Talamus MCP Server
by ampres-aiio.github.ampres-ai/talamusv1.1.3
Local-first, source-grounded memory that survives AI agent sessions.
context tax
queued
security
queued
cold start
queued
freshness
Maintained43d ago
Install Talamus MCP server
Install in Claude Code
claude mcp add talamus -- uvx talamus mcp serveInstall in Cursor
{
"mcpServers": {
"talamus": {
"command": "uvx",
"args": [
"talamus",
"mcp",
"serve"
]
}
}
}Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).
Install in Claude Desktop
{
"mcpServers": {
"talamus": {
"command": "uvx",
"args": [
"talamus",
"mcp",
"serve"
]
}
}
}Settings → Developer → Edit Config (claude_desktop_config.json), then restart.
Install in VS Code
{
"servers": {
"talamus": {
"type": "stdio",
"command": "uvx",
"args": [
"talamus",
"mcp",
"serve"
]
}
}
}Add to .vscode/mcp.json in your workspace.
Install in Windsurf
{
"mcpServers": {
"talamus": {
"command": "uvx",
"args": [
"talamus",
"mcp",
"serve"
]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json.
Freshness
Maintained — last maintenance signal 43d ago. The newest of the signals below sets the band.
Last commit (default branch)
2026-08-28 · 43d ago · GitHub
Latest release
2026-08-24 · 47d ago · GitHub · v1.1.3
Package published
no data · npm/PyPI
Registry entry updated
2026-08-24 · 47d ago · official registry · v1.1.3
FAQ
›How do I install the Talamus MCP server in Claude Code?
Run: claude mcp add talamus -- uvx talamus mcp serve. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.
›Does Talamus require an API key?
No required environment variables are declared in its published metadata.
›Can I use Talamus as a remote (hosted) MCP server?
No hosted endpoint is published; it runs locally over stdio.
›Is Talamus in the official MCP registry?
Yes, as io.github.ampres-ai/talamus.
Alternatives to Talamus
Other memory MCP servers.
MemoryActiveKnowledge graph-based persistent memory for maintaining context.
HindsightActiveHindsight: long-term memory for AI agents modeled on human memory.
Codebase MemoryActiveIndexes a repo into a persistent local knowledge graph of functions, classes, call chains, HTTP routes and cross-service links, using tree-sitter and LSP.
CogneeActiveMemory manager for AI apps and agents using graph and vector stores, with ingestion from many data sources.
HonchoActiveMemory that reasons: continual learning for stateful agents. Better context, fewer tokens.
Basic MemoryActiveLocal-first AI memory: a semantic knowledge graph of Markdown files that humans and LLMs both read and write, with optional cloud sync and team workspaces.