We build the systems behind the business — not just apps.

Every product we ship sits on the same foundation: a graph-native knowledge base, AI agents that read and write it directly, and automation that turns decisions into action. Here's what's actually underneath.

What's different

The concepts behind everything we build

Four ideas we keep reaching for, on every project — because they compound instead of decaying.

Graph-native knowledge modeling

Every fact is a node. Every relationship is an edge.

We model knowledge as a graph, not a folder of documents. Concepts, decisions, and sources link directly to each other, so meaning compounds instead of decaying into stale pages nobody rereads.

  • Plain-text notes double as graph nodes — portable, diffable, no proprietary format or vendor lock-in.
  • Explicit links are the edges: backlinks, neighbors, and shortest-path queries resolve deterministically, not by fuzzy search.
  • Contradictions are tracked, not silently overwritten — every claim carries provenance and a confidence rating.

Knowledge bases built to compound

Built for compounding, not just retrieval.

Most teams bolt a chatbot onto raw documents and call it a knowledge base. We treat capture and curation as first-class engineering — one concept per note, sourced claims, decisions that are never quietly rewritten.

  • Lightweight decision records are superseded, never deleted — a full audit trail of why, not just what.
  • Clear thresholds decide what earns a permanent note versus a passing mention, keeping the graph dense and useful.
  • The index is always derived from the notes, never hand-maintained, so it can't drift out of sync.

AI as an operating layer

Agents that read and write the same knowledge you do.

We don't bolt AI onto the business after the fact — we build it as a layer the business runs on. The same graph we read from is what our agents reason over and write back to.

  • Tiered model routing: fast reasoning models triage and delegate execution to specialized task models, so cost tracks the size of the job.
  • Capture and reasoning work local-first where it matters, so day-to-day operation doesn't depend on a third-party API staying up.
  • Every agent-authored change is version-controlled and reviewable — automation never means losing the paper trail.

Agentic automation, not just scripts

A router, not a monolith.

Instead of one giant assistant, we build a router that triages work to narrowly-scoped specialist agents — each with its own permissions, tools, and slice of the knowledge base.

  • Domain-scoped agents keep blast radius small and permissions explicit, instead of one over-privileged bot.
  • Scheduled agents publish operational status automatically, so reporting stops being a manual chore.
  • The same pipeline that triages an incoming message can turn an idea into a spec, into issues, into shipped code.

See it

Why a graph beats a document pile

Keyword search finds pages. A knowledge graph finds relationships. Watch an agent walk three hops to an answer no single document contains.

hermes ❯ Why did we change pricing before the launch?
sourced by surfaces caused by blocks drives feeds timed against DEC Pricing decision SRC Market research CON Customer churn CON Onboarding flow DEC Q2 launch CON Product roadmap CON Support load
  1. 01 Start → Pricing decision
  2. 02 sourced by → Market research
  3. 03 surfaces → Customer churn
  4. 04 caused by → Onboarding flow
  5. 05 blocks → Q2 launch

Philosophy

Compounding, not disposable

Most engineering work produces artifacts that decay — chat logs no one rereads, docs that drift from reality, dashboards nobody trusts. We build the opposite: every decision, source, and automation feeds back into one graph that gets more valuable over time, not more cluttered. That's the standard we hold every project to, whether it's an internal tool or a client-facing product.

Standing on open source

Projects we build with

Our stack is deliberately local-first and open where it can be. These are the projects that make the work possible — thank you to their maintainers.

Astro

MIT

Static site framework powering www.300tech.cloud and our brand landing pages.

graphify

Local tooling

Knowledge-graph querying over our markdown notes — path, explain, and community structure.

Ollama

MIT

Local model runtime for the agent stack — reasoning stays on our hardware when it matters.

Supabase

Apache-2.0

Postgres, auth, and edge functions behind lead intake and product data planes.

Inter

OFL-1.1

Primary UI typeface in the HERMES·OS design system.

JetBrains Mono

OFL-1.1

Monospace telemetry typeface used for lockups, kickers, and status chrome.

Matt Pocock skills

Open source

Engineering and productivity agent skills vendored into our COS skill bundle.

Python

PSF

Indexer, connectors, dashboards, and publish scripts across the Hermes COS.

Contact

Get in touch

Want the same foundation under your product? Tell us what you're building.

Email us