Launched May 19, 2026
Lumi

Lumi

Your AI finally remembers you. No more starting from zero.

SubscriptionMCP2,387 impressions#16 of its week

Lumi gives your AI persistent memory across chats and tools. Every new Claude, ChatGPT, or Gemini session starts already knowing your project, preferences, and history, no re-explaining, no copy-pasting old threads. Store wide, retrieve narrow: Lumi saves everything but surfaces only what's relevant per prompt, cutting token usage on long projects without losing context. Upload PDFs and docs for instant RAG, no setup needed. Organize memories in vaults and collections. Search semantically, Lumi understands meaning, not just keywords. Connect via MCP in 60 seconds via OAuth. Privacy-first: AES-256 encryption, TLS 1.3 in transit, row-level data isolation, and full deletion control, permanently removed from all backups within 30 days. Never sold, never used to train AI. Free to start: 300 memories, 2 vaults. Starter at $9/mo.

Lumi adds persistent, searchable memory to Claude, ChatGPT and Gemini so AI remembers your context across sessions.

for
Developers and AI enthusiasts who use LLMs and need cross-chat context.
pricing
freemium
works withClaudeChatGPTGemini

Key features

6 features of Lumi
  • Cross-LLM Memory — Store and retrieve context across Claude, ChatGPT and Gemini from a single vault.
  • Semantic Search — AI-powered search finds relevant memories by meaning, not just keywords.
  • Vault Organization — Create vaults and collections with hierarchical control to structure memories.
  • Document Upload — Upload PDFs and docs for instant retrieval-augmented generation without setup.
  • End-to-End Encryption — AES-256 at rest, TLS 1.3 in transit, row-level isolation and 30-day backup deletion.
  • MCP OAuth Connect — Connect your tools in ~60 seconds via MCP token authentication.

Use cases

  • Recall project specifications when switching from ChatGPT to Claude.
  • Search past design decisions stored as PDFs without re-uploading them.
  • Reduce token usage on long-running projects by retrieving only relevant context.

Lumi vs alternatives

LumiContextAtlasMemoryGraphUnified MCP ServerMCP Bridge by Appfactor
Best forPersistent memory layer for LLMsCode-aware context for ClaudeGraph memory for AI coding agentsBroad MCP integration platformAPI-to-AI bridging
PricingFreemiumFreeFreeSubscriptionFree
DevHunt upvotes1107298
LaunchedMay 2026May 2026Dec 2025Jan 2026May 2026

Lumi FAQ

How does Lumi keep my data private?+

All memories are encrypted with AES-256 at rest, TLS 1.3 in transit, and isolated per user; the team cannot query your data.

Can I use Lumi with any LLM?+

Currently Lumi integrates with Claude, ChatGPT and Gemini via MCP OAuth.

What happens when I delete a memory?+

The memory is instantly removed and permanently erased from all backups within 30 days.

Will my data be used to train AI models?+

No. Lumi never sells data or uses it to train AI.

Is there a free tier?+

Yes, the Free plan includes 300 memories, 2 vaults and semantic search at $0/month.

How does Lumi reduce token usage?+

It retrieves only the most relevant memories for each prompt instead of sending the full conversation history.

Summarized by DevHunt from llmmemory.ai · Sep 29, 2026. Details may change; check the official site.