Every AI agent platform ships a GUI. Chat windows, node editors, drag-and-drop flows, settings panels. And only a GUI. Here's why we built a native Rust CLI that shares everything with the desktop app
That means:
No headless operation. You can't run agents on a server without a display.
No scripting. Automating agent management requires either a REST API you have to host or brittle UI automation.
No CI integration. Checking agent status, cleaning up sessions, or validating configuration in a pipeline? Open a browser.
No composability. You can't pipe agent output into jq, grep, or another tool. The data is trapped behind a window.
AI power users — the people building real workflows, deploying to production, managing dozens of agents — live in the terminal. Forcing them into a GUI for every interaction is a productivity tax they shouldn't have to pay.
OpenPawz ships a native Rust CLI that talks directly to the same engine library as the desktop app. No REST API. No network layer. No second-class citizen.
The Librarian Method inverts the problem. Instead of the system guessing which tools to load, the agent itself requests the tools it needs — after it has understood the user's intent.
The metaphor is literal: a library patron (the agent) walks up to a librarian and describes what they need. The librarian finds the right books. The patron never needs to know the Dewey Decimal System.
The Conductor Protocol treats flow graphs not as programs to execute, but as blueprints of intent that can be compiled into optimized execution strategies before a single node runs.
Traditional platforms interpret flows imperatively — "do this, then this, then this." The Conductor interprets flows declaratively — "here is what needs to happen; let me figure out the fastest way to make it happen."
The compilation step produces an ExecutionStrategy: a sequence of phases, where each phase contains units that run concurrently, and each unit represents one or more original nodes merged or classified for optimal execution.
AI agents are powerful because they do things — they read files, run commands, send messages, search your data. That power comes with a question most agent frameworks don't answer well:
What stops the agent from doing things it shouldn't?
Most agent systems bolt on safety as an afterthought: a prompt that says "be careful," maybe a regex filter on outputs, and hope for the best. That's not security. That's a suggestion.
OpenPawz takes a different approach. We treat agent security as a systems engineering problem — not a prompt engineering one. The result is a 12-layer defense-in-depth architecture enforced at the Rust engine level, where the agent has zero ability to bypass controls regardless of what any prompt says.
Project Engram is a three-tier memory architecture for desktop AI agents. It replaces flat key-value memory stores with a biologically-inspired system modeled on how human memory works: incoming information flows through a sensory buffer, gets prioritized in working memory, and consolidates into long-term storage with automatic clustering, contradiction detection, and strength decay. The result is agents that remember context across sessions, learn from patterns, and forget gracefully.
This document describes the architecture as implemented in OpenPawz — a Tauri v2 desktop AI platform. The system implements three memory tiers, a persistent graph, hybrid search with reciprocal rank fusion, background consolidation, field-level encryption, and full lifecycle integration across chat, tasks, orchestration, and multi-channel bridges. This is our passion and looking for more minds to get involved!
Project Engram is a three-tier memory architecture for desktop AI agents. It replaces flat key-value memory stores with a biologically-inspired system modeled on how human memory works: incoming information flows through a sensory buffer, gets prioritized in working memory, and consolidates into long-term storage with automatic clustering, contradiction detection, and strength decay. The result is agents that remember context across sessions, learn from patterns, and forget gracefully.
This document describes the architecture as implemented in OpenPawz — a Tauri v2 desktop AI platform. The system implements three memory tiers, a persistent graph, hybrid search with reciprocal rank fusion, background consolidation, field-level encryption, and full lifecycle integration across chat, tasks, orchestration, and multi-channel bridges.
This is our passion and looking for more minds to get involved!
That means:
No headless operation. You can't run agents on a server without a display. No scripting. Automating agent management requires either a REST API you have to host or brittle UI automation. No CI integration. Checking agent status, cleaning up sessions, or validating configuration in a pipeline? Open a browser. No composability. You can't pipe agent output into jq, grep, or another tool. The data is trapped behind a window. AI power users — the people building real workflows, deploying to production, managing dozens of agents — live in the terminal. Forcing them into a GUI for every interaction is a productivity tax they shouldn't have to pay.
OpenPawz ships a native Rust CLI that talks directly to the same engine library as the desktop app. No REST API. No network layer. No second-class citizen.