Show HN: Yana – A local-first, human-governed AI runtime and IDE in Rust

Vũ Văn Tâm released Yana, a local-first, human-governed AI runtime and IDE written in Rust, with a live desktop workspace (Yana Studio) and a runtime (yana-rt) that routes Claude, GPT, Gemini, DeepSeek and local models through one authority contract across 19 providers. Yana's governance layer ships capability manifests, human approval, a hash-chained audit log, a SHA-256 core-lock manifest pinning 287 core files, and an independent watcher called Giám Thị that can halt every session; the knowledge layer includes 100 agents and 2,026 skills that grant no permissions. The runtime has 40 subcommands and zero Python dependency, while Yana OS (agent identity, autonomy levels, quotas, quarantine) remains in development and the ESP32-S3 Yana Wheelbot robotics platform is experimental; the macOS build is ad-hoc signed and not notarized, so Gatekeeper warns on first launch.

English https://github.com/yanacuti1121/Yana-AI/blob/main/README.md · Tiếng Việt https://github.com/yanacuti1121/Yana-AI/blob/main/README.vi.md · 한국어 https://github.com/yanacuti1121/Yana-AI/blob/main/README.ko.md · 中文 https://github.com/yanacuti1121/Yana-AI/blob/main/README.zh.md Created by Vũ Văn Tâm · Vietnam Yana is the control plane between an AI and real power. A model can say what it wants to do. Yana decides whether that is allowed, and a person can always stop it. Model proposes an action | Authority is this agent allowed to ask? | Capability what exact power is this? a small, fixed set | Policy may it happen now? rules first, then a human | Executor performs only the permitted operation Any model goes through the same path: Claude, GPT, Gemini, DeepSeek, or one running on your own machine. Skills teach an agent how to work; only a capability can grant permission to act. | Component | What it does | Where | Status | |---|---|---|---| | Yana Studio | Desktop workspace for working with AI on a real project. | tools/yana-studio https://github.com/yanacuti1121/Yana-AI/blob/main/tools/yana-studio | Live | | Runtime yana-rt | Rust engine: one turn loop and one authority contract for local and cloud models, 19 providers. | src/ https://github.com/yanacuti1121/Yana-AI/blob/main/src | Live | | Governance | Capability manifests, human approval, hash-chained audit log, core-lock integrity, and Giám Thị, an independent watcher that can halt every session. | core/ https://github.com/yanacuti1121/Yana-AI/blob/main/core | Live | | Harness adapters | Claude Code, Codex, Cursor and Antigravity, governed through generated hooks, rules and gates. Enforcement strength differs per host. | adapters/ https://github.com/yanacuti1121/Yana-AI/blob/main/adapters | Live, varies by host | | Knowledge layer | 100 agents and 2,026 skills that teach agents how to work. They grant no permissions. | core/agents https://github.com/yanacuti1121/Yana-AI/blob/main/core/agents , core/skills https://github.com/yanacuti1121/Yana-AI/blob/main/core/skills | Live | | Yana OS | Local management plane: agent identity, autonomy levels, quotas, health, quarantine. | src/os https://github.com/yanacuti1121/Yana-AI/blob/main/src/os | In development | | Yana Wheelbot | Robotics platform on ESP32-S3, in its own repository. | yana-wheelbot https://github.com/yanacuti1121/yana-wheelbot | Experimental | Live means shipped and in use. In development means real code exists but is not feature-complete. Experimental means opt-in and not independently verified. yana-rt has 40 subcommands. Zero Python dependency. This is the source-defined count across feature builds, including feature-gated ones. core/ ├── hooks/ 66 PreToolUse / PostToolUse / Stop hooks ├── rules/ 71 enforced rules ├── agents/ 100 specialist agents ├── skills/ 2,026 skills └── config/ └── core-lock.json SHA-256 manifest — 287 core files pinned One window for the things you switch between when working with AI on a project: - Files and editor: open a real folder, search across it, edit with CodeMirror. Saves detect outside changes before overwriting. - Terminals: real PTY sessions in tabs, or a grid of up to 12. - Git: read-only status, worktrees and diffs. - Chat: streamed through yana-rt , with local or cloud models under the same authority path as everything else. - Governance telemetry: what was allowed, what was blocked, and why. Download from the latest release https://github.com/yanacuti1121/Yana-AI/releases/latest or yana.vutam.link https://yana.vutam.link . | Platform | Installer | |---|---| | macOS, Apple Silicon | .dmg or .zip | | Windows | .exe , x64 or ARM64 | | Linux | .deb or .AppImage | Each release lists its own assets, so check that your platform is there, and verify against SHA256SUMS when provided. The macOS build is ad-hoc signed and not notarized no Apple Developer membership yet , so Gatekeeper warns on first launch; docs/MACOS INSTALL.md https://github.com/yanacuti1121/Yana-AI/blob/main/docs/MACOS INSTALL.md shows the two official ways to open it. pip install yana-ai Python CLI yana-ai install add Yana's hooks and rules to your repo yana-ai doctor . check that everything is wired cargo install yana-rt native runtime, no Python needed Needs Python 3.11+ or Rust , Git, and one supported harness. All commands are in COMMANDS.md https://github.com/yanacuti1121/Yana-AI/blob/main/COMMANDS.md . Yana is not published to npm, see VERSIONING.md https://github.com/yanacuti1121/Yana-AI/blob/main/VERSIONING.md . - Audit log: hash-chained, so editing or deleting a line is detectable. It is tamper-detectable, not tamper-proof. - Core-lock: a SHA-256 manifest detects changed, deleted or injected files in core/ . - Human gate: force-push, publish, deploy and delete need confirmation in the current session; earlier approval does not carry over. - Giám Thị: opt-in, runs outside any AI session, and on a finding locks every later tool call until a person removes the lock. - Limits: guard-destructive.sh matches command strings, not a full shell parse, so a deliberately crafted command can slip past it. Browser-only web deployments without the Rust runtime are not fully governed. Details: known limitations https://github.com/yanacuti1121/Yana-AI/blob/main/docs/reference/known-limitations.md . ARCHITECTURE.md https://github.com/yanacuti1121/Yana-AI/blob/main/ARCHITECTURE.md · PHILOSOPHY.md https://github.com/yanacuti1121/Yana-AI/blob/main/PHILOSOPHY.md · ROADMAP.md https://github.com/yanacuti1121/Yana-AI/blob/main/ROADMAP.md · CHANGELOG.md https://github.com/yanacuti1121/Yana-AI/blob/main/CHANGELOG.md · CONTRIBUTING.md https://github.com/yanacuti1121/Yana-AI/blob/main/CONTRIBUTING.md · SECURITY.md https://github.com/yanacuti1121/Yana-AI/blob/main/SECURITY.md · Acknowledgements https://github.com/yanacuti1121/Yana-AI/blob/main/ACKNOWLEDGEMENTS.md · Lineage https://github.com/yanacuti1121/Yana-AI/blob/main/docs/history/LINEAGE.md Built by one person, no team, no funding: Vũ Văn Tâm , Vietnam · yana.vutam.link https://yana.vutam.link/ · phamlongh230@gmail.com mailto:phamlongh230@gmail.com · Apache 2.0 https://github.com/yanacuti1121/Yana-AI/blob/main/LICENSE