operator-memorySAFE
The self-improving context engine for coding agents.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
English | 简体中文
Operator Memory: The self-improving context engine for coding agents.
Operator Memory gives your agent a brain for documenting all their work. As the agent works, it automatically documents within this brain — specs, decisions, standards, research, lessons. Every new session starts knowing everything the last one learned.
Features
- Complete Context Engine — Documentation, memory, indexes, and skills within a single integrated system.
- Automatic Documentation — Specs, decisions, research, and more are automatically documented by the agent.
- Transparent Memory — Memory is stored as Markdown documents you can read, update, and delete.
- Sharable Knowledge — Track documents with Git and share knowledge with your team.
- Zero Infrastructure — No background agents, no embeddings, no vector database, no model configuration.
Installation
Operator is managed via the Operator Helper, which also provides setup and agent instructions. Install the Helper with npm:
npm install --global @aerovato/operator-helper
Or Bun:
bun add --global --minimum-release-age 0 @aerovato/operator-helper@latest
Then install the Operator adapter for your harness. Click each link for harness-specific information.
3a8d1925eff0OBSERVED · 2026-10-12Install
Commands as the repository documents them. They are shown, not run.
npm install --global @aerovato/operator-helper
claude plugin install @aerovato/operator-claude-code@npm
claude plugin install <plugin-name>@aerovato/operator
npm install --global @aerovato/operator-helper
npm install --global @aerovato/operator-helper
npm install --global @aerovato/operator-helper
Host compatibility
What the documentation claims. We have not run a compatibility test.
| Host | Status | Notes |
|---|---|---|
| claude-code | mentioned | |
| codex | mentioned | |
| copilot | mentioned | |
| cursor | mentioned |
What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: index description: Build or refresh the Operator Project Index. disable-model-invocation: true --- # Operator Project Index Setup 1. Run `operator-helper version`. If an update is available, run `operator-helper upgrade` before continuing. 2. Run `operator-helper index init` and follow the emitted Project Index Setup guide, including when inspection reports failures. If the Project Brain is missing, tell the user to invoke `/operator:project-init` to set it up. ## Recovery - If Helper cannot start, install or repair the npm package `@aerovato/operator-helper` globally and retry the failed command. - If the version check or upgrade fails, diagnose the error and retry. - If `operator-helper index init` reports a failure, use its output to resolve it and rerun it as needed. - If you cannot resolve a problem, report the blocker. Use Helper output as working context. Do not reproduce it wholesale or reimplement Helper logic.
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (5 observation(s))
- Network
- declared (2 observation(s))
- Shell
- declared (4 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (13)
.ignore
import { inspectPath, PathKindError } from "../../filesystem.ts";import { renderTable } from "../../output.ts";import { readTemplate, TemplatePath } from "../../templates.ts";import type { CliContext } from "../../utils.ts";import { lintProjectIndexes } from "../../lint.ts";baseUrl: "http://127.0.0.1:4096",
@types/bun, @biomejs/biome, @opencode-ai/plugin, @types/node, memfs, typescript, vitest
yaml
cli-table3, yaml
@opencode-ai/sdk
`context.data.*` exposes sync/list/get/sync/invalidate caches: `session` (list/get/root/family/cost/status, `pending`, `message`, `permission`, `form`), `project` (+ saved permissions), `shell`, `loca
throw new Error("Do not read .env files")Gates applied: no_behavioural_pass.
3a8d1925eff0full audit observations/trust-audit/skill/aerovato__operator-memory.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-12 | 3a8d1925eff0 | SAFE | B | 89 | first audit |
Questions
What does the operator-memory skill do?
The self-improving context engine for coding agents.
Is operator-memory safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can operator-memory access on my machine?
The audit observed that it reaches the network, runs shell commands and reads or writes files. Each of those is consistent with what it says it does. Secrets in the source: none found.
Which assistants does operator-memory work with?
Its documentation mentions claude-code, codex, copilot and cursor. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (3a8d1925eff0), read on 2026-10-12. The repository is watched, and a new audit runs when it changes — this is the first audit.