S
Supermemory
Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.
open-sourcememory-knowledge
31.0k
Stars
+2587
Stars/month
182
Commits (90d)
10
Releases (6m)
Star Growth
+7.8k (33.3%)estimated from velocity
Overview
Supermemory is a state-of-the-art memory and context layer that extracts facts from conversations, maintains user profiles, and handles knowledge updates and contradictions. It provides hybrid search combining RAG and memory, supports connectors for various services, and can be run fully locally with one binary.
Deep Analysis
Key Differentiator
Claims #1 performance on three major AI memory benchmarks with 95% recall and 99.4% context reduction.
⚡ Capabilities
- • Memory extraction from conversations
- • User profile maintenance
- • Hybrid search (RAG + memory)
- • Multi-modal content processing
- • Automatic forgetting of expired information
🔗 Integrations
Google DriveGmailNotionOneDriveGitHubMCP serverOllama
✓ Best For
- ✓ Adding persistent memory to AI agents
- ✓ Building AI products with memory capabilities
- ✓ Running memory systems locally
✗ Not Ideal For
- ✗ End-user AI applications
- ✗ Generic chatbots for customers
- ✗ Standalone content generation
⚠ Known Limitations
- ⚠ Requires integration into existing AI systems
- ⚠ Primarily focused on memory/context layer
Alternatives
M
Mem0
Universal memory layer for AI Agents
M
MemOS
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harne
M
Memary
The Open Source Memory Layer For Autonomous Agents
M
Memori
Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production
Works with Supermemory
Tools that integrate with Supermemory, often used together in the same stack.
Compare Supermemory
Maintain Supermemory?
Show your live rank in your README, or put Supermemory in front of every visitor to AgentoolRank.