Oratrixa Phronosis
Agents don't act. They propose. Governance decides.
What it does
ORA is a communication platform built on slow discovery, deep alignment, and emotional safety. Three phases — ORA (connection), ORIGIN (intelligence), SANCTUARY (the safety layer).Modern AI optimizes for capability. ORATRIXA Phronesis optimizes for judgment. A distributed governance protocol that sits between AI agents and execution. Agents don't act — they propose. A deterministic math engine scores every action before it touches the real world. Trust accumulates as a graph.
Does the same job
all alternatives →
- HAHephaestus – Autonomous Multi-Agent Orchestration FrameworkNov 2025 · github.com · ▲81
- TPTrust Protocols for Anthropic/OpenAI/GeminiFeb 2026 · mnemom.ai · ▲40
Much of my work right now involves complex, long-running, multi-agentic teams of agents. I kept running into the same problem: “How do I keep these guys in line?” Rules weren’t cutting it, and we needed a scalable, agentic-native STANDARD I could count on. There wasn’t one. So I built one. Here are two open-source protocols that extend A2A, granting AI agents behavioral contracts and runtime integrity monitoring: - Agent Alignment Protocol (AAP): What an agent can do / has done. - Agent Integrity Protocol (AIP): What an agent is thinking about doing / is allowed to do. The problem:…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com