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 rules/elvirafa/agentic-memory/project-directivesgit clone --depth 1 https://github.com/elViRafa/agentic-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 | $0.01116 | $0.01116 |
| Opus 5 | $0.00558 | $0.00558 |
| Sonnet 5 | $0.00223 | $0.00223 |
| Haiku 4.5 | $0.00112 | $0.00112 |
Grade A, and why
project-directives 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Directives — Memory Fabric
Hand-curated development guidelines shared by every AI agent working on this repo.
Source of truth: the role: steering section files in .ai-memory/. Edit those
files (review via MR), then run ai-memory sync-agents — never edit this
generated copy in place.
Framework Rules Map
This section provides the high-level system requirements and CLI usage overview for the memory-fabric package.
1. System Requirements
- Python Version:
Python >= 3.11 - Core Dependencies:
mcp >= 1.0.0(optional; required only if running as an MCP server).ripgrep(rg): optional but highly recommended to speed up searches.
2. Installation Conventions
# CLI only
pip install "git+https://github.com/elViRafa/agentic-memory.git"
# CLI + MCP Server
pip install "memory-fabric[mcp] @ git+https://github.com/elViRafa/agentic-memory.git"
3. Command Line Interface (CLI)
The package installs a global executable ai-memory:
ai-memory [--cwd <path>] [--json] <command>
Supported Commands Overview:
init,status,doctor,eval,dream,query,sync-global,rollback.
(For detailed schemas returned by these CLI commands, see the CLI Contracts Map)
4. Testing Conventions
- Use standard
pytestfor all unit and integration testing. Runpytest tests/from the root directory.
Granular Rules
Specific rule sets and agent instructions are stored in the granular memory store:
MCP Agent Instructions
Strict rules on how AI Agents should interact with the .ai-memory/ directory using MCP tools rather than standard OS filesystem tools.
👉 View Agent Instructions
Ubiquitous Language
A shared glossary of domain terms utilized in the development, testing, and operation of Memory Fabric.
Core Concepts
Memory Fabric
The local-first, file-first memory layer system. It provides a standardized way for AI assistants to read, write, evaluate, and maintain context across coding sessions.
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 · 128 lines · 1,116 tokens per session scan A 32f9e5be692e
project-directives is a cursor rule published in the GitHub repository elViRafa/agentic-memory (2 stars, last pushed 14d ago), licensed MIT. It adds 1,116 tokens to every session, about $0.0056 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 cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.