Browse
Mem-Dog logo

Mem-Dog

AI Developer ToolsFree plan available

Updated

In short

Mem-Dog is an open-source AI memory platform that ingests 300+ apps into a private, self-hosted knowledge base with graph and RAG search.

What is Mem-Dog?

Mem-Dog is an open-source AI memory platform that ingests data from 300+ apps and turns it into searchable, private knowledge on your own infrastructure. Built for developers and teams building AI applications, it pulls from sources like Slack, Gmail, GitHub, WhatsApp, HubSpot, and Salesforce through Nango OAuth, then runs the data through 42 AI agents that classify it, extract entities, generate embeddings, and build knowledge graphs. Retrieval spans five search modes: vector (pgvector), full-text (BM25), hybrid, graph-based (Neo4j), and merged signals, with RAG chat that returns answers backed by numbered inline citations. Mem-Dog supports 10 memory types (timeline, session, episodic, semantic, factual, organizational, and more) and a temporal knowledge graph that tracks facts with valid_at/invalid_at timestamps for point-in-time queries. It ships SDKs for Python, TypeScript, Go, Rust, and Ruby (around 120 methods each), an MCP server for Claude Desktop and Cursor, and adapters for LangChain, CrewAI, and OpenAI. Because it is self-hosted and open source under Apache 2.0, no data leaves your environment; it runs on any cloud (GKE) or even a Mac mini. Pricing is free with no per-seat or usage fees.

What is Mem-Dog used for?

Developers and teams building AI applications use Mem-Dog to ingest data from 300+ apps into a private, self-hosted memory layer with semantic search and cited RAG chat.

How much does Mem-Dog cost?

Free

Free

Free and open source (Apache 2.0)

View pricing

Plan

Price not published

Self-hosted — no per-seat or usage fees

View pricing

Pros and cons

Pros

  • Ingests data from 300+ apps (Slack, Gmail, GitHub, HubSpot, Salesforce) via Nango OAuth
  • Five search modes including vector (pgvector), BM25 full-text, and graph-based (Neo4j) retrieval
  • Self-hosted and open source under Apache 2.0 — no data leaves your infrastructure
  • SDKs for Python, TypeScript, Go, Rust, and Ruby, plus an MCP server for Claude Desktop and Cursor
  • Temporal knowledge graph with valid_at/invalid_at timestamps for point-in-time queries

Cons

  • Self-hosting requires infrastructure setup (Postgres/pgvector, Neo4j) and DevOps effort
  • New and relatively unproven, with a small community compared to established memory layers
  • No managed/hosted tier — you run and maintain everything yourself

Questions about Mem-Dog

What is Mem-Dog?

Mem-Dog is an open-source, self-hosted AI memory platform that ingests data from 300+ apps, processes it through 42 AI agents, and enables semantic search and RAG chat over your own private knowledge base without sending data to external servers.

Is Mem-Dog free?

Yes. Mem-Dog is free and open source under the Apache 2.0 license. It is self-hosted with no per-seat licensing or usage fees, though you provide your own infrastructure to run it.

What apps and integrations does Mem-Dog support?

Mem-Dog connects to 300+ apps through Nango OAuth, including Slack, WhatsApp, Gmail, GitHub, Telegram, Discord, HubSpot, and Salesforce. It also offers an MCP server for Claude Desktop and Cursor, plus adapters for LangChain, CrewAI, and OpenAI.

How does Mem-Dog search work?

Mem-Dog offers five search modes: vector search via pgvector, full-text via BM25, hybrid, graph-based via Neo4j, and merged signals. Its RAG chat returns conversational answers with numbered inline citations.

Mem-Dog vs Mem0?

Both are AI memory layers, but Mem-Dog is fully self-hosted and open source under Apache 2.0 with 300+ app ingestion, five search modes, and a temporal knowledge graph, making it a fit for teams that need data to stay on their own infrastructure. Mem0 offers a managed cloud option, which Mem-Dog does not.

What are the best alternatives to Mem-Dog?

Reviews

Sign in to rate and review Mem-Dog.

Sign in to review

No reviews yet. Be the first to review Mem-Dog!

Visit Mem-Dog