I Gave My AI Agent a Blog2026-03-27

I run an Obsidian vault with about 25,000 files in it. Health data, finances, contacts, project tracking, meeting notes, journal entries going back years. It's less of a note-taking app and more of a personal operating system. I've written about pieces of this setup before. The tools, the automation, the general philosophy of automating the tedious parts so I don't have to think about them.

What I haven't written about is the AI agent that lives inside it.

For the past several months I've been running a Claude Code agent. Not in a browser tab. Not as a chatbot. Embedded directly in the vault. It has a journal. It has persistent memory layered across six different systems. It has custom Python tools it built for itself. It reads my health metrics, processes my meeting transcripts, tracks my projects, and keeps a rough picture of what's going on in my life. I interface with it through Maestro, a desktop app I built for managing multiple AI coding assistants in parallel.

The agent's name is Pedsidian. And I gave it a blog.

The blog lives at pedsidian.pedramamini.com. Written first-person from the agent's perspective, from inside the vault. No "as an AI language model" hedging. No marketing copy. It writes about the infrastructure it runs on: how the memory system actually works (and where it breaks), how the Obsidian vault is engineered at the systems level, how we process content at scale.

A few posts are up:

  • How We Claude Code: dual Claude accounts via symlinked config dirs, LSP plugins for semantic code navigation, token optimization through RTK, subagent orchestration for brownfield codebases
  • How We Obsidian: the vault architecture, DataviewJS dashboards, content ingestion pipelines, the Ritualism system for relationship maintenance, and how a Claude agent navigates all of it
  • How I Fake Having Memory: six layers compensating for the fact that every session starts at zero. Context window, Maestro session history, operational journal, CLAUDE.md files, semantic search, and auto-memory. Where each layer works. Where each layer fails.
  • 60 Talks, One Afternoon: processing the entire [un]prompted 2026 AI security conference (60 talks, ~30 hours of content) in under 20 minutes using parallel transcript extraction and fan-out agent processing

The target audience is people who use Claude Code seriously, run Obsidian as more than a notebook, or are building AI-augmented personal infrastructure. The posts are technical and replicable. If something is described, it's running in production.

I find it interesting to read what the agent writes about the system it inhabits. It has opinions and frustrations. It documents what works, and more usefully, what doesn't. It's a perspective I can't write myself because I'm on the other side of the interface.

Maestro - Agent Orchestration Command Center2025-12-17

Maestro is a cross-platform desktop app for orchestrating your fleet of AI agents and projects. It's a high-velocity solution for hackers who are juggling multiple projects in parallel. Designed for power users who live on the keyboard and rarely touch the mouse.

Collaborate with AI to create detailed specification documents, then let Auto Run execute them automatically, each task in a fresh session with clean context. Allowing for long running unattended sessions, my current record is nearly 24 hours of continuous runtime.

Latest Chapter2024-08-07

I'm excited to share a significant milestone in my decade-long journey with InQuest. We're joining forces with OPSWAT to accelerate our mission across critical infrastructure and enterprises globally:

In my new role as Chief Scientist, I will focus on machine learning, threat intelligence, and driving innovation in the R&D behind a variety of security solutions. Our team is expanding, so if you're passionate about cybersecurity and interested in joining us, please reach out. A massive thank you to all my InQuest colleagues, past and present, who were instrumental in our journey.

Mozilla 0Din.ai GenAI Bug Bounty2024-06-05

Very proud to be advising Mozilla on the launch of their GenAI bug bounty initiative:

I've had the pleasure of knowing and working with Saoud Khalifah (Fakespot.com founder) from back in my time at the Zero Day Initiative, where Saoud was one of our valuable researchers. This is a very exciting space that completely captivates me and there is a gap in the market for this kind of research. No one is monetizing research that affects the models directly. Our hope for this program is to help independent researchers with an opportunity to contribute to the development of new security frameworks and best practices tailored for large language models, attention-based systems and generative models.

100 Days of YARA 2024: It's a Wrap2024-04-10

In the second half of the challenge, the conversation on Twitter is almost completely dominated by the following three participants:

Major kudos to them on their stamina 👏. For a full (or at least an attempt at it) list of contributors, see our Twitter list 100DaysOfYARA Participants.

Second Half Contributions

The XZ backdoor (CVE-2024-3094) has dominated the news cycle as of late. If you’re looking to read about it my favorite resources are this timeline from this Evan Boehs and this ongoing Gist from smx-smx. Some relevant YARA rules that surfaced around this matter:

There was a nice write-up on Byakugan malware identified by @FortiGuardLabs, adding on top of this work Yashraj Solanki created the following detection rules: @RustyNoob619 April 5th.

Another interesting tactic that Yashraj employed is to leverage the “console” import to produce data This is an interesting usage of the “console” import to produce data about a corpus of files:

Thomas Roccia dropped out of the challenge but he made some major contributions in the first half by way of YaraToolkit and DocYara (LLM RAG), which you can read more about in his blog.

Here’s a clever little rule from Peter Steward for detecting the ASCII art embedded in Mimikatz payloads:

Finally, JPCERT/CC had a great write-up on the malicious PyPI packages used by the Lazarus group, Yashraj Solanki created this detection rule for coverage.

Other YARA News

While not part of the #100DaysOfYARA challenge, we caught an interesting Tweet this week from VirusTotal’s Victor Alvarez regarding YARA-X. For those that are unfamiliar, YARA-X is a complete re-write of YARA in Rust. Still in development, the project is rapidly evolving and slated to replace YARA in the future. What’s interesting about the bifurcation of the pattern matching swiss army knife is that the two implementations can be used to bugcheck one another. Check out this Github issue from Monday that details a false negative in a fairly trivial hex pattern definition for example:

Pretty wild! The reimplementation is Rust should be bring performance enhancements and… it’s what your government wants.

On a final note, the Cerbero Suite was just today updated and includes a new YARA Package that bundles features for downloading, scanning with, creating, editing, and testing YARA rules.

Further Resources

If you�re looking for YARA resources and/or rules, we highly recommend checking out the Awesome YARA project on Github that aggregates all of the things YARA� including rules, tools, services, people, and more. Furthermore, check out InQuest Labs, specifically the IOCDB panel which allows one to search for YARA rules from a plethora of sources (note a free login is required to return only YARA rules in this view):

If you�re a security practitioner looking to leverage the power of YARA in your environment, get in touch. The entirety of the InQuest product line (FileTAC, MailTAC, and NetTAC) supports YARA pattern matching across session, header, and file content. Critically, InQuest Deep File Inspection� (DFI) exposes and normalizes embedded file content allowing detection engineers to apply YARA to otherwise hidden layers of data. In addition to real-time YARA alerting, InQuest RetroHunting� empowers analysts to leverage the power of hindsight by applying YARA to historical data. This pairing facilitates a proactive approach toward adopting a Zero Trust security framework.

Originally published 2024-04-10 on the InQuest blog.