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/monoes/monomindWrote 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/monoes/monomind/memory)<a href="https://agentmods.dev/commands/monoes/monomind/memory"><img src="https://agentmods.dev/badge/commands/monoes/monomind/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/monoes/monomind/memory"><img src="https://agentmods.dev/badge/commands/monoes/monomind/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 | $0.00025 | $0.01712 |
| Opus 5.5 | $0.00010 | $0.00685 |
| Sonnet 5.5 | $0.00005 | $0.00342 |
| Haiku 4.5 | $0.00003 | $0.00171 |
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 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Monomind Memory System
Persistent memory in local SQLite (sql.js/WASM when no native driver is available) with on-device embeddings for semantic search. Above 5,000 entries (MONOMIND_HNSW_THRESHOLD) search switches to an HNSW approximate-nearest-neighbour index; below it, brute-force cosine is faster. Supports cross-session and cross-agent collaboration.
Subcommands
| Subcommand | Alias | Description |
|---|---|---|
init |
— | Initialize the SQLite memory database |
store |
— | Store a key/value entry |
edit |
— | Edit an existing entry |
retrieve |
get |
Retrieve entry by key |
search |
— | Semantic/vector search |
list |
ls |
List memory entries |
delete |
rm |
Delete an entry |
templates |
— | Show best-practice entry templates |
stats |
— | Show memory statistics |
configure |
config |
Configure memory backend |
export |
— | Export memory to file |
import |
— | Import memory from file |
init — Initialize Database
npx monomind memory init
npx monomind memory init --backend sqlite --verbose --verify
npx monomind memory init --force # Overwrite existing
Flags: --backend hybrid|sqlite (default: hybrid; lancedb is accepted as a legacy alias for SQLite), --path, --force, --verbose, --verify (default: true), --load-embeddings
store — Store Data
# Store with specific namespace
npx monomind memory store --key "arch/api-design" --value "RESTful microservices" --namespace arch
# With tags and TTL
npx monomind memory store --key "pattern/auth" --value "JWT + refresh tokens" --namespace patterns --tags "auth,security" --ttl 86400
# Upsert (update if exists)
npx monomind memory store --key "bug/null-check" --value "Fixed null check in parser" --upsert
Flags:
| Flag | Short | Default | Description |
|---|---|---|---|
--key |
-k |
— | Storage key (required) |
--value |
— | — | Value to store (required) |
--namespace |
-n |
default |
Memory namespace |
--ttl |
— | — | Time to live in seconds |
--tags |
— | — | Comma-separated tags |
--vector |
— | false |
Store as vector embedding |
--upsert |
-u |
false |
Update if key exists |
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 · 200 lines · 25 tokens per session scan A abf0f40b6890
memory is a command published in the GitHub repository monoes/monomind (23 stars, last pushed yesterday), licensed Apache-2.0. It adds 25 tokens to every session and 1,712 once invoked, about $0.0001 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 2026-10-26.
Other commands, from other repositories
claude-flow-memory
Interact with Claude-Flow memory system.
sessions
Manage OpenAI Codex session history, aliases, and session metadata.
checkpoint
Create an identified recovery point and inspect exact restoration differences.
recall
Retrieve scoped lessons and evaluate their assumptions, conflicts, and applicability.
retro
Write this session's lessons into the project's lessons/ directory using the memory-discipline format.
save-session
Save current session state to a dated file in /.codex/session-data/ so work can be resumed in a future session with full context.