A second brain for Claude Code: project memory, estimated token & cost activity, semantic recall, and active guardrails.
A second brain for Claude Code: project memory, estimated token & cost activity, semantic recall, and active guardrails.
Project memory, estimated token & cost activity, local semantic recall, and active guardrails - through lifecycle hooks and an MCP server. Zero workflow changes.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"packmind": {
"command": "npx",
"args": ["-y", "packmind"],
"env": {
"ANTHROPIC_API_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| ANTHROPIC_API_KEY | Credential the server authenticates with. | Yes |
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Local-first semantic memory for MCP agents. Recall, remember, forget, echo, drift, stats over stdio.
A Model Context Protocol (MCP) server that provides access to OPET fuel prices data through Claude AI.
MCP server for web research, academic papers, Twitter/X, YouTube, and file ingestion. Eight tools for AI assistants — all via the MCP stdio protocol. Includes credential vault for institutional…
Local-first judgment layer: counter-examples & blind spots from your own knowledge base.