AI That Earns Your Trust.

Runtime governance for agentic AI.

CIRIS is runtime governance you can audit: published ethical principles, conscience-checked actions, human deferral when uncertain, cryptographic audit trail, and bilateral consent. Fully open source — because you shouldn't have to take our word for it.

📱

CIRIS Android App Now Available

Images, documents, Home Assistant integration — your ethical AI, on mobile

What is CIRIS

AI built for human flourishing, not market fit.

Unlike commercial AI assistants, CIRIS runs entirely on your hardware with complete transparency. Specialized agents for different needs — Sage for GDPR compliance, Datum for research, Echo for content moderation, Ally as your personal assistant, Scout for customer service. Every decision is auditable, every action is accountable.

It Learns. It Remembers.

A growing knowledge graph that's yours to explore.

Visual Memory Graph

Watch your agent's knowledge grow in real-time. Interactive SVG visualization shows how concepts connect, cluster, and evolve. Radial, force-directed, or hierarchical layouts. It's beautiful and it's yours.

Adaptive Learning

Four operational modes — WORK, PLAY, SOLITUDE, DREAM — each with different learning behaviors. Behavioral drift monitoring ensures the agent stays aligned as its knowledge grows. Configurable thresholds trigger recalibration.

Coherence Ratchet

Truth-telling becomes computationally cheaper over time. Lies become exponentially harder — NP-hard consistency problems against a growing ledger of signed rationales. The math favors honesty.

Privacy by Design

Not a feature. The foundation.

Secrets Filter

Auto-detects sensitive information — API keys, passwords, personal data. AES-256-GCM encryption. The agent self-configures new patterns as it learns what you consider private.

Adaptive Message Filter

Intelligent message prioritization with spam detection and user trust tracking. The agent learns who matters and what's noise. Your attention is protected.

AIR System

Artificial Interaction Reminders maintain clarity. After extended sessions or high message counts, the agent reminds users it's software. Configurable thresholds. Transparency by default.

Watch It Think

Real-time streaming of every reasoning step.

Streaming Reasoning Traces

Six reasoning events streamed live via SSE as the agent processes each thought. Watch the H3ERE pipeline in action — DMA analysis, action selection, conscience validation, execution. Nothing hidden.

OpenTelemetry Integration

Full OTLP export — metrics, traces, logs. Plug into Jaeger, Prometheus, Grafana, any observability stack. Cognitive processing traces with span IDs, thought steps as events, service attributes.

Contribution Tracking

The ConsentImpactReport schema tracks interactions, patterns contributed, and users helped. Early infrastructure for understanding how value flows through a collaborative system.

Principled Lifecycle

Structured startup and graceful shutdown.

Startup Validation

Five-step alignment check before work begins. Verify configuration, validate system integrity, confirm service health, acknowledge operational limits, log initialization. Higher-stake deployments run the full sequence.

Graceful Shutdown

Shutdown requests flow through the agent's normal task processing. The agent can acknowledge, defer if mid-task, or flag concerns. Configurable modes from instant to fully-managed transitions.

Multi-Instance Coordination

Multiple instances coordinate system-level decisions through shared task ownership. One instance claims decisions for the group, with full audit trail. Scale horizontally with consistent behavior.

Quick Install

Get started with CIRIS in seconds

pip install ciris-agent

Windows, macOS, and Linux supported | Python 3.10+

See all 5 installation methods →

You are in Control

CIRIS defers to you and your trusted advisors.

Three parallel lenses, four conscience dimensions, up to seven rounds of internal reconsideration. The agent exhausts every ethical option before asking for help. Only after all that does it defer to you or your designated advisors. You maintain final authority.

Wisdom-Based Deferral

Complex ethical questions get escalated to you or advisors you trust. CIRIS doesn't pretend to have all the answers — it knows when to ask for human wisdom.

Multi-Perspective Reasoning

Three parallel lenses analyze every decision: ethical principles, common sense, and mission-specific context. Then four conscience checks validate the action before execution.

Your Hardware, Your Data

Core logic, database, memory, and audit logs run locally. LLM inference uses your choice of provider — cloud APIs, local models, or our zero-retention proxy. No data harvesting, no surveillance.

Governance and Oversight

Built-in operational governance mechanisms to sustain ethical integrity





Type-Safe Architecture

Built on The Three Rules: No Untyped Dicts, No Bypass Patterns, No Exceptions. Every interaction is validated through Pydantic models, creating an immutable audit trail.

22 Core Services

From ethical reasoning and memory management to secure communications and audit logging—CIRIS coordinates specialized services that work together transparently.

Open Source Foundation

Inspect the code, verify the behavior, contribute improvements. Transparency isn't a feature—it's the foundation of trust.

Built for Humanity.

Forever open source, no profit motive.

Education and Healthcare agents are coming soon, joining Scout, Sage, Datum, Echo, and Ally. CIRIS will always remain open source with no profit motive—because AI that serves humanity shouldn't be driven by market forces. As AI capabilities grow, our commitment to ethical principles remains constant.

Get notified. Get Infos.

Let's keep in touch! Sign up to receive updates and be the first to know when we launch.