What is Super-Memory-TS AGENTS.md?

Project instructions for Super-Memory-TS, an npm-publishable MCP server that stores project information for AI assistants and finds related content by meaning.

Use them when developing or maintaining Super-Memory-TS, indexing projects, or working with its local memory and search system.

They explain the server’s architecture, commands, project separation, and search modes before development work begins.

How Veedubin/Super-Memory-TS configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Veedubin/Super-Memory-TS. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Veedubin/Super-Memory-TS/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Veedubin/Super-Memory-TS

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/veedubin/super-memory-ts/agents-md/github.svg)](https://agentmods.dev/instructions/veedubin/super-memory-ts/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/veedubin/super-memory-ts/agents-md"><img src="https://agentmods.dev/badge/instructions/veedubin/super-memory-ts/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/veedubin/super-memory-ts/agents-md"><img src="https://agentmods.dev/badge/instructions/veedubin/super-memory-ts/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,852 This file is loaded in full into every session.

When invoked 1,852 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01852	$0.01852
Opus 5.5	$0.00741	$0.00741
Sonnet 5.5	$0.00370	$0.00370
Haiku 4.5	$0.00185	$0.00185

Measured 2mo ago against content hash 4db39d66540c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Super-Memory-TS AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - Super-Memory-TS

Role: NPM-publishable MCP server with local embeddings and vector search
Package: @veedubin/super-memory-ts
Repository: https://github.com/Veedubin/Super-Memory-TS
License: MIT
Current Version: v2.6.5

Why This Exists

This project provides a local-first semantic memory system with project isolation, tiered search strategies, and MCP protocol integration for AI assistants like Boomerang.

Architecture (v2.6.5)

Component	Technology	Notes
Database	Qdrant (v1.7+)	HNSW indexing, payload filtering
Embeddings	BGE-Large (1024-dim, GPU) / MiniLM-L6-v2 (384-dim, CPU)	fp16 precision by default
Protocol	MCP (Model Context Protocol)	stdio/HTTP modes
Integration	Built-in for Boomerang v2	Zero-overhead direct imports

Key Features

Project Isolation: Payload-based filtering via BOOMERANG_PROJECT_ID
Custom Path Indexing: index_project tool accepts custom path parameter
Tiered Search:
- tiered (default): Fast Reply - MiniLM + BGE fallback
- parallel: Archivist - Dual-tier RRF fusion for maximum recall

Commands

Command	Purpose
`npm run build`	Compile TypeScript to `dist/`
`npm run typecheck`	Type-check without emitting (`tsc --noEmit`)
`npm run prepublishOnly`	Runs `npm run build` before publish
`npm run dev`	Watch mode with `tsx`
`npm run test`	Run tests with `bun test`
`npm run lint`	ESLint on `src/`

Publishing

Trigger

Pushing a semver tag triggers .github/workflows/npm-publish.yml:

git tag v1.0.0
git push origin v1.0.0

Workflow Details

Trigger: push on tags matching v*.*.*
Node version: 22
Scope: @veedubin
Provenance: Enabled (id-token: write)
Secret required: NPM_PUBLISH_TOKEN

Pre-Publish Checklist

NPM_PUBLISH_TOKEN secret is set in GitHub repo settings
package.json version bumped appropriately
npm run typecheck passes
npm run build succeeds and dist/ is generated
Tag pushed in vX.Y.Z format

Read the full file on GitHub · 182 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 182 lines · 1,852 tokens per session scan A 4db39d66540c

Subscribe to this mod's changes

Super-Memory-TS AGENTS.md is an instructions file published in the GitHub repository Veedubin/Super-Memory-TS (0 stars, last pushed 4mo ago), licensed MIT. It adds 1,852 tokens to every session, about $0.0074 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Super-Memory-TS AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Super-Memory-TS AGENTS.mdVeedubin/Super-Memory-TS	Instructions file	0	4mo ago	MIT	A	1,852	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

Super-Memory-TS: Instructions file for Codex