skills.rest
zach-source
zach-sourceCOMMUNITY
Explore all skills by this author →
GitHub

graphiti

Store and retrieve persistent AI memory in a FalkorDB temporal knowledge graph.

Updated Feb 18, 2026
Search Tags:#debugging#context management#problem solving#knowledge graph#ai memory#persistence
One-click install
npx skills add https://github.com/zach-source/claude-plugins --skill graphiti-zach-source
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: graphiti
Source: https://github.com/zach-source/claude-plugins/tree/main/plugins/ai-memory/skills/graphiti
Command: npx skills add https://github.com/zach-source/claude-plugins --skill graphiti-zach-source

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires httpx, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a persistent memory system for AI interactions, allowing it to recall past conversations, project context, and learned solutions, thereby improving consistency and efficiency across sessions.

Core Features & Use Cases

  • Temporal Knowledge Graph: Stores information as a graph of entities and their relationships, enabling complex queries and pattern recognition.
  • Context Management: Loads project context at session start, stores learnings from problem-solving, and persists session summaries.
  • Proactive Memory: Automatically stores insights from failure-to-success debugging, infrastructure discoveries, and tool configurations.
  • Use Case: When debugging a complex issue that took several hours, Graphiti can store the root cause, the solution, and the steps taken. In future sessions, if a similar issue arises, the AI can recall this stored knowledge, saving significant debugging time.

Quick Start

Use the graphiti skill to search for project context related to 'nix-dotfiles architecture'.

Frequently Asked Questions about graphiti

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

FAQPage Schema
How do I maintain persistent AI memory across different sessions?▼

To maintain persistent AI memory, you can use a temporal knowledge graph backed by FalkorDB. This stores project context, solutions, and user preferences, allowing the AI to recall past interactions and improve consistency across sessions.

What is the best way to store debugging solutions for future AI recall?▼

The best way to store debugging solutions is using proactive memory patterns that save root causes and steps taken from failure-to-success scenarios. This allows the AI to automatically recall the stored knowledge if a similar issue arises later.

Can I manage project context and architectural decisions using a knowledge graph?▼

Yes, you can manage project context and architectural decisions by storing them as a graph of entities and relationships. This enables complex queries and pattern recognition for structured data storage.

How do I search for specific project context stored in AI memory?▼

You can search for specific project context using dedicated search tools like `search_nodes` and `get_episodes`. These tools query the temporal knowledge graph to retrieve relevant historical information and session summaries.

Does persistent AI memory work with FalkorDB for context management?▼

Yes, persistent AI memory works directly with FalkorDB to manage context. It loads project context at session start and persists session summaries, ensuring infrastructure discoveries and tool configurations are retained.

Related Skills

Explore More Software Engineering Skills→
FalkorDBFalkorDB
22

falkordb-skills

Provide FalkorDB guidance for Cypher queries, Docker deployment, and data migration.

Official
Advanced
zyj18860969891-bytezyj18860969891-byte

session-logs

Search JSONL session logs by keyword and summarize matching user/assistant messages with metadata.

Community
Intermediate
Shakudo-ioShakudo-io

graphiti-memory

Search and record institutional knowledge in Graphiti memory graphs.

Official
Intermediate
ehfazrezwanehfazrezwan
5

search

Retrieve relevant stored memories using hybrid vector and temporal knowledge graph search.

Community
Advanced