-
A technical look at project modes, brand systems, editable HTML, media generation, preview sandboxes, exports, and design safety guardrails Most AI design tools are either image generators or slide generators. They can make something visually impressive, but the output is often hard to edit, hard to reuse, hard to export properly, or disconnected from the…
-
A technical look at reusable role definitions, runtime boundaries, delegated agents, approval policies, context modes, tool scopes, and profile promotion Most AI assistants treat every conversation the same way. The user sends a message, the assistant responds, and the same general-purpose agent tries to handle everything. That works for casual chat. It does not work…
-
A technical look at Skills Hub, Smart Skills activation, prompt injection, tool guides, provenance, and user-controlled self-improvement Most AI assistants have one big prompt and a list of tools. That works for simple chat. It does not scale well for a personal AI agent. A personal agent needs to handle different kinds of work: research,…
-
A technical look at the Safety & Control Plane, trust boundaries, prompt-injection defence, tool permissions, memory privacy, and user-approved actions Most AI agents are built for capability first and safety second. They add tools, memory, browser access, shell commands, and scheduled tasks, then try to bolt on safety later. That approach creates problems. A personal…
-
A technical look at local-first memory, entity extraction, retrieval, wiki export, and nightly refinement in a personal AI agent Memory is one of the biggest differences between a chatbot and a real personal AI agent. A chatbot can answer the current message. A personal AI agent needs to remember who you are, what you are…
-
A technical look at context assembly, memory retrieval, token budgeting, tool safety, and local-first AI architecture Context is one of the hardest problems in AI agents. A simple chatbot can survive on the latest user message and a bit of conversation history. A personal AI agent cannot. A real personal agent needs to understand the…
-
A technical look at self-awareness, diagnostics, controlled self-management, and user-approved improvement loops AI agents are getting more capable every month, but most of the conversation still focuses on tool use, model quality, and automation. That is important, but I think the next real step for personal AI agents is different. The next step is self-awareness…
-
Every once in a while, a project comes along that feels like it should already exist, something obvious in hindsight, yet strangely absent from the landscape. Thoth is one of those projects. In a world where AI tools increasingly rely on cloud‑hosted models, opaque data pipelines, and centralized storage, Thoth takes a very different stance:…
-
Building a Local, Privacy‑First RAG Pipeline with LangChain: From Embeddings to Hybrid Retrieval As part of my broader project to build a completely local, privacy‑first AI assistant, I’ve been exploring how to design a robust Retrieval‑Augmented Generation (RAG) pipeline using LangChain, LangGraph, and local LLMs. My goal is to create a model‑agnostic system that runs…
-
I have started building a completely local, privacy‑first AI assistant: a multimodal system that combines retrieval‑augmented generation (RAG) and tool calling powered by local LLMs. I chose a model‑agnostic framework—LangChain—to keep the architecture flexible and to make it easy to swap or compare models. My first step was to learn LangChain and LangGraph deeply so…