memorylayerSemantic memory for AI agents. 95% token savings with vector search.
Install via ClawdBot CLI:
clawdbot install khli01/memorylayerSemantic memory infrastructure for AI agents that actually scales.
Visit https://memorylayer.clawbot.hk and sign up with Google. You'll get:
# Option 1: Email/Password
export MEMORYLAYER_EMAIL=your@email.com
export MEMORYLAYER_PASSWORD=your_password
# Option 2: API Key (recommended for production)
export MEMORYLAYER_API_KEY=ml_your_api_key_herepip install memorylayer// In your Clawdbot agent
const memory = require('memorylayer');
// Store a memory
await memory.remember(
'User prefers dark mode UI',
{ type: 'semantic', importance: 0.8 }
);
// Search memories
const results = await memory.search('UI preferences');
console.log(results[0].content); // "User prefers dark mode UI"from plugins.memorylayer import memory
# Store
memory.remember(
"Boss prefers direct reporting with zero bullshit",
memory_type="semantic",
importance=0.9
)
# Search
results = memory.recall("What are Boss's preferences?")
for r in results:
print(f"{r.relevance_score:.2f}: {r.memory.content}")Before MemoryLayer:
# Inject entire memory files
context = open('MEMORY.md').read() # 10,500 tokens
prompt = f"{context}\n\nUser: What are my preferences?"After MemoryLayer:
# Inject only relevant memories
context = memory.get_context("user preferences", limit=5) # ~500 tokens
prompt = f"{context}\n\nUser: What are my preferences?"Result: 95% token reduction, $900/month savings at scale
memory.remember(content, options)Store a new memory.
Parameters:
content (string): Memory contentoptions.type (string): 'episodic' | 'semantic' | 'procedural'options.importance (number): 0.0 to 1.0options.metadata (object): Additional tags/dataReturns: Memory object with id
memory.search(query, limit)Search memories semantically.
Parameters:
query (string): Search query (natural language)limit (number): Max results (default: 10)Returns: Array of SearchResult objects
memory.get_context(query, limit)Get formatted context for prompt injection.
Parameters:
query (string): What context do you need?limit (number): Max memories (default: 5)Returns: Formatted string ready for prompt
memory.stats()Get usage statistics.
Returns: Object with total_memories, memory_types, operations_this_month
Episodic - Events and experiences
memory.remember('Deployed MemoryLayer on 2026-02-03', { type: 'episodic' });Semantic - Facts and knowledge
memory.remember('Boss prefers concise reports', { type: 'semantic' });Procedural - How-to and processes
memory.remember('To restart server: ssh root@... && systemctl restart...', { type: 'procedural' });memory.remember('User likes blue', {
type: 'semantic',
metadata: {
category: 'preferences',
subcategory: 'colors',
source: 'user_profile'
}
});const stats = await memory.stats();
console.log(`Total memories: ${stats.total_memories}`);
console.log(`Operations this month: ${stats.operations_this_month}`);
console.log(`Plan: ${stats.plan} (${stats.operations_limit}/month)`);FREE Plan (Current)
Pro Plan ($99/mo)
Enterprise (Custom)
Generated Mar 1, 2026
AI agents in customer support can use MemoryLayer to store and retrieve past interactions, preferences, and issue resolutions. This enables personalized responses without loading full conversation histories, reducing token usage and improving response times for handling complex queries.
Educational AI agents can leverage MemoryLayer to remember student progress, learning styles, and topic mastery. By semantically searching for relevant past lessons and feedback, the agent tailors explanations and recommendations, enhancing engagement while minimizing computational costs.
AI agents in healthcare applications can store patient histories, symptoms, and treatment outcomes using MemoryLayer. During consultations, the agent retrieves only pertinent memories to provide accurate triage advice, ensuring privacy and efficiency in medical decision-making.
AI agents in e-commerce platforms use MemoryLayer to track user preferences, purchase history, and browsing behavior. By retrieving semantically relevant memories, the agent generates personalized product recommendations, boosting sales while optimizing API usage and reducing latency.
AI agents in project management tools store task details, team preferences, and procedural knowledge with MemoryLayer. This allows quick recall of relevant information during planning and execution, improving collaboration and reducing the need for manual data lookup in large projects.
Offer a free tier with limited operations and storage to attract individual developers and small teams, then upsell to Pro and Enterprise plans for higher usage and support. This model drives adoption through accessibility while generating revenue from scaling businesses.
Charge based on API operations and storage consumption, with tiered pricing to cater to different user scales. This aligns costs with usage, appealing to startups and enterprises that need scalable, pay-as-you-go memory management for AI agents.
Provide custom enterprise solutions with self-hosted options, dedicated support, and SLAs for large organizations. This model targets industries with strict data privacy or high-volume needs, offering premium features and tailored integrations for a higher price point.
š¬ Integration Tip
Start by setting up environment variables for API keys to avoid hardcoding credentials, and use the free plan to test basic remember and search functions before scaling.
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