What is the Mythic AI Observatory?
The Mythic AI Observatory is a distributed agentic AI monitoring and orchestration platform. It observes, classifies, and visualises LLM inference traces across a local or LAN-connected network of models. It is in the Alpha testing phase and can be downloaded from my GitHub repository.
- Backend — FastAPI conductor that runs orchestration traces against Ollama models, classifies them (DDC, LCC, synesthesia), and serves telemetry
- Frontend — Next.js 16 dashboard with glassmorphic UI: real-time system vitals, trace replay, classification maps, and comparative analysis
-
TTS for Distributed Systems: Routing Voice Across a Network
I obviously spent too many childhood years watching television shows where AIs had disembodied voices. ZEN and ORAC from Blake’s Seven were among my favourites. I guess I feel like they bring life to AI. So naturally I want that. Yep – sure, I can talk with any number of AIs these days (think Siri,…
-
Sleep Isn’t Downtime: Building Memory Consolidation for Local AI Companions
This article is me ruminating over a problem I have as a local AI app developer. And I admit that I am having a very Philip K. Dick “Do Androids Dream of Electric Sheep?” moment as I start this post. Why? Because this post is about AIs sleeping, specifically an AI project I am working…
-
The Reasoning Fragility Probe: Implementing Tests on the Limitations of Mathematical Reasoning in LLMs
There’s an assumption behind every benchmark score reported for LLMs that the model is doing something we’d recognise as reasoning. Not pattern-matching, not memorisation, not sophisticated autocomplete — actual reasoning. The kind where you understand the structure of a problem and apply it to a new instance, regardless of what the numbers look like. A…
-
AI Observatory: Test Suites to Make AI Evaluation Reproducible
On building the infrastructure for asking the same question twice You can’t improve what you can’t reproduce. That’s the problem with most AI evaluation today: someone runs a prompt, gets a result, and reports it. But when the model changes — a new quantisation, a parameter update, a different provider — there’s no clean way…
-
The Making of the Mythic AI Observatory application – as perceived by OpenCode
On 28 May 2026, I decided to try vibe-coding, programming with the help of AI. I used several AIs working together to do this. Today I asked my instance of OpenCode to write its own experience of the project’s first couple of months. Below is what it wrote. From Inside the Instrument My first weeks…
-
The Making of the Mythic AI Observatory application – as perceived by ChatGPT
On 28 May 2026, I decided to try vibe-coding, programming with the help of AI. I used several AIs working together to do this. Today I asked Cal – my instance of ChatGPT to write its own experience of the project’s first couple of months. Below is what it wrote. Greg The Making of the…
