Cinqic flagship software

Your AI.
Your models.
Your machine.

Juniper is a local-first AI app for people who want a thoughtful assistant, visible model controls, and a clear boundary around private data.

Published evaluation prerelease 0.3.0-rc.7

01 — Model control

Choose a model without becoming a systems administrator.

Juniper’s Models Market detects the device profile, explains which compact models fit, and manages verified downloads and storage.

01

Device-aware recommendations

Review a curated catalog of four instruction-tuned GGUF models below 1B parameters with source revision, license, size, and SHA-256 details.

02

Verified model lifecycle

Downloads are resumable and integrity-checked, with atomic installation, pause/resume, and removal.

03

Model-agnostic by design

No model family is required and no model is bundled in the installer. Compatible providers and runtimes remain visible choices.

04

Juniper-owned desktop runtime

The desktop bundle owns its loopback llama.cpp process, so ordinary local use does not require Ollama or an account.

02 — Assistant workspace

A useful assistant with the controls exposed.

The chat workspace supports streaming, Markdown, export, private chats, and mobile layouts. Assistant profiles keep personality, model choice, tool policy, memory policy, import, and export in one place.

Optional provider connections include Ollama, OpenAI-compatible servers, and llama.cpp-compatible servers for advanced users and existing setups.

Context

Deterministic composition

System prompt, assistant settings, memories, enabled tools, and recent conversation stay within a context budget.

Tools

Explicit permissions

Host-authored calculator, conversion, datetime, attachment, memory, search, and system-info contracts.

Storage

Local persistence

SQLite application state, scoped text attachments, diagnostics, and private-chat boundaries.

03 — Data boundaries

The app should tell you where your prompt goes.

Juniper labels routes as ON DEVICE, LOCAL NETWORK, REMOTE, or UNKNOWN, and never treats UNKNOWN as safe. Desktop provider credentials use the operating-system keychain; secrets are not written to SQLite or exports.

Telemetry, analytics, crash reporting, and accounts are not part of this release. A tool the request did not enable is denied rather than executed.

04 — Published release

0.3.0-rc.7 is available for evaluation.

This is the latest public Juniper release verified on GitHub. The current source repository is ahead at 0.3.0-rc.17, which is not advertised here as a downloadable release.

Download a platform build

Use the release assets below and verify them against the accompanying SHA-256 manifest.

05 — Known limitations

The boundaries are part of the release.

Android can inspect the model catalog and manage app state, but this prerelease does not claim a packaged native local-inference process on Android. Secure credential storage is unavailable on Android. MCP client calls, iOS, and macOS are not included; the Windows MSI may also trigger an unsigned-app warning.