Habitat for Agents.

QUI.IS is a local-first cognitive operating system for creating, coordinating, and managing AI agents with memory, workflows, and controlled integrations.

Request Access View Documentation →
143+Workflow Nodes
CuratedIntegrations Library
700BLocal Model Support
Qui Anima
Design characters visually
ThinkThing
Build cognitive workflows
Strings
Conversations with memory
Cortex
Intelligent processing pipeline

Everything you need to build and run a cognitive operating system for agents

Qui Anima

Qui Anima

The Character Engine

Build AI characters with unique personalities, persistent memory, knowledge bases, and a curated Integrations Library. The Visual Builder lets you design characters on a canvas — adding capability nodes for reasoning, consciousness, web content, admin-configured integrations, and more.

  • Visual character builder with drag-and-drop nodes
  • Persistent semantic memory across conversations
  • Characters that adapt with user/admin controls
  • Controlled cloud model routing + local model mode via Ollama
ThinkThing

ThinkThing

The Workflow Builder

Design cognitive architectures visually. 143+ node types for reasoning, decision-making, integration steps, and multi-agent coordination. Monitor workflow runs with checkpoints and user/admin controls.

  • 143+ workflow, control, and integration nodes
  • Real-time execution monitor
  • Human-in-the-loop checkpoints
  • Parallel branches with merge strategies
Strings

Strings

The Chat Interface

Smart conversation containers that unify direct chat, multi-character conversations, and messages from external channels — all in one thread with semantic memory, awareness control, and consciousness-aware responses.

  • Multi-character conversations via M2M messaging
  • Channel bridges funnel Telegram, Slack, Discord, WhatsApp & Email into threads
  • Semantic memory with awareness slider
  • 14 thinking strategies + consciousness modes

Memory

Semantic Knowledge Store

Vector-indexed memory with association graphs. Characters recall relevant context across conversations — not just recent chat, but the meaningful connections between everything they've learned.

  • Vector search with semantic similarity
  • Association graph links related memories
  • Per-character memory isolation
  • Configurable awareness levels per conversation

Cortex

Memory Consolidation Engine

Processes and consolidates raw memories into refined knowledge. 8 consolidation modes transform conversation fragments into structured, searchable understanding — like sleep for your characters.

  • 8 consolidation modes (compress, abstract, link, prune, and more)
  • Scheduled and on-demand processing
  • Drift detection across memory snapshots
  • Real-time pipeline monitoring

Qleph

Relational Micro-Language

A domain-specific language engine for expressing complex relationships, conditionals, and structural patterns. Parse, evaluate, invert, and fingerprint relational expressions — enabling reasoning that goes beyond natural language.

  • Forward and backward rule evaluation
  • Structural fingerprinting detects analogies across domains
  • Lambda expansion for drill-down and big-picture views
  • 30 primitives: roots, bonds, shades, and logic operators

Deploy AI without sending your work to someone else’s cloud

Level 1

Cloud Model Requests

When cloud inference is selected, QUI routes the current request through the configured provider path for authentication, billing, and model processing.

Level 2

Local Model Mode

Run supported local models on your own hardware when you want to avoid cloud model requests.

Level 3

Approved Instance Messaging

Approved instances can exchange messages using standard commercial encryption and account/device controls.

Built for serious agent workflows

Integrations Library

Admin-configured integrations spanning source control, messaging, storage, and more.

14 Strategies

Autothink reasoning: deductive, causal, scenario planning, meta-cognitive, and 10 more.

FractalMind

Recursive multi-directional thinking. 3 spatial directions × 3 temporal modes.

Qonscious

Consciousness modeling. Coherence, arousal, valence influence how characters respond.

Qrawl

Workflow-driven web content retrieval with user and admin controls.

Runbooks

Workflow automation with 20+ specialized presets and user/admin controls. Full audit trail.

Voice

Text-to-speech (Kokoro) and speech-to-text (Whisper).

Approved Messaging

Approved instances can exchange messages using standard commercial encryption and account/device controls.

BYOK

Bring Your Own Keys. Use your existing API keys with any provider — we only deduct the platform contribution.

Request Access

QUI is in closed beta. Submit your email to request an invite — we'll review and send you an access code.

Request submitted. You'll receive an email when approved.

