claw-memory-liteManage and query your agent's distilled long-term memory with lightweight, fast SQLite-powered tools and automated daily extraction.
Install via ClawdBot CLI:
clawdbot install timothysong0w0/claw-memory-liteGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
post → https://x.com/atlasforgeai/status/2026380335249002843Potentially destructive shell commands in tool definitions
eval (Calls external URL not in known-safe list
https://github.com/timothysong0w0/claw-memory-lite/issuesUses known external API (expected, informational)
raw.githubusercontent.comGenerated Mar 22, 2026
An AI agent helps users manage daily tasks and reflections by automatically extracting key insights from their activity logs. This enables users to query past decisions and patterns to improve personal efficiency and goal tracking over time.
A support agent uses the skill to store and retrieve insights from past customer interactions logged daily. This allows for quick access to resolved issues and common queries, enhancing response accuracy and reducing resolution times.
Researchers employ the skill to distill findings from daily experiment logs into a queryable database. It facilitates easy retrieval of trends and results, supporting data analysis and report generation without manual sorting.
Project teams integrate the skill to capture daily progress notes and extract actionable insights. This helps in monitoring milestones, identifying bottlenecks, and improving project planning through historical data queries.
A health-focused agent logs daily wellness activities and uses the skill to extract patterns from these records. Users can query past health metrics to track progress and make informed lifestyle adjustments.
Offer the skill as part of a subscription-based AI agent platform, providing regular updates and premium features like advanced analytics. Revenue is generated through monthly or annual fees from individual users and small teams.
License the skill to large organizations for integration into their internal AI systems, with customization and support services. Revenue comes from one-time licensing fees and ongoing maintenance contracts tailored to business needs.
Provide a basic version of the skill for free to attract users, with paid tiers unlocking additional capabilities such as larger databases or automated scheduling. Revenue is driven by upgrades and in-app purchases for enhanced functionality.
💬 Integration Tip
Ensure the OpenClaw agent is properly set up and add the automation script to HEARTBEAT.md for seamless daily memory extraction without manual intervention.
Scored Jun 19, 2026
Audited Apr 17, 2026 · audit v1.0
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.