Historis

MCP (Model Context Protocol) is the open standard that lets AI assistants connect to external tools and data. Historis ships an MCP server, so any MCP-compatible client works with your shared timeline directly — no copy-paste, no export.

Always scoped to your organization and your visibility rules — never the whole database.

- Events — dated client and supplier interactions
- People — contacts linked to their full history
- Tags — your classification across events and people
- Follow-ups — open loops and what needs attention
- Context — organization and per-person summaries
- Knowledge — durable notes on what you know, not just what happened

Your AI reads and writes freely by default. Every write is attributable, logged, and reversible — and you can restrict what agents may read and write, organization-wide.

search, list events, get person history, search knowledge, daily brief

create / update events, link people, write knowledge notes, manage tags & rules

OAuth — connect Claude or ChatGPT in a click, no key to copy.

API tokens — for Cursor and custom clients, scoped per token.

Historis is the memory layer, not the intelligence. You bring your own AI provider; Historis never trains on your data and never sends it anywhere you did not connect. Every AI write is attributable and reversible, and you can restrict AI agents' permissions for your organization.

What's still open with Dupont SARL, and what should I follow up on?

Log a call with the plumber: quote sent, follow up Friday.

Summarize everything that happened with my suppliers this week.

Any MCP-compatible client. Today that includes Claude (desktop and web), ChatGPT and Cursor, and more clients adopt MCP regularly.

No. Historis stores and structures your data and exposes it to the AI you connect. The intelligence is your provider's; the memory is yours.

By default an assistant can read and write. You stay in control: restrict what AI agents may read or write for your organization, and every write is attributable, logged, and reversible — scoped to what you can see.

Every request is scoped to your organization and your team and visibility rules. An assistant only ever sees what you can see.

Create notes, search, & think with your Fabric AI workspace

Read, search, and write Obsidian vault notes via Team Relay collaborative server. Supports shared folders and real-time sync.

One memory. Every AI. Nothing to install. Memxus works across Claude, ChatGPT, Cursor and Slack — and any app your team uses that needs to remember (Notion, Linear/Jira, Gmail, Salesforce/HubSpot, Intercom, Zendesk, Google Drive, Confluence, GitHub). No extension, no local setup, no repeated context. Save once. Remember everywhere.

Open-source shared AI memory and team knowledge layer with 44 MCP tools for notes, memories, URLs, emails, projects, graph search, semantic search, and Git sync.

Official Notion MCP server for searching, reading, creating, and updating Notion pages, databases, and workspace content from AI agents.

Keep teams & agents coordinated automatically

Interact with your Anytype data through its API, enabling AI assistants to access your information.

MCP server for Apple Notes with semantic search and CRUD operations. Claude searches, reads, creates, updates, and manages your Apple Notes through natural language.

Markdown-first Notion MCP server with 9 composite tools, 39 actions, and ~77% token reduction via tiered docs.