hybrid-memoryHybrid memory strategy combining OpenClaw's built-in vector memory with Graphiti temporal knowledge graph. Use when you need to recall past context, answer temporal questions ("when did X happen?"), or search memory files. Provides decision framework for when to use memory_search vs Graphiti.
Install via ClawdBot CLI:
clawdbot install clawdbrunner/hybrid-memoryGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/clawdbrunner/openclaw-graphiti-memoryAudited Apr 17, 2026 · audit v1.0
Generated Mar 1, 2026
Agents use Graphiti to recall past customer interactions and issue timelines, while memory_search retrieves internal documentation like troubleshooting guides. This ensures accurate, context-aware responses by combining temporal conversation history with static knowledge bases.
Legal professionals leverage Graphiti to track case timelines and entity relationships, such as witness statements over time, and use memory_search to access curated legal precedents and case files. This hybrid approach streamlines evidence retrieval and chronological analysis for litigation.
Medical staff employ Graphiti to monitor patient treatment histories and symptom progression, while memory_search pulls up clinical guidelines and research papers. This supports informed decision-making by integrating temporal health data with up-to-date medical protocols.
Project managers use Graphiti to log meeting discussions and milestone changes over time, and memory_search to access project documentation like GOALS.md. This facilitates effective retrospectives and planning by combining temporal insights with static project artifacts.
Offer the hybrid memory system as a cloud-based service with tiered subscriptions based on usage and storage. Revenue is generated through monthly fees, with premium tiers including advanced analytics and integration support for enterprise clients.
Provide tailored implementation and training services to organizations adopting the hybrid memory system. Revenue comes from project-based fees for setup, customization, and ongoing maintenance, targeting industries with complex data needs like legal or healthcare.
Deploy a free version with basic memory_search and Graphiti capabilities, monetizing through paid upgrades for advanced features like increased storage, priority support, and automated sync daemons. This model attracts individual users and small teams before upselling.
💬 Integration Tip
Start by configuring OpenClaw's memory with a reliable embedding provider like Gemini, then deploy Graphiti's Docker stack to handle temporal data before syncing both systems for seamless hybrid recall.
Scored Apr 19, 2026
Search and analyze your own session logs (older/parent conversations) using jq.
Maintain Clawdbot's compounding knowledge graph under life/areas/** by adding/superseding atomic facts (items.json), regenerating entity summaries (summary.md), and keeping IDs consistent. Use when you need deterministic updates to the knowledge graph rather than manual JSON edits.
Manage and retrieve long-term memories with LanceDB using semantic vector search, category filtering, and detailed metadata storage.
Fast semantic memory system with JSON indexing, auto-consolidation, and <20ms search. Capture learnings, decisions, insights, events. Use when you need persistent memory across sessions or want to recall prior work/decisions.
Search and retrieve relevant information from your indexed memory files using semantic queries and direct file reads for context.
Fast semantic search for AI agent memory files using TF-IDF and SQLite. Enables instant context retrieval from MEMORY.md or any markdown documentation. Use when the agent needs to (1) Find relevant context before starting a task, (2) Search through large memory files efficiently, (3) Retrieve specific rules or decisions without reading entire files, (4) Enable semantic similarity search instead of keyword matching. Lightweight alternative to heavy embedding models - zero external dependencies, <10ms search time.