Skip to content
TakoAPI
Back to skills

graphiti

by emasoudy

Personal Development
2.1kDownloads reported by clawskills.sh
2Stars
0Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Knowledge graph operations via Graphiti API.

Description

What This Skill Does

Provides knowledge graph operations through Graphiti's REST API. Supports searching stored facts, adding new episodes or memories, and managing entities and relationships in a graph database backed by Neo4j and Qdrant.

Combines graph-based relationship traversal with vector search, enabling semantic queries that return structured facts rather than raw text chunks.

When to Use It

  • Searching past project notes stored as graph facts
  • Recording meeting summaries as new knowledge episodes
  • Querying relationships between people and projects
  • Persisting AI conversation memory across sessions
  • Retrieving context about a specific topic from accumulated knowledge

Example Workflow

INPUT

User asks: What do we know about the Phase 1 integration?

AGENT
  1. 1

    Resolve Graphiti service URL via config, env var, or localhost default

  2. 2

    POST query to /facts/search with the relevant search terms

  3. 3

    Receive ranked fact results from the knowledge graph

  4. 4

    Return structured facts to the user

OUTPUT

A list of relevant stored facts about Phase 1 integration, including relationships and entities extracted at ingestion time

Requirements

  • Neo4j database instance
  • Qdrant vector search instance
  • Graphiti service running and accessible

Installation

clawhub install emasoudy/graphiti

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links