Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/neerajg03/vector-memory/agents-mdgit clone --depth 1 https://github.com/NeerajG03/vector-memoryWhat 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 | $0.03436 | $0.03436 |
| Opus 5 | $0.01718 | $0.01718 |
| Sonnet 5 | $0.00687 | $0.00687 |
| Haiku 4.5 | $0.00344 | $0.00344 |
Grade A, and why
vector-memory 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 536 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guide - Vector Memory MCP Server
This document provides AI agents with comprehensive information about the codebase architecture, design decisions, and development guidelines.
Table of Contents
- Project Overview
- Architecture
- File Structure
- Core Components
- Design Decisions
- Development Guidelines
- Testing Strategy
- Publishing Workflow
Project Overview
Purpose: MCP server that provides semantic memory capabilities for AI assistants using Redis vector store and HuggingFace embeddings.
Key Features:
- Save files (PDF, TXT, MD) to vector memory
- Recall information using natural language queries
- Automatic duplicate removal when re-saving files
- Smart chunking based on file type
- Memory management tools
Tech Stack:
- Language: Python 3.12+
- Framework: FastMCP (MCP server framework)
- Vector Store: Redis with RedisVectorStore
- Embeddings: HuggingFace sentence-transformers
- Build Tool: Hatchling
- Package Manager: uv
Architecture
High-Level Flow
User/AI Client
↓
MCP Protocol (stdio)
↓
FastMCP Server (vector_memory.py)
↓
├─→ HuggingFace Embeddings (sentence-transformers)
└─→ Redis Vector Store (mcp_vector_memory:*)
Data Flow
-
Save to Memory:
File Path → Check Existence → Determine File Type → Get Optimal Chunk Size → Load Document → Remove Old Versions → Chunk Content → Generate Embeddings → Store in Redis -
Recall from Memory:
Query → Generate Query Embedding → Similarity Search in Redis → Retrieve Top K Results → Format Output
File Structure
vector-memory/
├── vector_memory.py # Main MCP server (2 tools)
├── manage_memory.py # Interactive management CLI
├── cleanup.py # Quick cleanup CLI
├── main.py # Entry point (if needed)
├── test_connection.py # Connection test script
├── validate_server_json.py # Schema validation script
├── pyproject.toml # Package configuration
├── server.json # MCP registry metadata
├── README.md # Quick start guide
├── USAGE.md # Complete usage documentation
├── AGENTS.md # This file
├── LICENSE # MIT license
└── .github/workflows/
└── publish-mcp.yml # Automated publishing workflow
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.
- yesterday First seen · 536 lines · 3,436 tokens per session scan A c26bb0507933
vector-memory AGENTS.md is an instructions file published in the GitHub repository NeerajG03/vector-memory (0 stars, last pushed 10mo ago), licensed MIT. It adds 3,436 tokens to every session, about $0.0172 per session on Opus 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.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.