memory-proEfficient semantic search engine for OpenClaw workspace memory using FAISS and Sentence-Transformers, indexing Markdown and key agent files.
Install via ClawdBot CLI:
clawdbot install royhk920/memory-proA highly efficient semantic search engine for your OpenClaw workspace memory, powered by FAISS and Sentence-Transformers.
This skill indexes Markdown files and key agent files (e.g. MEMORY.md, SOUL.md) to provide meaning-based context retrieval instead of exact keyword matching.
This skill can be installed on any OpenClaw host.
# Clone or copy the folder
cd memory-pro-export
chmod +x install.sh
./install.shThe installation script will:
~/.openclaw/skills/memory-prouvsystemd user service (memory-pro.service)sentence-transformers (all-MiniLM-L6-v2)~/.openclaw/workspace/memory/ and MEMORY.md, SOUL.md, etc.)Use the client script to query the running service.
# Basic search
python ~/.openclaw/skills/memory-pro/scripts/search.py "What did I do yesterday?"
# JSON output (for better tool parsing)
python ~/.openclaw/skills/memory-pro/scripts/search.py "project updates" --jsonThe index is automatically rebuilt when the background service restarts. If you need to force an immediate update:
systemctl --user restart memory-pro.service(Note: Service restart takes ~15-20 seconds to rebuild index and load models. The client script has auto-retry logic.)
The service behavior can be customized by editing ~/.config/systemd/user/memory-pro.service:
MEMORY_PRO_WORKSPACE_DIR: The root of your workspace (e.g., ~/.openclaw/workspace/)MEMORY_PRO_DATA_DIR: Directory containing .md files to index.MEMORY_PRO_CORE_FILES: Comma-separated list of core files to always index.MEMORY_PRO_PORT: The port for the API (default 8001).systemctl --user status memory-pro.servicekill $(lsof -t -i:8001) then restart service.Generated Mar 1, 2026
Freelancers can use Memory Pro to index project notes, client briefs, and personal reflections stored in Markdown files. This enables quick semantic search to recall past decisions, project details, or creative ideas without manual tagging, improving productivity and client responsiveness.
Researchers and students can index academic notes, literature reviews, and thesis drafts as Markdown files. The semantic search helps retrieve relevant concepts or references across documents, aiding in literature synthesis and avoiding redundant work during writing phases.
Software development teams can index technical documentation, code comments, and meeting notes in Markdown format. Memory Pro allows developers to quickly find solutions or historical context based on meaning, reducing time spent digging through files and improving onboarding for new team members.
Content creators and bloggers can index article drafts, research notes, and editorial calendars stored as Markdown files. Semantic search helps retrieve past ideas or related content for inspiration, streamlining the writing process and ensuring consistency across publications.
Offer Memory Pro as a cloud-hosted service with tiered subscriptions based on storage limits, search frequency, and team size. Revenue comes from monthly or annual fees, targeting small to medium businesses needing efficient knowledge retrieval without self-hosting.
Sell on-premise licenses to large organizations requiring data privacy and customization. Include premium support, custom integrations, and training services. Revenue is generated through one-time license fees and ongoing maintenance contracts.
Provide a free version with basic indexing and search capabilities for individual users, while charging for advanced features like API access, priority support, and enhanced analytics. This model attracts a broad user base and converts power users to paid plans.
💬 Integration Tip
Ensure the background service is running via systemd before querying, and configure environment variables to match your workspace structure for optimal indexing.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection