mnemosyne-lite SKILL.md skillA
mnemosyne-lite from juanmackie/mnemosyne-hermes is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add juanmackie/mnemosyne-hermes/mnemosyne-lite@git:20261006.217829ePins git:20261006.217829e in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- juanmackie/mnemosyne-hermes
- Path
skills/mnemosyne-lite/SKILL.md- Versions recorded
- 1
- Latest version
- git:20261006.217829e, committed Oct 6, 2026
- Size
- 2,756 bytes
- Repository stars
- 15
- License
- MIT
Search the local mnemosyne-lite SQLite store and get a few ranked, cited cards instead of reading raw tables. Use when the user asks about past memories ("have we seen this before", "what did we decide", "find notes about ..."), or before any recall call. Also use to create a store with init and summarise it with describe.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# mnemosyne-lite: search local memory without reading tables The `mnemosyne-lite` CLI answers questions from a local SQLite store. One `recall` returns a handful of ranked cards, each capped per card (default 500 chars, marked with `…`), however many memories exist. Prefer it to `list` without a query or dumping tables: those cost tokens in proportion to the store. ## First: learn the store ```bash mnemosyne-lite describe ``` This shows the memory count, per-namespace counts, the date range, and example calls. Run it once per session before searching. `recall --query` filters by words; `--namespace` scopes to one namespace (exact match). ## Search ```bash mnemosyne-lite recall --query "<words as the user said them>" mnemosyne-lite recall --query "<words>" --format cards mnemosyne-lite recall --query "<words>" --namespace <ns> --max-results 5 mnemosyne-lite list --limit 20 mnemosyne-lite describe ``` Add `--format json` for structured output, `--max-results` for more cards (max 100), and `--max-chars N` to cap card bodies. `list --format cards` renders the same capped cards without a `match:` line. ## Reading the output …
Read the whole file at its exact version.
How to install
mdr add juanmackie/mnemosyne-hermes/mnemosyne-lite@sha256:4763638e0039035fThe line at the top of this page pins the label git:20261006.217829e, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_wkpunxvflorkcfrs)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 6, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (2756 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
juanmackie/mnemosyne-hermes · 15 stars · license MIT · pushed 2026-11-01 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_wkpunxvflorkcfrs GET https://markdownregistry.com/api/v1/resolve?ref=juanmackie/mnemosyne-hermes/mnemosyne-lite GET https://markdownregistry.com/api/v1/blob/4763638e0039035fa9ec4b9ae735796eacfaf28ac542387a35eb5190d0426c1d
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.