Local-first · Ready out of the box · Data never leaves your machine

ChengYoung — A local-first desktop AI agent

Ready out of the box: a built-in local inference engine runs fully offline; connect your own cloud providers when you want. No account required, no usage data collected.

Download for Windows See capabilities

Current version 1.13.0 · Windows 10/11 (x64) · Installer ≈ 62 MB · In-app auto-update

✓No telemetryNothing is collected or uploaded; the installer ships without telemetry code.

✓Data stays localConversations, sessions and model files live on your own devices.

✓Verifiable updatesIn-app updates are verified with minisign signatures — a mismatched signature is rejected.

Local models + your own cloud

No vendor-logo wall — the engine and the integrations stay under your control.

Local inference engineBuilt-in llama.cpp / GGUF with Vulkan GPU acceleration (NVIDIA / AMD / Intel, integrated + discrete) — fully offline.

Cloud optionalConnect the model providers you configure yourself; API keys are stored only in the OS keychain.

Models on demandFetched in-app from Hugging Face; each model's license is governed by its model page.

Memory guide8 GB RAM to start; 16 GB RAM / 8 GB VRAM is comfortable for 7B models.

Capabilities

Every item maps to a real panel in the product.

Local inference

Fully offline AI

Built-in llama.cpp / GGUF engine with Vulkan GPU acceleration — full functionality without a network.

Workflows

One-click task chains

Capture repeatable tasks as Recipes and replay them with one click, any time.

Skills & extensions

Extend on demand

Built-in skills work out of the box; bring more tools via MCP (Model Context Protocol).

Scheduler

Run on a schedule

Let tasks run automatically on a plan; results land back in your sessions.

Secure built-in browser

Isolated web panel

Third-party pages open in an isolated panel inside the main window: separate profile, zero injection. Agent browser control is off by default, per-site authorized with per-action confirmation.

Multilingual

16 UI languages

Chinese, English and 14 more — follow your system or set them manually.

Typical scenarios

From a developer's terminal to everyday work — one local agent for all of it.

Development

Code Q&A and changes

Let it understand your project: locate issues, explain code, propose reviewable edits.

Writing

Docs and reports

Gather material, draft and polish into documents that are ready to use.

Offline

Everyday tasks without a network

Summarize, rewrite and translate in airplane mode — local models need no cloud.

Automation

Batch file and data processing

Natural-language-driven renaming, extraction and clean-up — on a schedule.

Download ChengYoung (Windows)

Install directly and update in-app; the local inference engine is bundled, models download on demand.

Version 1.13.0 Released 2026-10-05 Windows 10/11 (x64) Installer ≈ 62 MB

Download ChengYoung_1.13.0_x64-setup.exe Releases page SHA256SUMS.txt

certutil -hashfile ChengYoung_1.13.0_x64-setup.exe SHA256

Per-user install — no administrator rights required; in-app updates are verified with minisign signatures.
After the first launch, search and download a local model in Settings → Models (each model's license is governed by its model page).
Memory guide: 8 GB to start; 16 GB RAM / 8 GB VRAM is comfortable for 7B models. GPU acceleration needs a Vulkan driver.
macOS / Linux: not available yet.

Pricing

Currently free — all features, no usage limits.

Free

All features · No usage limits · No telemetry

ChengYoung is currently free to use: local inference, workflows, skills & extensions, scheduler and the secure built-in browser are all included.

Paid tiers and cloud service: not available yet. There is also an independent sub-product, LicenseDesktop (offline license management for software vendors) — see its pricing →