memory-ui
Skill3 starsChanged 10 days agoMITView on GitHub
Launch the Mnemosyne browser UI to inspect stored memory.
- Installs packages
In this repository20 other files it gives its agents.
- AGENTS.mdAGENTS.md
- covidence-full-text-reviewSkill
- covidence-full-text-retrievalSkill
- covidence-screeningSkill
- impeccableSkill
- ilearning-autoadvanceSkill
- oh-my-piSkill
- auditing-worktreesSkill
- camofox-browserSkill
- demo-runbookSkill
- hermes-deepseek-cacheSkill
- i-have-adhdSkill
- multi-repo-pr-review-merge-roundSkill
- oh-my-ghosttySkill
- tldrSkill
- writing-reportsSkill
- sci-hub-accessSkill
- slack-mention-watchSkill
- slack-scanSkill
- superpowers-using-superpowersSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 28
Prefer a Hermes-tracked background process over nohup/disown:
- Distinctive: line 70
If it was started as a tracked process, kill that session.
- Very specific: line 74
Only use mnemosyne-browser through the venv PATH.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Mnemosyne UI / Browser Dashboard
Mnemosyne ships a read-only local web dashboard (mnemosyne-browser) for viewing memory. It binds to 127.0.0.1 (loopback only) and opens the SQLite DB read-only — use the CLI for any write/management action.
Environment
Mnemosyne is installed into the Hermes runtime venv. That venv's path changes when hermes update moves the runtime, so look it up each time instead of hardcoding it:
MNEMO_VENV=$(hermes --run-module site 2>/dev/null | grep -o "/[^']*/venv/lib" | head -1 | sed 's#/lib$##')
export PATH="$MNEMO_VENV/bin:$PATH"Key paths:
- Venv:
$MNEMO_VENV(currently under~/.hermes/installs/.../venv; the old~/.hermes/hermes-agent/venvis stale) - DB:
~/.hermes/mnemosyne/data/mnemosyne.db(fully local, no cloud) - Plugin:
~/.hermes/plugins/mnemosyne(symlink) - Provider:
memory.provider = mnemosyne(already active)
Start the browser UI (background process)
Prefer a Hermes-tracked background process over nohup/disown:
export PATH="$MNEMO_VENV/bin:$PATH" # MNEMO_VENV from the Environment section
mnemosyne-browser --port 8081 # run via terminal(background=true)Then verify readiness before reporting success:
curl -s http://127.0.0.1:8081/api/stats # expect {"tiers": {...}, "total": N}Open http://127.0.0.1:8081 in the browser (default browser is Brave, profile 'brave-live').
Read-only UI actions
The dashboard supports browse, search, tier/source filtering, sort, and per-memory detail via endpoints:
GET /— HTML pageGET /api/stats— tier countsGET /api/search?q=&src=&tier=&sort=&limit=&offset=— JSON resultsGET /detail/<memory_id>— single-memory detail
Write/management actions are CLI (NOT the UI)
The browser is read-only. For writes use the CLI:
export PATH="$MNEMO_VENV/bin:$PATH" # MNEMO_VENV from the Environment section
mnemosyne store "content" [source] [importance] # add
mnemosyne recall "<query>" [top_k] # search
mnemosyne update <id> "<content>" [importance] # update
mnemosyne delete <id> # remove
mnemosyne stats # totals
mnemosyne sleep # consolidation
mnemosyne export <file.json> # portable backup (push to cloud only when user chooses)
mnemosyne backup <dir> / restore <backup.db.gz> # compressed snapshots
mnemosyne sync ... # encrypted remote sync to a server YOU runStop the server
If it was started as a tracked process, kill that session. The loopback server is safe to leave running, but stop it when the user is done to avoid a stray process.
Gotchas
- Only use
mnemosyne-browserthrough the venv PATH; the baremnemosyne-browsermay not resolve outside it. - macOS
greplacks-P; find memory IDs withmnemosyne recall "<q>" 10 | grep "ID:"instead. - Requires
fastapi+uvicorn(both already installed in the Hermes venv). hermes memory statussays "not available" / tools return "Mnemosyne not initialized" after ahermes update: the new runtime venv is missing the packages. Fix:uv pip install --python "$MNEMO_VENV/bin/python" mnemosyne-memory==<previous version> sqlite-vec fastembed, then start a new session.- New session / gateway restart is required for
mnemosyne_*provider tools to appear in an already-running session. - The bundled
mnemosyne-memory-overrideskill handles memory ROUTING; this skill handles the VISUAL UI + CLI management.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

