ChengYoung — Your private desktop AI agent

A built-in local inference engine works even fully offline; connect your own cloud model services when you want. No sign-up, nothing uploaded — your data stays 100% on your machine.

Runs fully local · No sign-up · Ready out of the box · Windows 10/11 (x64)

✓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 lock-in — your runtime and data stay under your control.

Local inference engineBuilt-in llama.cpp / GGUF with Vulkan GPU acceleration — fully offline.
Cloud optionalConnect the model providers you configure yourself; API keys stay only in the OS keychain — not collected, not uploaded.
Models on demandFetch local models in-app: built-in Hugging Face and ModelScope download sources — faster downloads in mainland China; each model's license is governed by its model page.

Skills & Extensions

Human-verified third-party extensions with install and data-flow disclosures.

Search & Web Info

Tavily Web Search

Web-wide search and structured content extraction in one call.Compatibility tested

Dev & Business

GitHub (Official)

Let the agent work your issues, pull requests and code search directly.Compatibility tested

Search & Web Info

Exa AI Search

Semantic AI search — find pages by meaning, not just keywords.Compatibility tested

Databases & Data

MongoDB Database

Official extension: queries, aggregations and index management in-session, against your own Atlas or local instance.Compatibility tested

Browse all extensions →

Download ChengYoung (Windows)

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

Version 1.34.0 Released 2026-11-14 Windows 10/11 (x64) Installer ≈ 49 MB
Show SHA256 checksum command
certutil -hashfile ChengYoung_1.34.0_x64-setup.exe SHA256
  • Per-user install — no administrator rights required; in-app updates are verified with minisign signatures.
  • If Microsoft Defender SmartScreen warns on first install: that is normal while a new signature builds desktop reputation, and the publisher line shows our registered company name and location (certificate fields). Verify the SHA256 above first, then choose "More info → Run anyway".
  • 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.
  • Other products: ChengYoung Typeset (coming soon) · LicenseDesktop (independent sub-product site).

Pricing

The app is free; local models cost nothing to run, cloud models are billed by their providers.

Free

All features · No usage limits · No telemetry

The app itself is completely free, and no account is required. Two ways to run models: local models infer on your own hardware at zero model cost, or cloud models connect to providers you configure yourself, billed at each provider's standard rates (ChengYoung takes no cut). Workflows, skills & extensions, the scheduler and the secure embedded browser are all included.

The only requirement for local models is your own hardware: memory and GPU decide which model sizes run comfortably (see the specs in the download section). If paid tiers or a cloud service ever launch, this page will say so in advance — the app itself is free. There is also an independent sub-product, LicenseDesktop (offline license management for software vendors) — see its pricing →

ChengYoung Typeset is still in development; its pricing and licensing will be announced before release.