engram

ReallyArtificial/engram
★ 2 stars TypeScript AI/LLM Updated today
Agent memory system with retain-recall-reflect loop. Hybrid search, entity resolution, observation synthesis. TypeScript library + MCP server.
View on GitHub → Try with Claude — $10 free →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "engram": {
      "command": "npx",
      "args": [
        "-y",
        "ReallyArtificial/engram"
      ]
    }
  }
}

README Excerpt

A learning agent memory system with reflect loop. Engram stores facts extracted from text, links them to entities and relationships, and periodically synthesizes higher-order observations (patterns, preferences, insights). Engram is two things: 1. **A TypeScript library** — import `Engram` and call `retain()`, `recall()`, `reflect()` directly.

Tools (19)

BobDefaultENGRAM_AUTO_REFLECTENGRAM_DB_PATHENGRAM_DEFAULT_BANKENGRAM_DEFAULT_BANK_NAMEENGRAM_EMBEDDING_MODELENGRAM_LANGUAGE_MODELENGRAM_PROVIDERENGRAM_REFLECT_MAX_CLUSTERSENGRAM_SKIP_EVIDENCE_EVALdefaultforgetinspectopenairecallreflectretainretain_direct

Topics

agent-memoryagentsaiai-agentsai-infrastructureembeddingsllmmcpmemorymodel-context-protocolsqlitetypescriptvector-search