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/RohiRIK/OpenLtmWrote 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/commands/rohirik/openltm/memory)<a href="https://agentmods.dev/commands/rohirik/openltm/memory"><img src="https://agentmods.dev/badge/commands/rohirik/openltm/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/commands/rohirik/openltm/memory"><img src="https://agentmods.dev/badge/commands/rohirik/openltm/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 | $0.00041 | $0.01389 |
| Opus 5.5 | $0.00016 | $0.00556 |
| Sonnet 5.5 | $0.00008 | $0.00278 |
| Haiku 4.5 | $0.00004 | $0.00139 |
Grade A, and why
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 5d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parse the first word of the arguments as <subcommand>. Pass remaining words as <args>.
If no subcommand given, show:
Usage: /openltm:memory <subcommand>
recall — search memories
/openltm:memory recall [query] [--category X] [--project X] [--limit N]
learn — store insight
/openltm:memory learn [insight] [--category X] [--importance N] [--save-context]
forget — delete memory by ID
/openltm:memory forget <id> [reason]
relate — link two memories
/openltm:memory relate <src-id> <tgt-id> <type>
propose — review memories proposed at session end
/openltm:memory propose — list all pending proposals
/openltm:memory propose review — show proposals interactively
/openltm:memory propose accept <session-id> <index>
/openltm:memory propose reject <session-id> <index>
recall
Search LTM memories. Call mcp__plugin_openltm_memory__recall with parsed args:
| Arg | Field |
|---|---|
| positional text | query |
--category X |
category |
--project X |
project |
--limit N |
limit (default 10) |
Display each result: ID · content · category · importance ★ · confirmed count · tags · relations.
Write the query as natural language — each word is matched separately (full-text, plus semantic search when an embedding provider is configured), so FTS operators like quotes or NOT are not interpreted. Results are ranked by relevance, importance, decay, and project scope; stale memories are marked and ranked lower.
learn
Store a memory via mcp__plugin_openltm_memory__learn. Parse args:
| Arg | Field | Default |
|---|---|---|
| positional text | content |
required |
| — | title |
always generate a ≤ 60-char noun phrase |
--category X |
category |
auto-detected |
--importance N |
importance |
3 |
--project X |
project |
current project |
--tags t1,t2 |
tags |
— |
--save-context |
also write a project context item | off |
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.
- 5d ago Changed · -28 lines 6b7a9c9abc1f
- 1mo ago First seen · 161 lines · 41 tokens per session scan A 6024f08f8831
memory is a command published in the GitHub repository RohiRIK/OpenLtm (28 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 1,389 once invoked, about $0.0002 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 2026-08-30.
Other commands, from other repositories
help
Get help with EverMem plugin setup and available commands.
audit
Audit .flow/memory/ entries against the current codebase — Keep / Update / Consolidate / Replace / Delete / Harden per entry.
memory-migrate
Migrate legacy .flow/memory/{pitfalls,conventions,decisions}.md flat files into the categorized YAML schema — host agent classifies each entry directly.
prime
Prime context for fresh session: /prime [task hint] [--quick] [--verbose].
warden-select
Measure pending token-warden candidate rules for an agent on the golden suite, evict or activate them, and recompile the agent's memory.
update
Sync tasks and refresh memory from your current activity.