Free local AI inference · no Saient key

Your machine.
Your model.
Your AI workshop.

Saient is a local AI desktop app — chat, a real coding agent, image & video generation, a vision analyzer, text-to-speech, and LoRA training, running on your own hardware. Local inference needs no Saient account, licence key or hosted-inference key.

Tauri + Svelte tinyq4 GGUF engine GPU-accelerated
[>_<]
/|#|\
/   \
saient — agent · ~/projects/snake
What's inside

One app. Seven studios. No required cloud inference.

Task-focused local AI tools in a single native window. Language, image, video and speech use model-specific local runtimes.

>_

Chat

Talk to any local GGUF model. Renders live HTML artifacts in a side pane — ask it to build a tool or a game and watch it run.

GGUFlive artifacts

Saient — the coding agent

A real agent with a PTY terminal and a tool-use loop (read · ls · write · edit · bash). It plans, writes files, runs commands, and fixes its own errors — on your local model, in a sandboxed workspace.

Ctrl · Shift · K — toggle Saient

Image Gen

SDXL text-to-image with LoRA support, schedulers, live progress, and an optional face-detail pass.

SDXLLoRA

Video Gen

Text-to-video and image-to-video with Wan & CogVideoX — frame control, live progress, and an optional refine & upscale pass.

WanCogVideoXi2v

Vision

Ask questions about any image — describe it, read its text, count objects — with a local Moondream2 analyzer. Paste a screenshot and go.

Moondream2local

Text-to-Speech

Kokoro American and British voices with speed control and local 24 kHz WAV output.

Kokoro

LoRA & Merge

Train SDXL LoRAs with a dataset cleaner. A local checkpoint merge worker exists; the v1.0.10 picker limitation is documented.

trainmerge

One engine

Powered by Quartz, Saient's native inference runtime — local model execution with no ONNX Runtime or cloud inference.

QuartznativeVulkan
Guides and use cases

Practical local AI pages.

Step-by-step pages with real screenshots, exact model boundaries, hardware notes, proof status, downloads and source links.

The agent

It doesn't just answer.
It does the work.

Open the Agent screen, choose a project and local model, then give it a scoped goal. Saient can run a plan→act→verify loop within the permissions you grant.

  • planBreaks the goal down into concrete steps and a JSON plan you can edit.
  • actReads, writes, edits and runs inside a sandboxed workspace.
  • verifyRuns explicit checks, records feedback, and can re-plan after an error.
  • safeWrite mode is off by default; project level, sandbox and confirmation settings control what it may do.
planner · autonomous run
goal › add a /health endpoint + a test
───────────────────────────────
planning… 3 steps
read server.py
edit server.py +12 −0
write test_health.py
bash pytest -q
2 passed — goal achieved
Local-first, by design

Local inference data stays on your machine.

0
Saient licence keys required
0
hosted-inference keys required
local
prompts and model execution
free
no Saient inference metering
[>_<]
/|#|\
/   \

Saient is ready.

Download the free desktop app, add the models you choose, and run supported AI workflows on your own hardware.

v1.0.24 · free and no-key · packages hosted directly on saient.co.uk · release notes · Code signing policy

On code signing — we’re on it. The Windows installer is not yet Authenticode-signed, so Windows will warn about an “Unknown publisher” and SmartScreen may ask you to confirm. That is a certificate we are actively working to put in place, not a corner we cut. The release pipeline is already wired to sign automatically the moment one is available, so this notice disappears on its own. Until then every download is listed with its SHA-256 in the release manifest so you can check what you got.

Platform verification. Both packages contain the same terminal and runtime repairs. Version 1.0.24 passes native Windows runtime, frontend and Rust CI checks; an installed Windows desktop/GPU session has not been verified for this version. Linux desktop testing remains the more extensive of the two. Exact source revisions, checksums and verification limits are recorded in the release manifest.

Windows prerequisites. The bundled inference engines require the Microsoft Visual C++ v14 Redistributable (x64). Install it from Microsoft if it is missing. Python 3.10+ is also required for the Saient terminal. NVIDIA GPU acceleration requires a compatible NVIDIA driver. The CUDA runtime library is bundled; the CUDA toolkit is not required.

Thank you. To everyone who has downloaded Saient, reported something broken, or just followed along — genuinely, it helps, and it is the reason the rough edges get found at all.