graphitiKnowledge graph operations via Graphiti API. Search facts, add episodes, and extract entities/relationships.
Install via ClawdBot CLI:
clawdbot install emasoudy/graphitiInstall Graphiti stack (Docker):
Install Graphiti stack (Docker)Query and manage your knowledge graph using Graphiti's REST API with dynamic service discovery.
Search the knowledge graph for relevant facts.
Usage:
bash command:"
GRAPHITI_URL=\$({baseDir}/references/env-check.sh)
curl -s -X POST \"\$GRAPHITI_URL/facts/search\" \
-H 'Content-Type: application/json' \
-d '{\"query\": \"YOUR_QUERY\", \"max_facts\": 10}' | jq .
"Add a new episode/memory to the knowledge graph.
Usage:
bash command:"
GRAPHITI_URL=\$({baseDir}/references/env-check.sh)
curl -s -X POST \"\$GRAPHITI_URL/messages\" \
-H 'Content-Type: application/json' \
-d '{\"name\": \"EPISODE_NAME\", \"content\": \"EPISODE_CONTENT\"}' | jq .
"The skill uses environment discovery to find Graphiti automatically:
clawdbot config get skills.graphiti.baseUrl$GRAPHITI_URLhttp://localhost:8001To change the Graphiti URL:
export GRAPHITI_URL="http://10.0.0.10:8001"
# OR
clawdbot config set skills.graphiti.baseUrl "http://10.0.0.10:8001"Search for information:
bash command:"
GRAPHITI_URL=\$({baseDir}/references/env-check.sh)
curl -s -X POST \"\$GRAPHITI_URL/facts/search\" \
-H 'Content-Type: application/json' \
-d '{\"query\": \"Tell me about Essam Masoudy\", \"max_facts\": 5}'
"Add a memory:
bash command:"
GRAPHITI_URL=\$({baseDir}/references/env-check.sh)
curl -s -X POST \"\$GRAPHITI_URL/messages\" \
-H 'Content-Type: application/json' \
-d '{\"name\": \"Project Update\", \"content\": \"Completed Phase 1 of Clawdbot integration\"}'
"Generated Mar 1, 2026
A hospital uses Graphiti to search and link patient symptoms, treatments, and outcomes across medical records stored in Neo4j. This enables doctors to quickly find similar cases and identify effective interventions, improving diagnosis accuracy and personalized care.
A bank employs Graphiti to add transaction episodes and search for suspicious patterns in a knowledge graph, integrating with Qdrant for vector-based anomaly detection. This helps analysts uncover complex fraud networks and reduce false positives in real-time monitoring.
A logistics company uses Graphiti to manage shipment data as episodes, searching for bottlenecks and relationships between suppliers, routes, and delays. This supports dynamic rerouting and predictive analytics to enhance efficiency and reduce costs.
A university research team leverages Graphiti to add project updates and search for interdisciplinary connections across publications and datasets. This facilitates knowledge discovery and collaboration by mapping expertise and findings in a structured graph.
A tech company integrates Graphiti to search for relevant solutions and add new support tickets as episodes, linking issues to resolutions in a Neo4j graph. This speeds up response times and improves self-service options through intelligent fact retrieval.
Offer Graphiti as a cloud-based service with tiered pricing based on usage, such as API calls and graph size. This model provides recurring revenue and scalability for clients in industries like healthcare and finance, with add-ons for advanced analytics.
Sell on-premise licenses for large organizations needing full control over their Neo4j and Qdrant integrations. This includes customization, support, and training packages, generating high-value contracts with upfront and maintenance revenue.
Provide professional services to help clients deploy and optimize Graphiti for specific use cases, such as fraud detection or supply chain management. This model leverages expertise to drive implementation projects and ongoing optimization contracts.
💬 Integration Tip
Ensure Neo4j and Qdrant services are properly configured and accessible before deploying Graphiti, and use the dynamic configuration options to manage URLs across environments for seamless operation.
Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.
Manage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks Clawdbot to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.
Local search/indexing CLI (BM25 + vectors + rerank) with MCP mode.
Use when designing database schemas, writing migrations, optimizing SQL queries, fixing N+1 problems, creating indexes, setting up PostgreSQL, configuring EF Core, implementing caching, partitioning tables, or any database performance question.
Connect to Supabase for database operations, vector search, and storage. Use for storing data, running SQL queries, similarity search with pgvector, and managing tables. Triggers on requests involving databases, vector stores, embeddings, or Supabase specifically.
Query, design, migrate, and optimize SQL databases. Use when working with SQLite, PostgreSQL, or MySQL — schema design, writing queries, creating migrations, indexing, backup/restore, and debugging slow queries. No ORMs required.