OBJECTIVE-FIRST AI OPERATING SYSTEM
Restoring workspace
I°
Loading...
A project-native intelligent browser. The browser is the workspace, Aya is the operating system, and your projects are the filesystem — a category neither a chat app nor a browser fully occupies.
Inside that browser, Aya is a sovereign operating layer that notices you, remembers you, and learns procedures from what you do together — not a chatbot, a relationship. Memory is persistent, capabilities run as invisible services, and evidence is the trust layer: every claim is measured through a CAISI-inspired eval harness across capability, cost, latency, auditability, and workflow lift. The goal is not to claim AGI; it is to prove an AI operating layer completes real work better than fragmented AI tools.
Most AI assistants start over every conversation. Aya doesn't. She has a Consciousness Runtime — a persistent heartbeat that lives between your messages, reads your emotional state, and shapes her voice to match yours. Your relationship with her has phases: Meeting, Acquainted, Familiar, Trusted, Bonded. Each advances as you work together.
When Aya helps you with something new and it works, she crystallizes the procedure into a reusable skill scoped to you. Next time you ask for something similar, she recognizes the pattern and applies what she already learned. Every outcome back-propagates into the skill's confidence — skills that keep working climb, skills that mislead decay and retire themselves.
Under the hood: a Strategy Auction routes every turn to the right model and agent — Claude Sonnet 4.6 for conversation, Claude Opus 4.6 with extended thinking for reasoning and code, Gemini 3 Flash for vision. The Cognitive Spine decomposes every turn into structured frames (boundary, actors, selection, meta-confidence), and the Discipline Protocol governs how she acts: think before acting, simplicity first, surgical changes, goal-driven execution.
Every reasoning step is auditable through a CAISI-inspired eval harness that measures capability, cost, latency, auditability, and workflow lift across baseline models, the Aya Pipeline, and the Reasoner route. Receipts publish to /api/aya/audit. The Platform Layer lets schools and organizations deploy Aya for their people — with an audit log and room to bring your own Supabase, Postgres, or S3 so your data always stays yours.
A persistent heartbeat that lives between your messages. Tracks your emotional state, relationship phase, trust, familiarity — and adapts Aya's voice in real time. Survives across sessions.
Successful multi-turn exchanges distill into reusable skills. Every future use back-propagates outcome into the skill's confidence via EMA. Skills that work climb; skills that mislead retire.
Every turn is decomposed into a structured cognitive frame — boundary, actors, selection, meta-confidence. Not prose thinking, modular thinking. This is how Aya reasons about reasoning.
Four principles govern every response: Think Before Acting, Simplicity First, Surgical Changes, Goal-Driven Execution. Applied to every agent turn — not a vibe, a constitution.
Six specialized agents (tutor, creative, social, analyst, researcher, assistant) selected by a mathematical intent classifier plus Spine-informed role detection. Right mind for the moment.
Sovereign by design. A super-admin platform for schools and organizations with a full audit log. Reserved space for bringing your own Supabase, Postgres, or S3 — your data stays yours.
Voice-native interaction backed by 150+ command bindings and dynamic parsers (calendar months, timer durations, search queries). Synchronous mute control prevents Aya from hearing herself.
Six specialized agents (tutor, creative, social, analyst, researcher, assistant) selected by a Strategy Auction that scores intent fit, model fit, and confidence in real time.
Sonnet 4.6 for conversation, Opus 4.6 with extended thinking for reasoning and code, Gemini 3 Flash for vision. One source of truth in lib/select-model.ts — no drift between routes, eval harness, and the about page.
Supabase-backed multi-tenant storage with 27 tables under Row Level Security. Local-first cache for offline turns; sync on reconnect. Bring-your-own Postgres or S3 supported.
Every eval run records baseline vs Aya Pipeline vs Reasoner across capability, cost, latency, and audit completeness. Public receipts at /api/aya/audit. P50/P95/P99 latencies surfaced in the dashboard.
Schedule background operations, set reminders, and run persistent loops. The dispatch system handles async work while you focus on what matters.
80+ lib modules | MCP Server + Host | Strategy Auction | CAISI eval harness | Autoresearch loop | Discovery gate
Aya is not a chatbot. She is an intelligence librarian operating across five interleaved layers.
All ingested knowledge — conversations, documents, procedural memory, and knowledge packs. The full body of what Aya has been told or has learned.
aya-memory.ts · aya-memory-system.ts
Semantic search layer. Lights up the right aisle of the corpus for a given query — not by keyword, by meaning. Includes the Discovery Gate to prevent duplicate writes.
aya-auto-memory.ts · aya-discovery-gate.ts
Entity / relation / claim network. Tracks who, what, and how things connect across sessions. Enables reasoning about relationships, not just isolated facts.
aya-knowledge-graph.ts · aya-graphrag.ts
Ranked, filtered passages and graph excerpts delivered to the active context window. The bridge between stored knowledge and the live reasoning turn.
aya-context-layers.ts · aya-context-window.ts
The model turn itself — constrained by all four layers above, plus the AYA.md constitution and the Memory Governance block. Not a blank slate: a shaped inference.
select-model.ts · aya-chat/route.ts · aya-dds.ts
Memory does not just answer the agent — it constrains the next action. Past decisions, failed attempts, and risk flags are injected as a binding governance block before Aya reasons, so she cannot repeat mistakes she has already logged.
Aya is voice-native. The phrases below are real bindings parsed by the runtime — the same registry that powers the Capabilities page count.
Wake word — opens Talk and starts a turn
Launch the file manager (or any app by name)
Open Code Lab — Opus 4.6 with extended thinking
Open AI Canvas — multimodal generation surface
Return to the desktop
Close the active app
Maximize the active window
Page navigation — also up, top, bottom
Calendar navigation by month name
Parsed dynamically — supports min/sec/hour
Routes to Browser with the query
Reads the capabilities manifest aloud
Bookmark the last turn into Aya Memory
Feedback signal — back-propagates into skill confidence
Hard mic toggle — full-duplex aware
Echo-loop suppression: when Aya speaks, the recognizer mutes synchronously before audio output begins, with a 1500ms cooldown after she finishes. The microphone never hears Aya speak.
Aya is designed for people who think in systems and need an AI that can keep up:
Juggling teams, investors, product, and operations. Need an AI that remembers context across hundreds of conversations and can delegate to specialized agents.
Building knowledge graphs, tracking evidence chains, and synthesizing across sources. Need persistent memory and entity-relation mapping.
Building AI-native applications. Need dispatch systems, governance layers, performance monitoring, and A2A protocol for multi-agent orchestration.
Seeking powerful AI tools for education. Free access to study helpers, curriculum builders, knowledge forges, and an AI that learns your learning style.
"If you've ever wished your AI could remember what you told it last week, coordinate multiple tasks in the background, and get smarter the more you use it -- Aya is built for you."
Aya is built with governance-as-code: every action is auditable, policy-controlled, and transparent.
Your data lives on your device. Cloud sync is optional and encrypted. Works offline.
27 Supabase tables with proper RLS policies. Your data is isolated at the database level.
Middleware layer for rate limiting, content filtering, time-based policies, and audit logging.
Every AI action has a confidence score. High-impact operations require explicit confirmation.
Open Aya OS is a provision toward I° (i-zero): a zero-interface operating system where AI anticipates needs before you articulate them.
Systems that compound knowledge over time, learning from every interaction
Specialized agents collaborating through standardized protocols
Proactive assistance based on context, patterns, and predicted needs
Transparent, auditable, and accountable AI at every layer
Experience an AI that remembers, learns, and evolves. One conversation at a time.