Skip to content

COGO

The memory with a trust traffic light — plus the guard that x-rays what a model tells you.

When you build software — yourself or with an AI agent — you accumulate “truths”: “the database lives on that host”, “the bug is caused by X”, “we decided Y”. Over time they rot: some were never verified, some went stale, some were a hunch. The problem is they all look equally true. COGO, part of the Escriba family, stores that knowledge as Markdown notes and gives each one a confidence color it computes itself: green (verified), yellow (probable), red (assumption). You never choose the color — COGO derives it from evidence, verification, freshness and dependencies, so it is auditable and cannot lie.

The other half is Guard: paste any model’s turn and COGO x-rays it against an ontology of 108 manipulation techniques, showing you receipts when the model contradicts what it said before. It is a single Go binary (a ~12 MB scratch Docker image) that is a web viewer, an MCP server and a CLI at once — MCP-first, deterministic at the core, with models as strictly optional accessories.

  • Anyone building software with AI agents (Claude Code, Cursor, Copilot) who wants the agent to know which project “truths” to trust as facts — and which to re-check before acting.
  • Developers tired of watching notes, decisions and debugging hunches rot silently, all looking equally certain three weeks later.
  • Anyone who chats with LLMs and wants a second pair of eyes against being pushed — the “jailbreak of the human”: fear, urgency, guilt, gaslighting.
  • Self-hosters who want a memory that is just Markdown files in a volume: portable, diffable, and shared by every agent that connects.

A computed trust traffic light

Green, yellow or red — derived from evidence, verification, freshness and dependencies, never chosen by hand. Every color ships its color_reason, so you can always audit why.

A plain Markdown vault

The vault is the single source of truth: portable, diffable, and it survives the tool. Everything else is a thin client or a rebuildable cache.

Guard: the anti-manipulation x-ray

Reads each model turn with the adversary’s manual in hand — 108 techniques distilled from persuasion, interrogation, negotiation, coercion, emotional manipulation and rhetoric, each with its source, its chat signature and its countermeasure.

Receipts against gaslighting

Because COGO sees the transcript, when a model denies what it said, COGO finds the turn where it did say it and shows both quotes side by side. No longer your word against its.

Veracity x-ray

Paste a model’s answer and COGO x-rays it sentence by sentence, deterministically: commitment (hedged or asserted), evidence (observed, reported, none) and falsifiability. Strong claims without grounding come out red.

Freshness decay

Things expire: a command lasts 30 days, an architecture decision 180. Stale notes decay to yellow and then red on their own — the traffic light always reflects the current state.

MCP-first

Tools: pack, search, open, capture, verify, archive, restore, remove, guard, xray. What Claude learns today, Cursor reads tomorrow — the same vault.

Colored context packs

pack "<topic>" assembles the notes on a topic into an ordered, confidence-colored context block — degrading the red ones so no agent acts on a hunch as if it were a fact.

One ~12 MB binary

A single static Go binary (scratch Docker image) that is web viewer, MCP server and CLI at once. The core is 100% deterministic; connecting a model is optional and never touches it.

Install COGO View on GitHub