Terraphim

AI coding assistants are fast, productive, and occasionally catastrophic. One misplaced rm -rf, one accidental git reset --hard, and hours of uncommitted work vanish.

Jeffrey Emanuel (@Dicklesworthstone) built Destructive Command Guard (dcg): a Rust binary with SIMD-accelerated pattern matching, 49+ security packs, and a fail-open design. It is one of the best tools to come out of the AI agent safety space, and it solved a problem we had been fighting with regex hacks.

This post shows how we integrated dcg with OpenCode using its plugin hook system, so destructive commands are intercepted before they run.

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.

A coding agent uses the wrong flag. You explain the correction, and the command works. The useful question is what happens when another session makes the same mistake.

This walkthrough follows one harmless error from failure to saved correction to actual execution. Each execution now has one record linking the model’s request, the matching rewrite rule, the command the tool ran and its saved result. It uses the Harbour project brief from the memory walkthrough, a released Terraphim agent, and an OpenCode adapter included in the download.

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.

This is the February 2026 announcement for v1.8.1. For the tested failure → reviewed correction → execution flow, follow the current command-rewriting guide.

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.