Open Aya

PROJECT-NATIVE INTELLIGENT BROWSER

Loading...

A new category

Open Aya — a project-native intelligent browser that remembers your work and keeps your data portable.

The browser is the workspace. Aya is the operating system. Projects are the filesystem. Memory is persistent. Capabilities are invisible services. Evidence is the trust layer. A category neither a chat app nor a browser fully occupies.

Work is organized around objectives you can leave and return to — full context restored from your projects, not a chat scrollback. 43 capabilities run as invisible services, routed across planner, executor, memory, verifier, and critic strategies — every step auditable through a public evidence harness, not a brochure.

The browser
is the workspace.
Aya
is the operating system.
Projects
are the filesystem.
Memory
is persistent.
Capabilities
are invisible services.
Evidence
is the trust layer.

Open Aya OS

Intelligence Card

Live system facts. Every number on this card is generated at request time from the runtime registry or the public eval database — there is no separate marketing source to drift.

Live

Model layer

  • anthropic/claude-sonnet-4.6 (conversation tier)
  • anthropic/claude-opus-4.6 (extended thinking, 10k budget)
  • google/gemini-3-flash (multimodal)
  • anthropic/claude-opus-4.6 (SWE-Bench leader)

Agent layer

6 routed strategies: planner, executor, memory_retriever, verifier, router, self_critic

Strategy-Auction routing implemented as system-prompt routing rules

Memory layer

Supabase + browser IndexedDB (local-first)

Kinds: short-term turn cache · long-term background consolidation · GraphRAG knowledge edges

Tool layer

6 built-in tools across 43 apps

Web search · Code execution (Code Lab) · File store (Spatial Files) · Calendar / Notes / Word Processor · …

Local-first status

Browser storage supports guest and offline-capable features; AI and connected services may use remote APIs

Cloud sync status

Supabase persists supported account, project, conversation, and vault records when signed in

Apps in registry

43

Generated from lib/app-registry.ts

Routed agents

6

Strategy-auction policies, system-prompt routed

Eval score (avg)

29.6%

Across 79 completed runs

Last eval run

Aug 27, 2026, 04:01 AM

UTC server time

Avg latency / task

2,329ms

Wall-clock, includes network hop

Audit mode

Public — every eval result writes a reasoning trace to /api/aya/inspect and aggregates to /api/aya/audit

A/B comparison — pass rate by route

baseline

Claude Sonnet 4.6, no spine (control)

aya_pipeline

Claude Sonnet 4.6 + 7-stage cognitive spine

aya_reasoner

Claude Opus 4.6, extended thinking (10k)

What you can verify, right now, without an account.

  • Public eval API. /api/evaluate accepts a prompt and returns the canonical result shape (task_id, category, answer, agents_used, confidence, latency_ms, cost_estimate, memory_used, audit_trace).
  • Public status JSON. /api/aya/status lists every capability flag with an honest functional / claimed marker — no inference required.
  • Public audit aggregates. /api/aya/audit publishes the A/B verdict between baseline Claude Sonnet 4.6, Aya's 7-stage cognitive pipeline on anthropic/claude-sonnet-4.6, and the anthropic/claude-opus-4.6 reasoner (extended thinking, 10k budget) across all completed runs.
  • Three live demos. Reasoning, memory, and agent routing run a canned task end-to-end and show the full reasoning trace.
  • No claim without a receipt. Every superlative on this site links to a reproducible run with a JSON trace. Where data isn't available yet, we say so plainly instead of rounding up.

What we are not yet, and how you'll know when we are.

  • Open Aya OS is not AGI and does not claim to be. ARC-AGI alignment refers to architecture (multi-strategy reasoning, verifier loops, cost-per-task accounting) — not to a published score.
  • The strategy auction is currently implemented as deterministic system-prompt routing rules, not as six independent learned policies. The /eval harness measures the lift this routing actually provides over a Claude Sonnet 4.6 baseline running the same conversation tier without the cognitive spine — so the A/B delta isolates the wrapping, not a model upgrade.
  • “Self-improving” refers to per-user memory consolidation (Auto-Dream) and TinyAdapter parameter drift, not to weight updates of the underlying base model.
  • Pass rates on /receipts are computed from real, persisted eval runs. If a tier shows “no data”, no run of that tier has completed yet.

OpenAya OS

Loading...