Postgram runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 31 Oct 2026.
Self-hosted memory for AI agents with hybrid search, knowledge graphs, tasks, and document sync.
We read the source, 1 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const child = spawn(input.command, input.args, {
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Self-hosted, uncensored AI agent: ask it tasks, search its long-term memory and your documents.
Self-hosted AI agent for office work: run agents, office tools and documents from any MCP client.
Self-hosted AI workspace: semantic RAG document search, long-term memory, and AI chat via MCP.
Knowledge-graph memory for your team's documents. Answers cite the source, not a summary.
Shared, source-backed memory for AI agents on your own Postgres, with an optional document engine.
Intelligent context infrastructure for AI teams: knowledge graph, sessions, tasks, documents.
One shared memory for all your AI agents: documents, tasks, databases and memories in one workspace
MCP server for GroupDocs.Watermark — add and search document watermarks via AI agents.
Answers built from our own checks of this server.