Your AI’s memory, made visible.

A universal memory layer for AI agents. Searchable, correctable, portable. Install once, remember everywhere.

{
  "mcpServers": {
    "lodis": {
      "command": "npx",
      "args": ["-y", "lodis"]
    }
  }
}

Add to Claude Code, Cursor, Windsurf, or any MCP client. That’s it.

Lodis dashboard showing memory browser with search, domain filters, and confidence scores

AI memory today is broken.

Today

With Lodis

Today

Your AI builds up knowledge about you over time. You can’t see what it stored.

With Lodis

Browse, search, and edit every memory in a real dashboard.

Today

Teach something in one tool, start over in the next. Context trapped in walled gardens.

With Lodis

One memory layer shared across all your AI tools.

Today

Corrections don’t stick. You can’t trace where it learned something or how sure it was.

With Lodis

Confirm, correct, or flag — with confidence scores and full provenance.

Lodis makes AI memory yours.

Search & Retrieve

Hybrid search finds the right memory even when the wording differs. Context-packed retrieval delivers token-budget-aware results. Filter by domain, confidence, entity type, or just ask.

Search results showing memories with confidence scores and entity types

Correct & Control

Confirm what's right. Correct what's wrong. Split compound memories. Flag mistakes. Your AI learns from your feedback.

"Prefers TypeScript with strict mode enabled"

0.92

ConfirmCorrectSplit

Connect & Understand

Memories are auto-classified into 13 entity types. People, projects, and preferences are automatically linked. Entity profiles generate summaries on demand. Contradictions detected.

person

Sarah Chen

Engineering lead at Acme

0.95

project

Project Atlas

Next-gen search platform

0.88

preference

TypeScript strict mode

Always enabled in all projects

0.99

27 MCP tools. One install.

Everything your agent needs to remember, learn, and forget.

memory_write

Create a memory with dedup detection and permanence tiers

memory_write({ content: "Sarah prefers morning meetings", domain: "work" })

memory_search

Hybrid semantic + keyword search with filters

memory_search({ query: "design decisions", minConfidence: 0.8 })

memory_correct

LLM-powered semantic diff correction

memory_correct({ id, correction: "It's Thursdays, not Tuesdays" })

memory_connect

Create typed relationship between memories

memory_connect({ from, to, relationship: "works_at" })

memory_onboard

Guided onboarding: scan tools, interview, seed

memory_onboard({ scan: ["claude", "cursor", "gitconfig"] })

memory_export

Export memories as portable JSON

memory_export({ format: "json" }) → lodis-backup.json

See all 27 tools

Core

memory_writeCreate a memory with dedup detection and permanence tiers

memory_searchHybrid semantic + keyword search with filters

memory_contextToken-budget-aware context retrieval

memory_updateModify content, detail, or metadata

memory_removeSoft-delete with reason tracking

Trust

memory_confirmMark a memory as verified and boost its confidence

memory_correctLLM-powered semantic diff correction

memory_flag_mistakeDegrade confidence on bad information

memory_pinPin as canonical — decay-immune, high confidence

Graph

memory_connectCreate typed relationship between memories

memory_get_connectionsTraverse the knowledge graph

memory_splitBreak compound memories into atomic units

Discovery

memory_listBrowse by domain, confidence, or recency

memory_list_domainsList all domains with memory counts

memory_list_entitiesShow extracted entities by type

memory_classifyAuto-classify a memory's entity type via LLM

memory_briefingLLM-generated entity profile summaries

Safety

memory_scrubDetect and redact PII from memory content

memory_set_permissionsPer-agent read/write access by domain

memory_archiveArchive for reference — deprioritize and freeze

Onboarding

memory_onboardGuided onboarding: scan tools, interview, seed

memory_importImport from Claude, ChatGPT, Cursor, gitconfig

memory_interviewAgent-driven cleanup and gap-fill

Data

memory_exportExport memories as portable JSON

memory_indexIndex external docs for unified search

memory_index_statusCheck staleness of indexed documents

memory_migrateMigrate local memories to cloud (Pro)

Local-first. Zero config.

~/.lodis/lodis.db  ← Your memories live here. On your machine.

SQLite + FTS5 + native vector search. Local or cloud.

Embeddings run locally via Transformers.js. No API calls for search.

0600 file permissions. OS-level access control.

JSON export. Your data is always portable.

Optional cloud sync (Pro). AES-256-GCM encrypted, zero-knowledge.

Four permanence tiers: canonical, active, ephemeral (TTL), and archived.

Run it your way.

Start local with full privacy. Move to cloud when you need sync.

Local

Free · Open source · MIT License

SQLite on your machine — zero infrastructure
Stdio or HTTP transport — works with any MCP client
No accounts, no cloud, no API keys required
API tokens for remote client access
Dashboard at localhost:3838

Your data never leaves your machine.

Get Started

Free during beta

Cloud

Managed · Multi-device · AES-256-GCM encrypted

Turso cloud database — sync across devices
OAuth 2.1 — connect Claude.ai with one click
API tokens for remote MCP clients
Managed hosting — nothing to run
Dashboard at app.lodis.ai

Same memory, everywhere you work.

Start local, migrate anytime. memory_migrate moves your memories to cloud in one command.

Get started in 30 seconds.

Same config for every MCP client. Paste it into the file below for the client you use.

{
  "mcpServers": {
    "lodis": {
      "command": "npx",
      "args": ["-y", "lodis"]
    }
  }
}

Claude Code: ~/.claude.json
Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json
Cursor: ~/.cursor/mcp.json
Windsurf: ~/.codeium/windsurf/mcp_config.json