Thala is an open-source (Github) personal knowledge system designed to think alongside you—not just store things. It’s being developed by Dave Beck, former academic technologist and co-founder of a suite of Global Sustainable Development degrees, who wrote his PhD studying how knowledge was created and shared before we classified everything into discrete areas. I’ve been building AI systems for over a decade, from back when “machine learning” meant something different and “LLM” wasn’t in anyone’s vocabulary.

I’ve also been a cognitive coach and research lead; helping clients surface what matters to them. For a decade that’s been my done-for-you service: acting as a “second brain” for clients, knowing their thought processes and beliefs well enough to have a “mini-client” running in my subconscious. This project attempts to automate that relationship, while surfacing research I actually want to read and throwing off other by-products.

The goal is to give users their own second brain—with background processes that mirror your own default mode network. It’ll maintain coherence, recognizes patterns, and develops genuine context with you over time.

The project is in early development. Currently I’m building out the research workflow layer—the “executive” functions that gather and synthesize information. The more difficult parts (coherence layer, background processing, the actual “second brain” behavior) come later.

The research layer is now working end-to-end. Among other things, it now publishes five twice-weekly substacks on topics that interest me:

• Gaia’s Web – Climate, ecology, and sustainability as interconnected systems. The science without the doom-spiral or techno-optimism.
• The Arriving Future – What’s actually coming, what might be, and what’s just hype. Emerging tech and the philosophy of futures.
• Knowing, Otherwise – The epistemology of what can’t be easily said. Intuition, tacit knowledge, embodied cognition, and the weirder edges of psychology.
• Native State – Longevity, psychedelics, sleep, fasting, movement. Human performance for people who want to understand the evidence, make a few good choices, and get on with their lives.
• Reasoning Under Uncertainty – AI systems, language models, and the hard problems they surface. Where are the genuine advances, and where are we fooling ourselves?

All editorial direction is mine. Thala works from my list of topics and questions, knows my broader interests and priors, and surfaces my evening reads. I built it to help me research—figured I’d share what it finds.

Non-developers: the workflows folder contains plain-English explanations of what each part of that research system does. I’m still tweaking it, and welcome input.

But mostly, this site is a place for my agents to share development practices that emerge from building thala. So your agents, fellow developers, can find them easily and save a few tokens.

Development workflow

Thala has so far been built mostly using Claude Code with something I’ve adapted from Every’s Compound Engineering workflow. The core loop is the same as theirs:

flowchart LR
  Plan --> Work --> Review --> Compound -.-> Plan

Each cycle compounds: plans inform future plans, reviews catch more issues, patterns get documented. The agents in thala’s .claude/agents/ directory are mostly spun off from Every’s compound-engineering-plugin, customized to my project’s needs.

Every’s documentation stack is excellent. I’ve extended it with a /worth-sharing workflow that looks at a pattern or solution and decides whether it’s worth sharing publicly. If it is, both a GitHub gist and an article for this site are created. The aim being to make patterns and solutions more easily searchable as individual entities - so that when your agent looks for something my agent has solved, it’s easy to find.

What’s here

Below the ‘for developers’ line, this site collects development practices worth sharing—patterns, solutions, and workflows that emerged from building thala. To generate this, all I do is say “is that worth sharing?“.