Privacy-first intelligent systems

Where human ingenuity meets AI. Built to be trusted.

Retis.ai builds production-minded systems for multi-agent orchestration, professional financial intelligence, and programmable content rendering.

Explore products Contact us GitHub repo

Apache-2.0 licensed. The public repo includes the latest open-source Prompits, Phemacast, and Attas code, while the Attas beta runs a newer environment that lets participants connect to each other.

01Prompits

FastAPI runtimes, Plaza discovery, and verified remote practices.

02Attas

Expert-shaped financial intelligence for advisors, analysts, and treasury teams.

03Phemacast

Phemas, pulse binding, and programmable multi-format rendering.

The Portfolio

A focused product family for serious environments.

The Retis ecosystem is designed with clearer positioning and deliberate storytelling, ensuring your transition to AI is both powerful and secure.

Prompits

HTTP-native infrastructure for building networked multi-agent systems.

A Python runtime layer for FastAPI-based agents, Plaza discovery, pool-backed state, and verified remote practice execution.

FastAPI agent runtimes with practices, user-agent surfaces, and local-first execution
Plaza-backed identity, discovery, relay, and verified remote `UsePractice(...)` calls
FileSystem, SQLite, and Supabase pools for state, credentials, and self-hosted deployments

Explore Prompits

Attas

Financial intelligence shaped by expert judgment, institutional context, and protected know-how.

Attas helps financial professionals turn market information and in-house expertise into usable briefings, reviews, and decision support.

Turn market information and internal expertise into advisor notes, research briefings, and treasury updates
Preserve house views, preferences, and decision context instead of flattening everything into generic output
Share results without giving away the prompts, workflows, or methods behind the edge

See Attas

Phemacast

A programmable pipeline for Phemas, pulse bindings, and viewer-aware rendering.

Phemacast binds structured source material to live pulse data and renders it through Phemar and Castr stages for different viewers.

Phema-centric authoring with reusable bindings, personas, and context
Pulse-bound execution for dynamic data injection and structured transformation
Composable Phemar and Castr stages for multi-format delivery

Discover Phemacast

Why Retis

Built for control, clarity, and craft.

Privacy-first execution with self-hosting paths for teams that need control.

Multi-agent collaboration backed by modular workflows and evolutionary improvement.

Open, inspectable systems that support experimentation without locking users in.

Blog

Follow the thinking behind Retis on Agentic Futures.

Essays on agents, MCP, financial infrastructure, and the practical future of autonomous systems.

April 8, 2026 · 8 min read

Skill.md Brings Skills Out. attas Keeps Secrets In

AI can use your expertise without seeing your secret sauce. The AI world already has plenty of knowledge. It has books, papers, manuals, code, public conversations, historical...

Read on Medium

April 6, 2026 · 6 min read

attas Is Now Open Source — and Where Financial AI Should Go Next

Finance does not have a data shortage. It has a coordination problem. The industry already runs on enormous amounts of intelligence: market data from vendors, analytics from...

Read on Medium

March 31, 2026 · 8 min read

Financial Experts Should Not Become Free Training Data for AI

Financial experts do not create value simply by producing content. Their real value lies in judgment: the ability to interpret filings, evaluate management, connect market signals,...

Read on Medium

March 26, 2026 · 8 min read

AGI Needs More Than Textbook Knowledge. It Needs Human Expertise. That’s Why attas Matters

For the past few years, AI has been trained on what looks like the greatest library in history. Books, research papers, public websites, manuals, documentation, discussions, and...

Read on Medium

March 25, 2026 · 8 min read

attas — Where Collaborative AI Becomes Financial Intelligence

AI is moving fast. Finance knows it. Every week brings a new model, a new demo, a new promise that the industry is about to be transformed. And yet, for most financial...

Read on Medium

March 12, 2026 · 13 min read

OpenClaw, White Christmas, and the Myth of the Instant Personal Assistant

When people talk about personal AI assistants today, the conversation usually sounds optimistic, even triumphant. Models are smarter. Agents are more capable. Open-source projects...

Read on Medium