skills.rest
Bumblebiber
BumblebiberCOMMUNITY
Explore all skills by this author →
GitHub

hmem-read

Load long-term memory from hmem using read_memory() or load_project().

23|5|Updated Feb 19, 2026
Search Tags:#context#mcp#memory#read_memory#load_project#o-entries
One-click install
npx skills add https://github.com/Bumblebiber/hmem --skill hmem-read
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: hmem-read
Source: https://github.com/Bumblebiber/hmem/tree/main/skills/hmem-read
Command: npx skills add https://github.com/Bumblebiber/hmem --skill hmem-read

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Load long-term memory from hmem to restore prior context across sessions, so agents remember past decisions, projects, and conversations without re-reading everything.

Core Features & Use Cases

  • Immediate memory restoration via read_memory() or load_project(), bringing full project briefing and recent exchanges into context.
  • Supports targeted queries (search, context_for, memory_health, memory_stats) to surface relevant knowledge quickly.
  • Works across multiple projects and sessions, maintaining continuity when switching devices or sessions.

Quick Start

Invoke the read_memory command or load_project with a project identifier to restore prior context.

Frequently Asked Questions about hmem-read

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I restore long-term memory context for an AI agent across sessions?▼

To restore long-term memory context across sessions, load prior project briefings and recent exchanges by invoking read_memory() or load_project() with a project identifier. This brings full historical context into the current session without re-reading past conversations.

What is the best way to search past AI agent decisions without re-reading the entire chat history?▼

Searching past agent decisions is best handled by using targeted memory queries like search and context_for. These functions surface relevant historical knowledge from the memory server quickly, bypassing the need to reload full chat histories.

Does this memory loading approach work when resuming work on a specific project after a context reset?▼

Yes, memory loading works specifically for context resets and resuming work on specific projects. It enforces using load_project() to restore the exact prior project briefing and recent exchanges, maintaining continuity even after a session reset.

Can I check the status and health of my MCP server memory storage?▼

You can check memory storage status by running the memory_health and memory_stats queries. These functions integrate with the MCP server to report on the current state, capacity, and integrity of your stored long-term memory entries.

How do I retrieve prior context when there are no L1 summaries available?▼

To retrieve prior context without L1 summaries, use the read_memory() command to load long-term memory directly. This restores past decisions and project context from lower-level memory entries when summary layers are missing.

Related Skills

Explore More Software Engineering Skills→
pacphipacphi
6

AgentDB Memory Patterns

Provide persistent session and long-term memory for AI agents via AgentDB.

Community
Advanced
MOODMNKY-LLCMOODMNKY-LLC

session-logs

Search and analyze historical JSONL session logs with ripgrep and jq.

Community
Intermediate
OmarTheGreyOmarTheGrey
1

mcp-server-enhancement

Extends MCP servers with Pydantic-validated tools while maintaining stdio safety.

Community
Advanced
kyopark2014kyopark2014
4

memory-manager

Stores and retrieves agent memory via Markdown files and semantic search.

Community
Intermediate