Terraphim

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.

AI coding agents make the same mistakes over and over. We built a learning system that captures failures, stores corrections, and feeds them back into future sessions — turning every error into institutional memory.

Builds on Why Graph Embeddings Matter — the deterministic engine that makes "remember this correction forever" cheap. Apply the pattern in your own project via the Command Rewriting How-to.

You know what is embarrassing? Making the same mistake for the tenth time. Last week, I typed docker-compose up instead of docker compose up. The command failed. I sighed. I corrected it. Three days later? Same thing. Same sigh. Same correction.

Builds on Why Graph Embeddings Matter — the deterministic engine that lets Terraphim store and replay corrections in microseconds. Apply the pattern in your own project via the Command Rewriting How-to.

Today we are announcing a significant enhancement to Terraphim's engineer roles: multi-haystack support. FrontEnd Engineers and Python Engineers now have access to both local code search (via Ripgrep) and global GitHub search (via GrepApp) in a single query.

We are announcing native hook support for terraphim-agent v1.8.1. This feature captures failed commands from AI agents (Claude Code, Codex, OpenCode) and learns from them, creating a personal knowledge base of mistakes and corrections. No more jq dependency, no more bash wrappers: just terraphim-agent learn hook.

When it comes to semantic search, there are fundamentally different architectural approaches. Alibaba's zvec and Terraphim represent two distinct philosophies: neural embeddings vs. knowledge graphs, scale vs. interpretability, dense vectors vs. co-occurrence relationships.

How we use Aho-Corasick automata and knowledge graphs to automatically enforce coding standards across AI coding agents like Claude Code, Cursor, and Aider.

New: see Why Graph Embeddings Matter for the underlying engine that makes these hooks possible — sub-millisecond, deterministic, fully explainable.