knowledge-graph

A common point of confusion in Terraphim is understanding the difference between FFF (fzf-like fuzzy file finder) and Ripgrep haystack. This post clarifies what each does and how they complement each other.

This guide documents the step-by-step process for setting up a Frontend Developer role in Terraphim, including knowledge graph validation, MCP server configuration, and integration with OpenCode.

Vector embedding calls are the hidden tax on every RAG pipeline. You pay latency, you pay API cost, you get probabilistic results that vary run to run. There is a class of problem where none of that is acceptable. This post shows how Terraphim replaces embedding calls with Aho-Corasick finite-state automata -- deterministic, auditable, and under one millisecond for 1.4 million patterns.

We have published a comprehensive walkthrough showing how to build a specialised front-end developer agent using Terraphim's knowledge graph system, dual haystacks, and deterministic search. This post walks through the key concepts and links to the full guide.

Vector databases are probabilistic and slow. Graph embeddings are deterministic and sub-millisecond. If you are building context for an AI coding agent — or any system where you need to know why a result came back — the difference is not academic. It changes what your application is allowed to promise.

Your AI coding agent already has a knowledge graph. It is just not yours yet. The model knows GitHub, Stack Overflow, and the public training corpus -- it has no idea that in your project npm should be bun, that RFP is shorthand for acquisition need, or that the email about the Stripe receipt for the Obsidian licence lives in your Fastmail mailbox. This post shows the smallest path to fixing that for both Claude Code and opencode, using Terraphim and the three roles we have published over the last week (Terraphim Engineer, Personal Assistant, System Operator).

Two paths. CLI first.

Most "personal AI" tools split your context across silos: one search box for email, another for notes, a third for your chat history. Terraphim treats every source as a haystack on the same role, so a single query crosses all of them. This post shows how to wire up the two most common personal sources -- email via JMAP and notes in an Obsidian vault -- under a new Personal Assistant role.

Terraphim's System Operator role is the demo we point people at when they want to see a real Logseq knowledge graph drive search. 1,347 Logseq pages, 52 of them carrying explicit synonyms:: lines, covering Model-Based Systems Engineering vocabulary -- requirements, architecture, verification, validation, life cycle concepts. This post walks the demo end-to-end and shows the piece people miss: the KG is doing real work, not just re-ranking text matches.