Context Zero Engine
Local code-intelligence engine for AI agents — indexes a repository into a code graph and serves context over MCP and HTTP.
Free, self-hosted builds — engines, tools, and utilities. They run locally, on hardware you already have, and stay engineered to the same baseline as our paid software.
Each one runs locally, on hardware you already have — no account, no telemetry.
Local code-intelligence engine for AI agents — indexes a repository into a code graph and serves context over MCP and HTTP.
CPU-only Rust LLM inference engine — 4-bit quantized kernels and local serving, no CUDA or PyTorch.
Experimental self-hosted credential proxy for cooperative AI agents — reduces accidental key exposure, but is not yet a same-user isolation boundary.
Free Android opener for PDF, DOCX, RTF, XLSX, CSV, PPTX slide outlines, Markdown, and plain text.
Free live speech translation for Android.
Full access to Lven Instant for 3 days. Card required, cancel anytime.
Public builds, paid products, and active research all clear the same engineering baseline. Free is not a lower standard — it is the same standard, given away.
Fast, accurate voice-to-text — Windows, Linux, and Android today, with macOS and iPhone coming soon. One subscription covers every platform as it ships. The flagship product these builds share a standard with. See plans.
The strict performance, stability, and privacy bar every build clears before we issue it. Read the standard.
Active research and in-progress builds, documented in the open — where today’s experiments become tomorrow’s public work. Open frontier.