Store and recall — that’s it. Auto-classification, entity extraction, knowledge graph, smart dedup, and hybrid retrieval are all built in. SDKs for Python, TypeScript, Go, and MCP.
pip install mindglue-sdk
npm install mindglue
go get github.com/mindglue/sdk-go
from mindglue_sdk import MindGlue
mg = MindGlue(api_key="mg_...")
mg.store("user:123", "Prefers dark mode, uses Python")
result = mg.recall("user:123", query="user preferences")
# Returns formatted markdown context ready for system prompt
Three steps. No infrastructure to manage. Your agent gets smarter with every interaction.
Your agent stores memories with a single API call. MindGlue auto-classifies the type, extracts entities and relationships, generates embeddings, and deduplicates — all automatically.
When your agent needs context, hybrid retrieval combines vector similarity, knowledge graph traversal, and temporal recency to find exactly the right memories.
Get pre-formatted markdown context organized by type — facts, preferences, history, procedures — ready to inject directly into your system prompt.
When you call store(), MindGlue runs a full intelligence pipeline automatically. This is what you’d spend months building yourself.
Auto-categorizes as fact, preference, episode, or procedure via LLM
Identifies people, companies, products, and their relationships
Entities and relationships become graph nodes with cross-source bridges
Vector embeddings for semantic similarity search via HNSW index
Catches paraphrases across sources, merges with contradiction detection
“Acme Corp” and “Acme Corporation” become the same canonical entity
Full version history on every update, immutable audit trail
Stored in Postgres with pgvector, cached in Redis, webhook fired
Steps 1–4 run in parallel. The entire pipeline completes in under a second.
Building memory from scratch means wiring together embeddings, a vector DB, a graph DB, caching, dedup logic, and ranking algorithms. Or you could use MindGlue.
Every memory is classified as a fact, preference, episode, or procedure — automatically via LLM with confidence scoring. No manual labeling. No taxonomy to maintain.
Not just vector search. Three signals — semantic similarity, knowledge graph traversal, and temporal recency — fused into one ranked result. No other memory API does this.
Recall memories across users, projects, and deals simultaneously. Perfect for complex agent interactions.
Paraphrases caught across sources. Duplicates merged via LLM. Contradictions detected automatically. Full version history preserved. Your memory stays clean without any effort.
Full multi-tenant isolation. Each namespace is a separate memory universe with its own quotas and access control.
Python, TypeScript, and Go SDKs. MCP server for Claude Desktop & Cursor. Real-time WebSocket streaming. Full REST API.
Automatically sync data from the tools your team already uses. Every record flows through the full intelligence pipeline.
Database rows
Docs, Sheets, PDFs
Pages & databases
Channel messages
CRM records
Tickets & articles
Issues & PRs
Project issues
Wiki pages
Ask about “Greenleaf Health” and get the Salesforce deal, the Notion onboarding doc, Jira tickets, Slack conversations, and Confluence specs — all in one recall. MindGlue automatically builds knowledge graph bridges between entities across every source.
Scale plan includes 3 connectors. Additional connectors $19/mo each. Enterprise: unlimited.
Start free. Scale as you grow. No hidden fees.
For prototyping & personal projects
For teams building production agents
For production workloads at scale
For organizations with compliance needs
Overages: Pro $0.50/10K memories + $1.00/5K recall calls. Scale $0.75/5K recall calls. Free plan has hard limits.
All plans include: auto-classification, intelligent deduplication, 3 recall strategies, knowledge graph, GDPR-compliant forget, version history
Start free. No credit card required. Upgrade when you need more.