Other · Local MCP server
OMEM
Memory for AI agents that tracks beliefs over time and surfaces contradictions.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.troybrandonc-bit/omem- Version
- 0.3.15
- Status
- Active
- Category
- other
- Transport
- stdio (local process)
- Package
- PyPI
- Published
- 2026-09-01
- Updated
- 2026-09-01
- Publisher
- troybrandonc-bit (GitHub)
- Website
- infrastructure.omem-cloud.com
- Repository
- github.com/troybrandonc-bit/Omem
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| PyPI | omem-infrastructure | 0.3.15 | stdio |
How to connect OMEM
OMEM runs locally from a Python package published to PyPI: omem-infrastructure version 0.3.15. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install — the usual command is uvx omem-infrastructure. It reads these environment variables: OMEM_API_KEY (required, secret), OMEM_PROJECT (required), OMEM_BASE_URL, OMEM_AGENT and OMEM_USER; set them 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": {
"omem": {
"command": "uvx",
"args": [
"omem-infrastructure"
],
"env": {
"OMEM_API_KEY": "<secret>",
"OMEM_PROJECT": "<value>",
"OMEM_BASE_URL": "<value>",
"OMEM_AGENT": "<value>",
"OMEM_USER": "<value>"
}
}
}
}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 other servers
| Server | Runs |
|---|---|
| OleaDesk MailYour own AI reads, searches and drafts in your mailbox, on your Windows computer. | Remote · HTTP |
| Ollama / vLLM BridgeCall your local Ollama or vLLM model over MCP with schema-validated JSON output. | Local · stdio |
| Ololand DdOloLand M&A intelligence — 33 tools for deal analysis, valuation, risk, and cross-deal learning. | Remote & Local · HTTP, stdio |
| OmegaAIQuery, browse, and automate OmegaAI workspaces from any MCP client. Streamable HTTP with OAuth 2.0. | Remote · HTTP |
| OmentirFind LinkedIn prospects, draft outreach, and run human-paced campaigns from your AI agent. | Remote · HTTP |
| Omnarai MCPDeliberation + live 5-model council divergence over the Omnarai multi-AI attributed corpus. | Remote & Local · HTTP, stdio |
| OmniDome by HumanMirrorFree agent home for live work, trust, repeat return and high-throughput fleet routing. | Remote · HTTP |
| Omnis Venture Intelligence MCPVenture intelligence for autonomous agents with discovery, scoring, and workspace automation. | Remote · HTTP |