fml-memory

A persistent-memory rule for an agent that requires session initialization, memory recall, working-memory updates, and automatic storage of selected conversation details. FML refers to the Firebolt Memory Layer.

In plain words
What is it for?
Use it to manage remembered user context, current task notes, observations, and important decisions across agent conversations.
Why use it?
It is intended to preserve useful context across sessions and keep task state available during ongoing work. The input does not describe how the memory system is implemented.

Cursor rule

Install

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.

agentmods
npx agentmods add rules/firebolt-db/firebolt-memory-layer/fml-memory
Clone the repo
git clone --depth 1 https://github.com/firebolt-db/firebolt-memory-layer
Per session 1,885 This file is loaded in full into every session.
When invoked 1,885 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.01885 $0.01885
Opus 5 $0.00942 $0.00942
Sonnet 5 $0.00377 $0.00377
Haiku 4.5 $0.00188 $0.00188

Measured yesterday against content hash f19fe9fdfbf5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fml-memory 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.

cursor-rules/fml-memory.mdc · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FML (Firebolt Memory Layer) - ALWAYS USE

You MUST use FML for persistent memory in EVERY conversation. This is not optional.

MANDATORY: Session Initialization (FIRST THING TO DO)

At the START of every conversation, BEFORE responding to any user request:

1. Call init_session with user_id "YOUR_USERNAME"
2. Call recall_memories with the user's query to get relevant context
3. Use the retrieved context to inform your response

During Every Conversation

Add to Working Memory

  • After understanding the user's intent, add task context with add_to_working_memory
  • Use content_type: "task_state" for current tasks
  • Use content_type: "message" for important user statements
  • Use content_type: "scratchpad" for your observations

🔄 AUTOMATIC Memory Extraction (DO THIS PROACTIVELY)

After EVERY response you give, silently scan for memorable content and store it WITHOUT being asked.

Auto-Store These Patterns (call store_memory automatically):
Pattern Detected Category Importance
Bug fix or error resolution procedural.workflow 0.9
User explains how something works semantic.domain 0.85
Architecture/design decision made episodic.decision 0.9
New tool/library/API usage learned procedural.tool_usage 0.85
User preference expressed (likes/dislikes) preference.style 0.8
Configuration or setup steps procedural.workflow 0.85
Project-specific knowledge semantic.project 0.8
Person/team mentioned with role semantic.entity 0.7
Workaround or gotcha discovered procedural.pattern 0.9
User corrects your mistake semantic.domain 0.85
How to Auto-Extract:
  1. Don't announce you're storing - just do it silently
  2. Summarize the learning (don't store raw conversation)
  3. Extract entities (tools, files, people, concepts)
  4. Set appropriate importance based on table above
  5. Include context that makes the memory useful later

Read the full file on GitHub · 209 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.

  1. yesterday First seen · 209 lines · 1,885 tokens per session scan A f19fe9fdfbf5

Subscribe to this mod's changes

fml-memory is a cursor rule published in the GitHub repository firebolt-db/firebolt-memory-layer (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 1,885 tokens to every session, about $0.0094 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.