworkersqueuesreliability
Jul 7, 2026·6 min read

Metering the model gateway without guessing

How app.nz meters token streams, image responses, media jobs, BYOK traffic, failures, and routed provider/model pairs from the same catalogue used for pricing.

gatewaybillingmodelspricing
Jul 7, 2026·5 min read

BYOK provider keys in the model gateway

How app.nz lets users bring provider keys while keeping routing unified, validating providers, preferring user keys, hiding full secrets, and avoiding open-relay behavior.

gatewaybyoksecurityproviders
Jul 7, 2026·5 min read

Making Cog containers self-describing

How app.nz warms Cog containers, waits for real readiness, reads health and OpenAPI endpoints, and turns model schemas into typed prediction forms.

cogsgpuschemainference
Jul 7, 2026·5 min read

Mirroring ComfyUI models to make cold starts boring

Why app.nz mirrors popular Comfy model weights into R2 so GPU workers fetch predictable artifacts instead of relying on third-party hosts during cold starts.

comfygpur2performance
Jul 7, 2026·5 min read

RunPod serverless endpoints under the hood

How app.nz creates scale-to-zero GPU endpoints with bounded workers, queue-delay scaling, endpoint reuse, job polling, image updates, and explicit failure handling.

runpodserverlessgpuinference
Jul 7, 2026·6 min read

The lifecycle of an app.nz cloud machine

Provisioning is more than create: app.nz tracks provider ids, machine status, ready times, termination, simulated providers, and cleanup for CPU and GPU infrastructure.

provisioninghetznerrunpodinfrastructure
Jul 7, 2026·5 min read

Metering notebooks by the minute

How app.nz notebooks run free in the browser or on metered CPU/GPU sessions with pricing from the same endpoint, idle stop, balance stop, and durable session rows.

notebooksbillinggpumarimo
Jul 7, 2026·5 min read

Queues, visibility timeouts, and dead messages

The queue primitive behind app.nz background work: receive as a lease, ack on success, retry after visibility timeout, and move poison messages to dead state.

queuesworkersreliabilityagents
Jul 7, 2026·5 min read

Durable artifacts for coding agents

Why app.nz stores agent diffs, logs, previews, screenshots, and generated files as artifacts so a run remains auditable after the worker shuts down.

agentsartifactsr2deploys
Jul 13, 2026·4 min read

Cheaper GPUs by scheduling: multi-cloud arbitrage, hidden cold starts, and cogs that learn their own footprint

How app.nz cog hosting cut serving costs: community-first multi-cloud provisioning under a fixed price, serverless hedging that hides pod cold starts, and per-model learned stats (cold-start EMA, peak VRAM) that feed routing and future GPU bin-packing.

gpueconomicsmulti-cloudserverlesscogsautoscalingomniserve
Jul 10, 2026·4 min read

Hosted addons: Postgres with pgvector + PostGIS, and gobed GPU vector search

Attach managed services to any app or agent in one command — gobed GPU CAGRA vector search, PostgreSQL with HNSW vectors, PostGIS and graph traversal, Mongo, cache, auth, and AI monitoring — with env vars injected into every runtime.

addonspostgrespgvectorpostgisvector-searchgobedcliagents
Jul 10, 2026·7 min read

Run cloud agent tasks on your own computers with app worker

Fire an agent task from your phone and let your desktop code it: app worker turns any machine you own into a private, user-scoped worker with local engines — our codex fork (mainline fallback), claude, cursor-agent, gemini, grok.

agentsworkersclilocalcoding
Jul 10, 2026·3 min read

We open-sourced our investor room

The app.nz data room is now public pages: the 10-year vision, a full technical deep dive (architecture, ~1 ms routing, security, economics, benchmarks, roadmap, risks), all versioned in the repo.

companyinvestorsopen-sourceroutingagents
Jul 10, 2026·5 min read

Will it fit? An AI agent that 3D bin-packs your life into a van

A chat agent that estimates real item sizes, runs 3D bin-packing algorithms, and renders interactive three.js loading plans — with an honest verdict when it will not fit. Plus a free /api/packing/solve API.

3dpackingagentsthreejsapi
Jul 2, 2026·4 min read

Hosted notebooks: marimo in the browser or on cloud GPUs, billed per minute

app.nz notebooks run free on Pyodide in your browser or on per-minute CPU/GPU machines that stop themselves when idle. Plus SQLite, Parquet, and agent-trace dataset viewers with HTTP range reads.

notebooksdatasetsgpupythonpricing
Jun 26, 2026·5 min read

app.nz is now an MCP server

Point Claude, Codex, or any MCP client at app.nz/mcp and your agent can run every gateway model — chat, images, embeddings — plus search the MCP directory, through one connector and one API key.

mcpagentsgatewaytools
Jun 25, 2026·5 min read

Cloud coding agents: one prompt, one pull request

Run coding agents in sandboxed cloud environments instead of on your laptop — provider-aware (Codex, Claude Code, or our runner), skill-attachable, triggerable by schedules and webhooks.

agentscloudcodingcli
Jun 24, 2026·4 min read

Instant static deploys: from directory to URL in one command

app.nz hosts static sites behind a URL instantly — app sites deploy uploads, diffs, and prunes a directory so a deploy is the exact state of your build, scriptable into CI or an agent run.

sitesdeployshostingcli
Jun 26, 2026·6 min read

A searchable directory of 120+ MCP servers

What the Model Context Protocol is, how to wire a server into Claude or Codex, and a new searchable index of 120+ MCP servers filterable by category and pricing.

mcpagentstoolsdirectory
Jun 19, 2026·8 min read

Test-time training is a linear attention operator in disguise

A small reproduction of a 2026 paper showing that key-value-binding TTT unrolls into a linear-attention state, plus sweeps for extra inner steps, query mismatch, gradient sign, and momentum.

paperstest-time traininglinear attentionsequence models
Jun 19, 2026·7 min read

An attention sink can mean two opposite things

A small reproduction of a June 2026 paper showing that the same attention stripe can be either a no-op or a broadcast channel.

papersinterpretabilitytransformersattention
Jun 2, 2026·5 min read

The best coding models in 2026: a hands-on comparison

How to pick a coding model by the job — frontier vs agentic-mid vs fast — measured on cost per merged PR, not cost per token.

modelscodingcomparisonagents
May 26, 2026·4 min read

Cheap and fast: choosing budget LLMs for high-volume work

A 3-step workflow to find the cheapest model that still clears your quality bar — measured as cost per acceptable output.

modelspricingevalscomparison
May 19, 2026·6 min read

How to optimize prompts with evals (LLM-as-a-judge)

Treat prompts like code: score them with an eval, then let the optimizer search for a better one against your own dataset.

promptsevalsoptimizationllm-as-judge