skills.rest
Dexploarer
DexploarerCOMMUNITY
Explore all skills by this author →
Website𝕏@dEXploarerGitHub

memory-manager

Manage ElizaOS agent memory with pruning and semantic search.

7|2|Updated Nov 9, 2025
Search Tags:#performance#semantic search#embeddings#AI agent#memory management#context window#ElizaOS#pruning
One-click install
npx skills add https://github.com/Dexploarer/hyper-forge --skill memory-manager-dexploarer
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: memory-manager
Source: https://github.com/Dexploarer/hyper-forge/tree/main/.claude/skills/memory-manager
Command: npx skills add https://github.com/Dexploarer/hyper-forge --skill memory-manager-dexploarer

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill optimizes ElizaOS agent memory usage, implements pruning strategies, and effectively manages conversation context. It prevents context window overflow, improves agent performance, and ensures relevant information is retained for better responses.

Core Features & Use Cases

  • Memory Pruning: Implements time-based and size-based pruning to remove old or less important memories.
  • Context Window Management: Helps agents stay within LLM context limits by prioritizing and consolidating important memories.
  • Semantic Search: Utilizes embeddings for efficient retrieval of relevant memories.
  • Use Case: If your ElizaOS agent is experiencing context window limitations or slow responses, use this skill to "manage agent memory." It will help configure pruning strategies, importance scoring, and semantic search to optimize memory usage.

Quick Start

Optimize the memory usage for my ElizaOS agent by implementing time-based pruning.

Frequently Asked Questions about memory-manager

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

FAQPage Schema
How do I prevent my ElizaOS agent from running out of context window?▼

Context window overflow occurs when conversation history exceeds LLM limits. Memory management with pruning strategies removes old or less important memories, consolidates relevant information, and keeps your agent within token constraints while maintaining response quality.

What's the best way to implement memory pruning for an AI agent?▼

Memory pruning uses time-based and size-based strategies to automatically remove outdated or low-importance memories. Configure pruning policies with importance scoring and archiving to retain critical context while freeing space for new conversations.

How does semantic search with embeddings improve agent memory retrieval?▼

Semantic search uses embeddings to find contextually relevant memories beyond keyword matching. This enables agents to retrieve the most pertinent information from long conversation histories, improving response accuracy and reducing unnecessary context processing.

Can I use memory decay modeling to deprioritize old agent conversations?▼

Memory decay modeling automatically reduces the importance of older memories over time while preserving critical information. Combined with archiving workflows, it balances retention of historical context with fresh, relevant memory allocation for ongoing conversations.

Does ElizaOS agent memory management support configurable conversation length limits?▼

Yes. This Skill supports configurable conversationLength limits with CRUD memory operations, importance scoring, and semantic search. You can define thresholds that trigger pruning and archiving to maintain optimal memory usage across sessions.

What happens when I apply time-based pruning to agent memory?▼

Time-based pruning automatically removes memories older than a specified threshold, with optional importance weighting to preserve critical long-term context. This prevents unbounded memory growth while archiving older sessions for later retrieval if needed.

Related Skills

Explore More Software Engineering Skills→
nirholasnirholas
71

embeddings

Create and manage vector embeddings for semantic search across multiple providers.

Community
Advanced
sfc-gh-miwhitakersfc-gh-miwhitaker
3

tool-cortex-code-costs

Monitor and analyze Cortex Code usage costs with a Snowsight dashboard.

Community
Advanced
Nutopia13Nutopia13

context-optimizer

Prune and archive conversation history to manage 64k-context overflow.

Community
Advanced
JeremyKuhneJeremyKuhne
9

scratch-buffer-strategy

Identify optimal scratch-buffer strategies for hot-path .NET code.

Community
Intermediate