Developer · Local MCP server
Engram
Agent memory with automatic extraction, consolidation, and bi-temporal recall.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.tstockham96/engram- Version
- 0.5.1
- Status
- Active
- Category
- developer
- Transport
- stdio (local process)
- Package
- npm
- Published
- 2026-02-27
- Updated
- 2026-02-27
- Publisher
- tstockham96 (GitHub) · 2 servers with pages here
- Namespace
- Namespace verified by the MCP Registry via GitHub (github.com/tstockham96) · how
- Repository
- github.com/tstockham96/engram
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| npm | engram-sdk | 0.5.1 | stdio |
How to connect Engram
Engram runs locally from a Node.js package published to the npm registry: engram-sdk version 0.5.1. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx - the usual command is npx -y engram-sdk@0.5.1. It reads the environment variable GEMINI_API_KEY (required, secret); set it in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"engram": {
"command": "npx",
"args": [
"-y",
"engram-sdk@0.5.1"
],
"env": {
"GEMINI_API_KEY": "<secret>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More from tstockham96 (GitHub)
| Server | Runs |
|---|---|
| RailBudgets, propose-then-approve, and receipts for agents that buy for a human. Dry-run by default. | Local · stdio |
More developer servers
| Server | Runs |
|---|---|
| EngramPersistent, verbatim, searchable memory for AI assistants - one memory across every MCP client. | Remote · HTTPLive check: sign-in required |
| EngramCognitive memory for coding agents: hybrid recall, remember/forget, knowledge graph, nightly dreams. | Local · stdio |
| EngramLocal-first persistent memory for AI agents - SQLite + local embeddings, MCP-native, no cloud. | Local · stdio |
| EngramRanked local code-graph context for AI coding agents. Intercepts reads + greps. Apache-2.0. | Local · stdio |
| EngramMemory for AI agent teams across tools, sessions, repositories, and teammates. | Remote & Local · HTTP, stdioLive check: sign-in required |
| Engram CcUniversal AI coding assistant memory - session handoff, SLM compression, and semantic retrieval. | Local · stdio |
| Engram ServerDurable memory for AI agents: fact extraction, hybrid retrieval, temporal graph. SQLite/Postgres. | Local · stdio |
| Engram: AI memory you can edit in ObsidianShared memory for Claude, ChatGPT and any MCP client. Read and edit it in Obsidian or the web app. | Remote · HTTPLive check: sign-in required |