Wazoo

@etok_me @garrytan @zocomputer #BuildWithZo 👏

Zomaxxing at @wazootech 🐴 Cloned @garrytan's gstack to run full YC office-hours 🐴 20+ autonomous agents handling GTM, discovery, GitHub sync, planning, development, and delivery 🐴 Using spaces to #BuildInPublic → etok.zo.space/built-with-zo @zocomputer #BuildWithZo

The first solo unicorn is using @zocomputer #BuildWithZo 🦄

What if I told you the foundation for AI memory was standardized nearly 3 decades ago? The W3C standardized HTML, CSS, and XML. In 1999, they also gave us RDF, the interoperable primitives of linked data. We don’t build more proprietary silos. We build on the Semantic Web.

@AndrewYNg @Oracle @richmondalake The hard part isn't memory. It's the whole agent experience. @wazootech helps it help you.

@akshay_pachaar Skill graphs coming soon @wazootech git.new/skill-ontology

Skill Graphs > SKILL .md Everyone's talking about skills for AI agents. But almost nobody is talking about how to structure them. Right now, the default approach is simple. You write one skill file that captures one capability. A skill for summarizing. A skill for code review. A skill for writing tests. One file, one job, and it works. But I recently came across an idea that made me rethink this entirely. What if skills weren't flat files? What if they were graphs? Let me explain what I mean. Think about how a senior engineer onboards you to a large codebase. They don't hand you one giant document and say "read this." They give you a map. They point you to the right modules. They explain how pieces connect. Then they let you go deeper only where you need to. That's the mental model behind a skill graph. Instead of one big file, you build a network of small, composable skill files connected through wikilinks. Each file captures one complete thought, technique, or concept. The links between them tell the agent when and why to follow a connection. Here's what changes with this approach. The agent doesn't load everything upfront. It scans an index, reads short descriptions, follows relevant links, and only reads full content when it actually needs to. Most decisions happen before reading a single complete file. Each node is standalone but becomes more powerful in context. A "position sizing" node in a trading skill graph works on its own. But link it to risk management, market psychology, and technical analysis, and now you have context flowing between concepts. And suddenly, domains that could never fit in one file become navigable. Company knowledge. Legal compliance. Product documentation. Org structure. All traversable from a single entry point. The building blocks are surprisingly simple. Wikilinks embedded in prose so they carry meaning, not just references. YAML frontmatter so the agent can scan nodes without reading them. Maps of content that organize clusters into navigable sub-topics. Markdown files linking to markdown files, and nothing more. If you want to dig deeper or try building one yourself, check out arscontexta. It's an open-source plugin that sets up the structure and helps you build skill graphs with your agent. I have shared the link in the next tweet.

@etok_me @realdavidleen @kevingu @obsdmd git.new/ontology 👀

@realdavidleen @kevingu My thoughts: Build an @obsdmd vault with wikilinks to connect skills Or use existing linked data standards to develop an interoperable skill graph. Skill ontology soon @wazootech?

give your agents a db, not just a file system x.com/gukevinr/statu…

The future of AI isn't a bigger context window. It's memory that actually remembers. Check out what we're building: git.new/world-model

That's what we built. Worlds Platform = vector embeddings + SPARQL knowledge graphs Neuro-symbolic memory for AI agents. Fuzzy matching AND formal reasoning. Not either/or. Both.

RAG is broken and nobody wants to say it. We keep stacking vector databases on vector databases. It kinda works. But "kinda" isn't infrastructure. Here's the real problem 🧵

We're launching soon. Early access: github.com/wazootech/worl… Star it. Watch us build.

AI capability should be a public good, not a walled garden. We're building open infrastructure so anyone can deploy agents with real memory. No vendor lock-in. No data siloing. Just interoperable, auditable intelligence.

We built a "hippocampus" for AI agents. A neuro-symbolic memory layer that combines vector search intuition with SPARQL precision. AI agents today forget everything. We're fixing that. Introducing Worlds Platform — the World Engine for persistent, auditable agent memory. 🧵👇