Yana is a local-first, cross-platform control plane that sits between any AI model and real power over your machine. It runs, connects, orchestrates and governs agents across cloud and local model providers, with deterministic control over what an agent can access, change and execute, plus pre, post and stop hooks around every tool call.
Be the first to rate Yana. Your feedback helps other users decide.
Hand an agent real capabilities with explicit, deterministic limits on each one.
Route the same governance layer across cloud models and local ones.
Inspect and approve tool calls before they run, and react afterwards.
Similar tools in the same category — compare side-by-side
PageIndex is a document index for vectorless, reasoning-based retrieval. Instead of chunking text in...
OpenFlow is a visual builder for multi-agent AI workflows. You drag role cards onto a canvas, wire a...
DocuMemory is a memory engine that passively distils raw AI chat sessions into permanent architectur...
Guides and comparisons about code tools
Eight Show HN projects for trusting long agent runs: work context capture, distilled memory, folder fences, dollar budgets, plan review and tool governance.
Ten Hacker News launches that treat agent context, persistent memory and token accounting as first-class problems instead of afterthoughts.
Eleven recent open-source and self-hosted projects for building, sandboxing and deploying coding agents you own outright rather than rent.
Eleven recent projects that turn the Model Context Protocol from a neat demo into deployable infrastructure: registries, compiled servers, and gateways.
Eleven recent open-source projects for running inference, transcription, deep research and security work entirely on hardware you control.