10 actions in 10 pieces of software · ranked by words, meaning and measured trust · 700 ms
skillsupermemoryai/supermemoryrecord
- supermemory
Supermemory is a state-of-the-art memory and context infrastructure for AI agents. Use this skill when building applications that need persistent memory, user personalization, long-term context retention, or semantic search across knowledge bases. It provides Memory API for learned user context, Use
- supermemory
- 2hmem — Humanlike Memory for AI Agentsfound in code, not yet checkedno passport yet
- load_project
Load a project and activate it. Returns L2 content + L3 titles — the perfect project briefing.
- load_project
- 3purrfect-agentdemo or tutorialno passport yet
MCP serverpieverse-eng/purrfect-agent
- memory
Read or write a named memory key to persistent storage.
- memory
- 4Memory Palacefound in code, not yet checkedno passport yet
MCP serverjeffpierce/memory-palace
- memory_recall
skillrobin-liquidium/agent-skillsrecord
- persistent-memory
ALWAYS USE THIS SKILL when handling persistent memory in this workspace, including task-start memory recall, explicit "remember" instructions, storing durable preferences/facts, and retrieving prior context. This skill owns the local memory workflow and CLI for init/sync/search/add/recent/stats.
- persistent-memory
- 6personal-ai-memoryfound in code, not yet checkedno passport yet
- get_memory
Read one memory when its complete key is known.
- get_memory
- 7Perfectfound in code, not yet checkedno passport yet
- browser_evaluate
Guarded JS evaluate (disabled patterns: cookies/storage). Prefer snapshot/extract/click/fill.
- browser_evaluate
APInucleoid/total-recallrecord
- storeMemory
Store or reuse a near-duplicate memory
- storeMemory
- 9pi-memoryfound in code, not yet checkedno passport yet
MCP servergauravsharmacode/pi-memory
- memory_promote
Promote frequently-recalled daily-log snippets to MEMORY.md for permanent retention.
- memory_promote
- 10Mnemo - Persistent AI Memoryfound in code, not yet checkedno passport yet
- update_memory
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.