Hindsight vs WorkingMemory

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

Hindsight logoHindsightKnowledge & Memory · Local subprocess (stdio)Hindsight: Agent Memory That Works Like Human Memory - Built for AI Agents to manage Long Term Memory57GoodAuth: api key required
W
WorkingMemoryKnowledge & Memory · Remote HTTP/SSE
Persistent personal memory for AI assistants — save, search, and recall across every MCP client.39FairAuth: no auth required

Verdict: choose Hindsight for knowledge & memory work as a local process; choose WorkingMemory for knowledge & memory over a hosted endpoint. You can also run both side by side in one mcpServers block.

Which MCP server should you choose?

Hindsight logoChoose Hindsight when

  • You need dedicated capabilities in the Knowledge & Memory domain.
  • You prefer a local stdio subprocess transport.
  • Its auth model fits you: API key required.
  • You have the keys it needs: HINDSIGHT_API_LLM_API_KEY, HINDSIGHT_API_LLM_PROVIDER, HINDSIGHT_DB_PASSWORD.
Explore Hindsight

W
Choose WorkingMemory when

  • You need dedicated capabilities in the Knowledge & Memory domain.
  • You prefer a remote HTTP/SSE transport.
  • Its auth model fits you: No auth required.
Explore WorkingMemory

Feature & specification comparison

Rows where the two servers differ are marked.

SpecHindsight logoHindsight
W
WorkingMemory
CategoryKnowledge & MemoryKnowledge & Memory
Quality signal57/100 · Good39/100 · Fair
Install commandConfirmedConfirmed
TransportLocal subprocess (stdio)Remote HTTP/SSE
AuthAPI key requiredNo auth required
PricingFreeNot declared
Required env varsHINDSIGHT_API_LLM_API_KEYHINDSIGHT_API_LLM_PROVIDERHINDSIGHT_DB_PASSWORDNone listed
Verified ownerCommunity listingCommunity listing
GitHub stars53,323—
Directory activity 14 views 0 installs 0 upvotes 1 views 0 installs 0 upvotes
ToolsNot listedNot listed

Tools & capabilities

Hindsight tools

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

WorkingMemory 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.

Hindsight

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "vectorize-io-hindsight": {
      "command": "npx",
      "args": [
        "-y",
        "@vectorize-io/hindsight-coding-agents"
      ],
      "env": {
        "HINDSIGHT_API_LLM_API_KEY": "YOUR_HINDSIGHT_API_LLM_API_KEY_HERE",
        "HINDSIGHT_API_LLM_PROVIDER": "YOUR_HINDSIGHT_API_LLM_PROVIDER_HERE",
        "HINDSIGHT_DB_PASSWORD": "YOUR_HINDSIGHT_DB_PASSWORD_HERE"
      }
    }
  }
}

WorkingMemory

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "workingmemory": {
      "command": "npx",
      "args": [
        "-y",
        "workingmemory"
      ]
    }
  }
}

Frequently asked questions

Hindsight is categorized under Knowledge & Memory and uses a local stdio subprocess. WorkingMemory belongs to Knowledge & Memory and uses a remote HTTP/SSE transport. Pick Hindsight for knowledge & memory work and WorkingMemory 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.

Hindsight is listed as free. Auth: api key required. WorkingMemory has no declared pricing — check the project's own site. Auth: no auth required. 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 vectorize-io-hindsight and workingmemory as separate keys in the same mcpServers object, and your assistant will call tools from either one.

On AllMCPs, Hindsight has a quality signal of 57/100 (Good) with 14 views, 0 installs and 53,323 GitHub stars. WorkingMemory has 39/100 (Fair) with 1 views, 0 installs and 0 GitHub stars.