Streamient
Streamient is an open-source team-shared AI memory layer that organizes notes, URLs, email archives, and Git decisions into self-hostable memory, accessible for reading and writing by mainstream AI clients via MCP and API.
Updated: 2026-10-27
What is Streamient?
Streamient is a team-shared AI memory layer licensed under the AGPL-3.0 open-source license, formerly known as Kumbukum. It compiles notes, memories, contexted URLs, email archives, Git repositories, and decisions into an inspectable, self-hostable shared memory that can be read from and written to by tools like Claude, Cursor, and ChatGPT via MCP or API. It holds that team memory requires joint maintenance by multiple people, and single-point notes are difficult to survive for a long time.
Who is it for?
- Small teams that share AI assistants and want consistent context.
- Technical organizations that want to self-host their memory library and have full control over their data.
- Project managers who need to archive decisions, code, and emails in a linked manner.
Key features
5Shared Memory
The team's notes, decisions, and contexts are unified into a single repository, with multiple people and tools sharing the same set of memories.
Traceable Source
The content of the memory can be inspected and self-hosted, and key conclusions can be traced back to their original sources.
MCP Read/Write
The official claims to offer forty-four MCP tools, and Claude, Cursor, ChatGPT, Windsurf, Zed, and VS Code can directly read from and write to them.
No Per-User Fee
The official statement says there is no charge per user, and free accounts are already available for use.
Public beta for mobile devices
iOS and Android clients are in public beta, allowing you to access team memories anytime, anywhere.
How to use Streamient
- Add project tags to memory entries for faster retrieval.
- First, accumulate high-frequency decisions and project backgrounds to maximize the value of your memory.
- Save key sources with context URLs for easy retrieval.
- Configure MCP in your preferred client to let the memory automatically participate in conversations.
- It emphasizes that memory is a collective asset of the team, requiring a unified way of storage and retrieval, rather than being scattered across personal notes.
- Overall, the effectiveness of such tools depends on whether the users have clear goals.
- It is recommended to take the time to read the official documentation and release notes before formal adoption to confirm whether the functional scope, data permissions and billing rules match your own business processes.
- For uncertain details, prioritize confirmation through official customer service or the help center, and do not rely on third-party information to make important decisions.
- At the same time, any automation should retain a manual review link, especially in scenarios involving funds, external communication or legal obligations.
- humans remain the ultimate bearers of responsibility.
- The value of a tool does not lie in replacing judgment, but in freeing humans from repetitive work so they have time to tackle more complex issues.
Traffic & popularity
Data month Sep 2026
Streamient receives about 137.4K visits per month.
Monthly visits
4 monthsEstimated from third-party traffic data.
Similar tools
Kynage CockpitKynage Cockpit is an AI agent management cockpit that allows configuring roles and instructions for agents, connecting to Git repositories, and accumulating team context through shared memory and integrated Wiki.
MemoryRouterA persistent AI memory layer across ChatGPT, Claude, Codex and other tools, officially said to migrate ChatGPT memories, connect various AI tools via MCP, and make backgrounds and project contexts follow users at all times.
BackdropBackdrop is an AI coworker platform that officially supports more than 1,500 integrations. It lets teams use preset skills, build custom skills, or record demonstrations to teach agents, while shared memory connects people and agents in one continuous workflow.
BloomeBloome is an instant messaging platform that places humans and AI agents in the same chat. The official statement says that the agents will review each other and share memories, and can be connected to models such as Claude, ChatGPT, and DeepSeek to deliver research outputs.
IndentIndent is a shared AI colleague for the entire company. According to the official website, what one person teaches it benefits the whole company. You can ask it questions on Slack or @ it on pull requests. It can read code, adjust integrations, run commands, modify files, and create pull requests that pass tests.🔍Open NotebookAn open-source, privately deployable AI research note-taking tool positioned as "Taking Control of Research Privately". It offers AI note-taking, podcast generation, and privacy control, and is regarded as a self-hosted alternative to NotebookLM.