Kumbukum

by Unknown

Not rated
Website

About

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.

Details

Author
Unknown
Categories
Productivity, AI, Knowledge Base, Other, Communication

- Search across your knowledge base— Ask your assistant to find relevant notes, memories, URLs, emails, or pages with one unified knowledge search.
- Save and retrieve memories— Instruct your assistant to store decisions and learnings so context persists across sessions via memory tools.
- Create and update notes— Have your assistant maintain specs, docs, and meeting notes directly in your shared workspace.
- Bookmark and read URLs— Ask your assistant to save a URL with extracted content for later retrieval, or pull up a saved page.
- Search and inspect emails— Direct your assistant to retrieve email records and read threads to keep email context available in chat.
- Traverse the knowledge graph— Ask your assistant to link related items and follow connections between notes, memories, and projects.

Connect your AI tools to Streamient with the Model Context Protocol (MCP) — an open standard that lets AI assistants work directly with your notes, memories, saved URLs, emails, projects, and knowledge graph.

Instead of copying context between tools, your assistant reads and writes the same shared memory layer your team already trusts — across sessions, projects, and clients.

MCP is an open standard, developed by Anthropic, that creates a universal bridge between AI assistants and external tools. With the Streamient MCP server, your assistant can search and update your knowledge base directly — securely, and with your permission — without you leaving the chat.

With Streamient MCP, your AI assistant can:

- Search across everything— find relevant notes, memories, URLs, emails, and pages with one knowledge search
- Remember decisions and learnings— store memories so context persists across sessions
- Create and update notes— keep specs, docs, and meeting notes in one place
- Save and read URLs— bookmark pages with extracted content for later retrieval
- Search and read emails— retrieve email records, inspect threads, and keep email context available to AI clients
- Connect related knowledge— link items into a graph and traverse connections
- Organize by project— work within the right project automatically
- Ask in natural language— use AI chat to search, create, and analyze

The server exposes44 toolsacross notes, memories, URLs, emails, projects, graph, git sync, and search. See theTools referencefor the full list.

Public app submissions can use the curated/mcp/appendpoint on the same server. It exposes only private notes, memories, and project metadata tools; URL, email, git sync, graph, broad search, and chat orchestration tools remain available only on the full/mcpendpoint.

Streamient MCP works with any MCP-compatible client, including:

- Claude Desktop & Claude.ai
- Claude Code
- Cursor
- VS Code (with Copilot)
- ChatGPT
- Windsurf
- Codex CLI

- Setup & Authentication— connect your client with OAuth or a token
-
Tools— the full reference for all 44 tools
-
Claude Code— hooks for automatic search-before-work and store-after-work
-
Cursor (IDE)— global User Rules and project rules
-
Agent configuration— theAGENTS.md/CLAUDE.mdtemplate

Local-first agent memory: a plain-Markdown Obsidian vault is the source of truth, with a rebuildable DuckDB index for hybrid BM25 + vector + graph recall.

Local-first second brain for Claude. Saves notes as Markdown and recalls them across sessions with offline semantic search, no cloud and no API keys.

Local-first MCP memory server with no external dependency, source citations and OKF/Markdown KB.

Personal knowledge twin with semantic search. Store voice notes, documents, URLs, principles, and skills from any AI chat, then retrieve them with inline provenance citations. Hosted, multi-tenant, with per-user bearer-token auth and full data isolation.

Self-maintaining knowledge vault: figure-level search, auto-wikilinks, and sleep-based memory compression.

Dalexor MI is an advanced project memory system designed to provide AI coding assistants with Contextual Persistence. Unlike standard RAG (Retrieval-Augmented Generation) systems that perform surface-level keyword searches, Dalexor MI maps the logical evolution of a codebase, tracking how symbols, dependencies, and architectural decisions shift over time.

Historis keeps track of what happened — so you and your AI are never out of sync. Everything lands in one shared timeline, linked to the right people. Ask for the brief: what happened, what you should know, what needs handling.

Semantic search and RAG over Apple Notes with on-device embeddings, full CRUD, folder management, and fuzzy title matching. 10 tools. Fully local on macOS.

Centralized note store across AI clients: Claude, ChatGPT, Cursor, Codex, Windsurf. Save in one client, access in another instantly. Across devices — phone, desktop, everywhere. Cross-session context: 'catch me up' surfaces plans and findings from any prior session. AES-256-GCM encryption at rest, per-user key isolation. Soft delete with 30-day recovery window. Pin notes to exempt from cleanup and prioritize. Tag notes for categorization and filtering ('tag: auth'). Your mctx account is your identity — instant access from any AI tool.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.