Net wt. 1 SDK
100% real inference
Nutrition Facts
Serving size: 1 Sipp Client
Amount per pour
- Dependencies0
- Model formatGGUF
- EngineRust + C++ + GGML
- BackendBrowser-nativeWebGPU
% Dev Value
- Open source100%
- Type-safe100%
- Endpoint mixer1 API
Engineered in Rust and C++, Sipp keeps model weights and tokens on-device, minimizing copies across the WASM boundary for real-time games, local agents, and vision/chat apps on WebGPU or desktop. When work moves beyond the device, the same API extends to self-hosted gateways or trusted providers.
Net wt. 1 SDK
100% real inference
Serving size: 1 Sipp Client
Amount per pour
% Dev Value
WebGPU, WASM, Rust, C++, GGUF, TypeScript, OPFS-backed cache, gateways, providers. Contains no black-box runtime, no framework lock-in, no added sugar.
Initialize local WebGPU inference, stream real tokens, and keep GGUF weights in browser storage for repeat runs. Offload to a self-hosted gateway or trusted provider when need, same API.
import { SippClient } from '@sipphq/sipp';
// One client. Pour in the browser or from the cloud.
const blender = new SippClient();
// Run in the browser on WebGPU (or go native: CUDA · Vulkan · Metal)
const juice = await blender.add('local', {
kind: 'local',
source: '/models/llama3.gguf',
});
// ...or pour from a provider you love. Same interface, either way.
const ice = await blender.add('provider', {
kind: 'provider',
provider: 'openai',
model: process.env.OPENAI_MODEL ?? 'gpt-5-mini',
apiKey: requiredEnv('OPENAI_API_KEY'),
});
// Stream inference from either endpoint with one symmetric API
const [smoothie, snowcone] = await Promise.all([
blender.chat([{ role: 'user', content: 'Explain Sipp.' }], { endpoint: juice }),
blender.chat([{ role: 'user', content: 'Create a Sipp app.' }], { endpoint: ice })
]);Sipp's WebGPU backend cuts TTFT and runs decode up to 3x faster against other browser runtimes while keeping the same GGUF weights local. No native install. Pick a model and inspect the multipliers.
Mobile support is currently being worked on. Try demos on desktop.
Sipp vs
8.4×
faster
Sipp vs
5.4×
faster
Measured on Qwen 2.5 0.5B · Q4_K_M. LILO · 1024 in / 512 out · NVIDIA 3080 · Chrome (N=3, 9 runs, 1 warmup). Multipliers show how many times faster Sipp runs vs each browser runtime.
A bare-bones chat running 100% in your browser. Pick a model, start the tap, and then chat. No account, no server.
Mobile support is currently being worked on. Try demos on desktop.
The juice machine
Idle1 · Pick your flavor
Mobile support is currently being worked on. Try demos on desktop.
Real apps running real models with Sipp. No servers, no install, no waiting. Every one runs the model right in your browser.
Mobile support is currently being worked on. Try demos on desktop.
GameDesktop
A wizard duel where every spell is generated on the fly by a local LLM. No two casts the same.
Desktop only
AgentsDesktop
A swarm of little agents reason in-browser, each running a local model to pick its next move, all fighting for one banana.
Desktop only
VisionDesktop
Draw something and a local vision model snapshots the canvas, reads it, and gives you live feedback.
Desktop only
ChatDesktop
Chat with a VRM character whose emotes, actions, and replies are all chosen live by a local model.
Desktop only
The same endpoint API follows you to native runtimes, trusted provider calls, and a self-hosted gateway when you want one boundary for local and remote work.
Run GGUF weights in the browser on WebGPU. Zero install when the work fits on-device, with the same client model available when it does not.
Trusted server routes for local models, provider adapters, and app-owned endpoint policy.
Read the docs ›
Native apps, runtime internals, and gateway builds through the sipp crate.
Read the docs ›
Scripts, notebooks, and services that can register local, gateway, or provider endpoints.
Read the docs ›
Self-host an HTTP boundary that can expose local GPU targets, provider targets, or both under public endpoint names.
Read the docs ›
Fresh batch ready
Install Sipp, run a GGUF model in your browser on WebGPU, then use the same endpoint model across Node, Rust, Python, and the self-hosted gateway.