Cognee vs Total Agent Memory

A side-by-side look at the Cognee and Total Agent Memory MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.

Cognee logoCogneeKnowledge & Memory · Local subprocess (stdio)Memory manager for AI apps and Agents using various graph and vector stores and allowing ingestion from 30+ data sources55GoodAuth: no auth requiredTotal Agent Memory logoTotal Agent MemoryKnowledge & Memory · Local subprocess (stdio)Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall44FairAuth: not declared

Verdict: choose Cognee for knowledge & memory work as a local process; choose Total Agent Memory for knowledge & memory as a local process. You can also run both side by side in one mcpServers block.

Which MCP server should you choose?

Cognee logoChoose Cognee when

  • You need dedicated capabilities in the Knowledge & Memory domain.
  • You prefer a local stdio subprocess transport.
  • Its auth model fits you: No auth required.
Explore Cognee

Total Agent Memory logoChoose Total Agent Memory when

  • You need dedicated capabilities in the Knowledge & Memory domain.
  • You prefer a local stdio subprocess transport.
  • You have the keys it needs: TAM_MEMORY_DIR.
Explore Total Agent Memory

Feature & specification comparison

Rows where the two servers differ are marked.

SpecCognee logoCogneeTotal Agent Memory logoTotal Agent Memory
CategoryKnowledge & MemoryKnowledge & Memory
Quality signal55/100 · Good44/100 · Fair
Install commandConfirmedConfirmed
TransportLocal subprocess (stdio)Local subprocess (stdio)
AuthNo auth requiredNot declared
PricingFreeNot declared
Required env varsNone listedTAM_MEMORY_DIR
Verified ownerCommunity listingCommunity listing
GitHub stars32,58173
Directory activity 5 views 0 installs 0 upvotes 2 views 0 installs 0 upvotes
ToolsNot listedNot listed

Tools & capabilities

Cognee tools

No tool names declared yet. Check the project README from the listing page.

Total Agent Memory tools

No tool names declared yet. Check the project README from the listing page.

Ready-to-paste client configs

Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.

Cognee

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "topoteretes-cognee": {
      "command": "uvx",
      "args": [
        "cognee"
      ]
    }
  }
}

Total Agent Memory

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "total-agent-memory": {
      "command": "uvx",
      "args": [
        "total-agent-memory"
      ],
      "env": {
        "TAM_MEMORY_DIR": "YOUR_TAM_MEMORY_DIR_HERE"
      }
    }
  }
}

Frequently asked questions

Cognee is categorized under Knowledge & Memory and uses a local stdio subprocess. Total Agent Memory belongs to Knowledge & Memory and uses a local stdio subprocess. Pick Cognee for knowledge & memory work and Total Agent Memory for knowledge & memory.

Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.

Cognee is listed as free. Auth: no auth required. Total Agent Memory has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.

Yes. MCP clients support multiple servers: add topoteretes-cognee and total-agent-memory as separate keys in the same mcpServers object, and your assistant will call tools from either one.

On AllMCPs, Cognee has a quality signal of 55/100 (Good) with 5 views, 0 installs and 32,581 GitHub stars. Total Agent Memory has 44/100 (Fair) with 2 views, 0 installs and 73 GitHub stars.