persistent-memory▌
ropl-btc/agent-skills · updated Apr 8, 2026
Use this skill as the single memory system for this repository.
Persistent Memory
Use this skill as the single memory system for this repository.
Commands
Use either command style:
python3 .agents/skills/persistent-memory/scripts/memory.py <command>.agents/skills/persistent-memory/scripts/pmem <command>
Supported commands:
initsync(database-only health check)cleanup-legacybackfill-embeddings --batch 500prune --source "<label>" [--older-than <days>]search "<query>" --limit 8add "<memory text>" --tags "<comma,tags>" --source "assistant"recent --limit 10stats
Required Workflow
- Initialize memory in a fresh workspace:
pmem init
- At the start of substantial tasks:
pmem sync(database-only health check)pmem search "<topic keywords>" --limit 8
- When user explicitly says
rememberor when a durable preference/fact is learned:
pmem add "<memory text>" --tags "<tags>" --source "assistant"
- Before finalizing memory-sensitive work, verify recall state:
pmem stats
One-Time Migration (If Upgrading From Older Setup)
- Remove legacy imported rows:
pmem cleanup-legacy
- Generate vectors for existing notes:
pmem backfill-embeddings
Storage Rules
- Store durable preferences, long-lived facts, stable workflows, and repeated constraints.
- Do not store noisy one-off transient details unless requested.
- Keep entries concise and specific.
- Prefer tags that improve retrieval quality (
preferences,calendar,comms,product).
Retrieval Rules
- Use targeted search queries instead of broad terms.
- Keep default
--limitlow unless deeper recall is needed. searchautomatically reinforces recalled entries by updatinghitsandlast_seen_at.hitsare analytics-oriented and not used as a direct ranking boost.- Search uses hybrid retrieval: lexical + semantic.
- Semantic search tries
sqlite-vecfirst and auto-falls back to Python cosine if needed.
Bootstrapping and Recovery
- If
.memory/is missing, runpmem init. pmem syncis a lightweight database-only check (no markdown import/export).- If semantic mode degrades, run
pmem statsto inspectsemantic_backendandembedding_coverage. - For command examples and quick troubleshooting, read
references/usage.md.
Discussion
Product Hunt–style comments (not star reviews)- No comments yet — start the thread.
Ratings
4.7★★★★★36 reviews- ★★★★★Daniel Dixit· Dec 24, 2024
Useful defaults in persistent-memory — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
- ★★★★★Aarav Torres· Dec 16, 2024
I recommend persistent-memory for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
- ★★★★★Dhruvi Jain· Dec 12, 2024
persistent-memory fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
- ★★★★★Ishan Brown· Nov 15, 2024
persistent-memory has been reliable in day-to-day use. Documentation quality is above average for community skills.
- ★★★★★Mei Bansal· Nov 11, 2024
Registry listing for persistent-memory matched our evaluation — installs cleanly and behaves as described in the markdown.
- ★★★★★Aarav Reddy· Nov 7, 2024
Solid pick for teams standardizing on skills: persistent-memory is focused, and the summary matches what you get after install.
- ★★★★★Oshnikdeep· Nov 3, 2024
persistent-memory is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
- ★★★★★Naina Ghosh· Oct 26, 2024
persistent-memory has been reliable in day-to-day use. Documentation quality is above average for community skills.
- ★★★★★Ganesh Mohane· Oct 22, 2024
Keeps context tight: persistent-memory is the kind of skill you can hand to a new teammate without a long onboarding doc.
- ★★★★★Hassan Mehta· Oct 6, 2024
Solid pick for teams standardizing on skills: persistent-memory is focused, and the summary matches what you get after install.
showing 1-10 of 36