skills.rest
Psqasim
PsqasimCOMMUNITY
Explore all skills by this author →
Website𝕏@psqasim0GitHub

agent-memory

Manage AI agent memory across sessions with LangChain-compatible vector stores.

1|1|Updated Feb 10, 2026
Search Tags:#langchain#pgvector#agent-memory#memory-management#retrieval-augmented-generation#vector-store#chromadb
One-click install
npx skills add https://github.com/Psqasim/personal-ai-employee --skill agent-memory-psqasim
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-memory
Source: https://github.com/Psqasim/personal-ai-employee/tree/main/.claude/skills/agent-memory
Command: npx skills add https://github.com/Psqasim/personal-ai-employee --skill agent-memory-psqasim

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Memory management for AI agents enabling short-term conversation memory and long-term persistence to support context continuity and retrieval-augmented reasoning.

Core Features & Use Cases

  • Short-term memory: in-session chat history
  • Long-term memory: persistent vector stores (pgvector with PostgreSQL, or ChromaDB) for cross-session recall
  • LangGraph cross-thread memory and memory design patterns to orchestrate memory layers

Quick Start

Configure an AI agent to automatically store and retrieve both short-term and long-term memories using your configured vector store.

Frequently Asked Questions about agent-memory

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

FAQPage Schema
How do I persist chat history for AI agents across sessions?▼

You can persist chat history across sessions by implementing memory management that stores context in vector stores like pgvector or ChromaDB. This enables cross-session recall and retrieval-augmented reasoning for personalized interactions.

What is the difference between short-term and long-term memory in LangChain agents?▼

Short-term memory handles in-session chat history, while long-term memory uses persistent vector stores for cross-session recall. LangGraph cross-thread memory orchestrates these layers to maintain context continuity and retrieval-augmented reasoning.

Can I use ChromaDB and pgvector for retrieval-augmented generation memory?▼

Yes, both ChromaDB and pgvector with PostgreSQL are supported backends for retrieval-augmented memory usage. They store persistent memory that AI agents can retrieve to maintain context continuity across different sessions.

How do I isolate memory data by user or session in AI agents?▼

Memory data isolation by user and session is handled through specific memory design patterns. These patterns ensure safe data handling while orchestrating memory layers for both short-term conversation history and long-term persistence.

Do I need LangChain to manage cross-thread memory for AI agents?▼

LangChain-compatible backends are required to implement LangGraph cross-thread memory and orchestrate memory layers. This setup supports both short-term in-session chat history and long-term persistent vector store recall.

Related Skills

Explore More Software Engineering Skills→
samelhousseinisamelhousseini

postgres-ai

Automate vector search, RAG, and memory in Azure PostgreSQL with pgvector and azure_ai.

Community
Advanced
ChegginCheggin
1

convex-agents

Create persistent, stateful AI agents with thread management and tool integration.

Community
Advanced
abzhawabzhaw

agent-memory-systems

Coordinate in-context, working, long-term, and episodic memory systems for LLM agents.

Community
Advanced
FlexNetOSFlexNetOS

plan-memory-vector-intelligence

Integrate persistent memory and vector intelligence for comprehensive planning.

Official
Advanced