01 context
Every new Claude session, you re-explain your entire stack. Again.
Turn every chat, meeting, and decision into shared context your whole team — and your agents — can use tomorrow.
Every new Claude session, you re-explain your entire stack. Again.
Remember that customer call? The transcript’s sitting in a Google Doc.
Nobody reads transcripts.
Your new hire’s first week is three days of asking questions whose answers are in Slack threads from 2023.
Every new Claude session, you re-explain your entire stack. Again.
Remember that customer call? The transcript’s sitting in a Google Doc.
Nobody reads transcripts.
Your new hire’s first week is three days of asking questions whose answers are in Slack threads from 2023.
The knowledge exists. It’s just not connected.
Sync from every tool
Files from Drive, conversations from Slack, tasks from Linear — all flow in, automatically. No new tool to open, no new habit to build.
Organizes in the background
While your team works, memsloth groups conversations by project, person, and decision. Nothing to file.
Ready wherever you work
Living playbooks your team reads on Monday. Context Claude can reach on Tuesday.
AI sessions remembered across conversations.
Coding decisions and context across your codebase.
Docs and wikis turned into retrievable team memory.
Files and docs that become searchable knowledge.
Decisions from threads, preserved and findable.
Issue context and decisions, always in scope.
// mcp All via MCP — works with any agent that supports it.
memsloth is open source under the Apache 2.0 license. Read every line, audit exactly how memories are extracted and stored, and self-host the whole thing on your own infrastructure — your data never has to leave your servers.
We don’t train on your team’s memories. And there’s no lock-in: fork it, extend it, and run it wherever you want — no vendor, no waiting on anyone’s roadmap.
Open source and self-hostable. Clone the repo and run it on your own infrastructure.