SMRITI Memory vs Hindsight

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

SMRITI Memory logoSMRITI MemoryKnowledge & Memory · Local subprocess (stdio)Neuro-inspired long-term memory for AI agents with semantic graph and consolidation.53GoodAuth: not declaredHindsight 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

Verdict: choose SMRITI Memory for knowledge & memory work as a local process; choose Hindsight 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?

SMRITI Memory logoChoose SMRITI Memory when

  • You need dedicated capabilities in the Knowledge & Memory domain.
  • You prefer a local stdio subprocess transport.
  • You want tools like smriti_encode, smriti_recall, smriti_get_context.
Explore SMRITI Memory

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

Feature & specification comparison

Rows where the two servers differ are marked.

SpecSMRITI Memory logoSMRITI MemoryHindsight logoHindsight
CategoryKnowledge & MemoryKnowledge & Memory
Quality signal53/100 · Good57/100 · Good
Install commandConfirmedConfirmed
TransportLocal subprocess (stdio)Local subprocess (stdio)
AuthNot declaredAPI key required
PricingNot declaredFree
Required env varsNone listedHINDSIGHT_API_LLM_API_KEYHINDSIGHT_API_LLM_PROVIDERHINDSIGHT_DB_PASSWORD
Verified ownerCommunity listingCommunity listing
GitHub stars353,457
Directory activity 0 views 0 installs 0 upvotes 15 views 0 installs 0 upvotes
Tools12Not listed

Tools & capabilities

SMRITI Memory tools 12

  • smriti_encodeIngests a new memory. Accept `private=True` to exclude from team syncs.
  • smriti_recallRetrieves memories using semantic and graph-based retrieval.
  • smriti_get_contextHelper to inject the current active working memory slots into the context window.
  • smriti_how_well_do_i_knowPerforms a meta-memory confidence check on a given topic.
  • smriti_knowledge_gapsIdentifies topics the agent has identified it needs more information on.
  • smriti_pinMarks a memory as permanent (protects it from strength decay).
  • smriti_forgetSoft-deletes/archives a memory, leaving a cryptographic tombstone.
  • smriti_consolidateTriggers a background System 2 consolidation run.
  • smriti_statsReturns system-wide statistics (total memories, rooms, private counts).
  • smriti_create_private_roomSpawns a private room. All memories inside this room are visibility-isolated.
  • smriti_open_uiLaunches the interactive visual D3.js memory graph in your default browser.
  • smriti_sync_obsidianExports the Semantic Palace graph structures to markdown files in an Obsidian Vault.

Hindsight 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.

SMRITI Memory

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "smriti-memory": {
      "command": "uvx",
      "args": [
        "smriti-memcore"
      ]
    }
  }
}

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"
      }
    }
  }
}

Frequently asked questions

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

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

On AllMCPs, SMRITI Memory has a quality signal of 53/100 (Good) with 0 views, 0 installs and 3 GitHub stars. Hindsight has 57/100 (Good) with 15 views, 0 installs and 53,457 GitHub stars.