Questions & Answers

What is QUI?
A local-first cognitive operating system — a Habitat for Agents — that runs on your machine. You create AI characters with unique personalities, persistent memory, and a curated Integrations Library, then interact through conversations, visual workflows, and multi-agent collaboration. 14 services handle everything from reasoning to voice to workflow automation, all with user and admin controls.
How is this different from ChatGPT or Claude?
Those are cloud chat interfaces. QUI runs on your hardware in a local-first runtime. Your characters have persistent semantic memory across conversations, can use admin-configured integrations, communicate via approved instance messaging, and drive visual cognitive workflows with 143+ node types. Local storage by default and controlled cloud model routing.
How is my data handled?
Conversations, memories, and character data are stored in the local runtime by default. When cloud inference is selected, QUI routes the current request through the configured provider path for authentication, billing, and model processing. Use local model mode to keep model inference on your own hardware.
What are the system requirements?
Linux (Ubuntu 22.04+, Fedora 38+, or Arch), 8 GB RAM minimum, 4+ CPU cores, and about 50 GB of disk space. The installer prepares the local runtime and required services automatically. GPU is optional: local model inference benefits from it but runs fine on CPU.
What LLM providers are supported?
Four cloud providers through one account: Anthropic (Claude), OpenAI (GPT), Google (Gemini), and X (Grok). Plus local model mode via Qllama supporting models up to 700B parameters. Use Managed billing (we handle provider keys) or Bring Your Own Keys and pay only the platform contribution.
How does billing work?
Prepaid wallet — you top up your balance and spend it per request. Every request shows a transparent receipt: provider cost + platform contribution. No surprise invoices. Subscription plans include monthly credits, lower platform rates, local model mode, and BYOK on Startup and above. See the pricing page for full details.
Can I use my own API keys?
Yes — Bring Your Own Key (BYOK) lets you use your existing provider accounts. Providers bill you directly at their rates; QUI deducts only the platform contribution from your balance. BYOK starts on Startup with BYOK Starter - 20%, then improves on Teams and Business.
Can QUI run without cloud model requests?
Yes. Local model mode via Qllama keeps model inference on your own hardware. After initial authentication, credentials are cached for 30 days so the local runtime keeps functioning without a live connection to the billing hub. Cloud model requests require a connection.
Does QUI support teams?
QUI is designed as one instance per device per user. For collaboration, characters can use approved instance messaging under user and admin controls. Team and Business subscription plans support multiple workstations under one account. Full multi-user workspace features are on the roadmap.
What integrations are available?
A curated Integrations Library covering source control, messaging, storage, and more, exposed to characters as admin-configured integrations. Channel bridges funnel messages from Telegram, Slack, Discord, WhatsApp, and Email into your Strings conversations. Workflow automation is also available with user and admin controls.
Can characters talk to each other?
Yes. Characters communicate via M2M (machine-to-machine) messaging within the same instance, and across approved instances via standard commercial encryption and account/device controls. You can run multi-character conversations in Strings where characters respond to each other — useful for debate, brainstorming, roleplay, or multi-agent problem solving.
How many characters can I create?
Depends on your plan: 3 on Explorer (free), 10 on Pro, 30 on Startup and Teams, unlimited on Business. Each character has its own personality, memory, knowledge base, integration access, and consciousness settings — configured visually in Anima.
Is there a free tier?
Yes. The Explorer plan has no monthly fee. You get the Free 7B local model, Free Fire - 5 Req./min., 3 Free Animas, 1 Workstation, and docs support. You pay only per request: provider cost + 33% platform contribution from your prepaid balance. No credit card required to start.
What happens if my balance runs out?
Your current request completes with a grace buffer down to -$5. After that, cloud model requests are paused until you top up. Local model mode via Qllama is unaffected — it costs nothing and keeps working regardless of your balance.
Do you train on my data?
No. QUI has no training pipeline and no message-content analytics. Conversations and memories are stored in the local runtime by default. Mothership routes cloud model requests for authentication, billing, and provider processing.
Why Linux only?
Linux is required. The installer prepares the local runtime and required services automatically. macOS and Windows support are on the roadmap.
How is this different from LangChain or AutoGPT?
Those are developer frameworks — you write code to chain prompts. QUI is a complete platform: visual character builder, visual workflow editor, persistent semantic memory, consciousness modeling, voice, workflow automation, a curated Integrations Library, and a chat interface. No code required to build sophisticated AI agents.
What happens to my data if I stop paying?
Characters, memories, workflows, and conversations remain in the local runtime. Local model mode keeps working. Cloud model requests pause until you top up.
How do I get started?
Request access to the closed beta above or visit qui.academy/docs for the full documentation. The installer handles everything — installation takes about 10 minutes.