Engram

Created By
ayvazyan102 months ago
Persistent AI memory backend with semantic search and knowledge graph. Stores episodic, semantic, and procedural memories in SQLite and retrieves the most relevant ones using vector similarity and graph traversal. All embeddings run locally, with no API keys required.
Overview

What is Engram?

Engram is a universal AI memory backend that gives any AI model a persistent, growing brain.

It stores memories in a local SQLite database with full-text search, vector semantic search, and a knowledge graph that connects related concepts.

Memory Types

  • Episodic — past events, conversations, decisions
  • Semantic — facts, knowledge, and beliefs about the world
  • Procedural — how-to instructions, workflows, and code patterns

Key Features

  • Semantic search — find memories by meaning, not just keywords
  • Knowledge graph — 7-step graph traversal connects related memories
  • Contradiction detection — automatically flags conflicting beliefs
  • Local-first — all embeddings run on-device, no API keys needed, no data leaves your machine
  • Universal — works with Claude, OpenAI, Ollama, and any MCP-compatible client

Install

npx -y @engram-ai-memory/mcp@latest

Claude Desktop Config

{
  "mcpServers": {
    "engram": {
      "command": "npx",
      "args": [
        "-y",
        "@engram-ai-memory/mcp@latest"
      ]
    }
  }
}

18 MCP Tools

store_memory, search_memory, recall_context, add_knowledge, check_contradictions, resolve_contradiction, forget, tag_memory, list_tags, decay_sweep, decay_policy, re_embed, embedding_status, index_status, memory_stats, plugin_list, webhook_subscribe, webhook_list

  • Homepage: https://engram.am
  • GitHub: https://github.com/ayvazyan10/engram
  • npm: https://www.npmjs.com/package/@engram-ai-memory/mcp

Server Config

{
  "mcpServers": {
    "engram": {
      "command": "npx",
      "args": [
        "-y",
        "@engram-ai-memory/mcp@latest"
      ]
    }
  }
}
Project Info
Created At
2 months ago
Updated At
2 months ago
Author Name
ayvazyan10
Star
-
Language
-
License
-
Category

Recommend Servers

View All
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

5 hours ago
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago