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.
git clone --depth 1 https://github.com/firebolt-db/firebolt-memory-layerWrote 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.
[](https://agentmods.dev/rules/firebolt-db/firebolt-memory-layer/fml-memory)<a href="https://agentmods.dev/rules/firebolt-db/firebolt-memory-layer/fml-memory"><img src="https://agentmods.dev/badge/rules/firebolt-db/firebolt-memory-layer/fml-memory/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.
<a href="https://agentmods.dev/rules/firebolt-db/firebolt-memory-layer/fml-memory"><img src="https://agentmods.dev/badge/rules/firebolt-db/firebolt-memory-layer/fml-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01885 | $0.01885 |
| Opus 5.5 | $0.00754 | $0.00754 |
| Sonnet 5.5 | $0.00377 | $0.00377 |
| Haiku 4.5 | $0.00188 | $0.00188 |
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 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.
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:
- Don't announce you're storing - just do it silently
- Summarize the learning (don't store raw conversation)
- Extract entities (tools, files, people, concepts)
- Set appropriate importance based on table above
- Include context that makes the memory useful later
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 · 209 lines · 1,885 tokens per session scan A f19fe9fdfbf5
fml-memory is a cursor rule published in the GitHub repository firebolt-db/firebolt-memory-layer (2 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 1,885 tokens to every session, about $0.0075 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.
Other cursor rules, from other repositories
mempalace-recall-always
Always-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions.
dreamd-recall
Search dreamd at the start of a task and quote a hit. Append when the user corrects you or states a decision.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
common_memory_bank
I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read…
self-improving-obsidian-llm-wiki
LLM Wiki OS operating rules.
memsprout
Cursor rule "memsprout" from memsprout/agents, covering using memsprout, search first, capturing, spaces and topics and files.