Skip to main content
Glama

marketnow-memory

Persistent, local memory for any AI agent — one file, zero dependencies.

Works with Claude Code, Cursor, Codex CLI, Windsurf, Cline, Continue, Aider, OpenCode, Goose, Amp and any MCP-compatible client (Model Context Protocol, stdio JSON-RPC 2.0).

  • No cloud — data stays in ~/.marketnow-memory/memory.json

  • No npm install — single file, Node >= 18, standard library only

  • No API keys — search runs locally (TF-IDF cosine similarity + lexical fallback)

  • No telemetry — zero network calls

  • Tested — 29 integration checks (node test.js)

Quick start

git clone https://github.com/alicelabs-llc/marketnow-memory.git
cd marketnow-memory
node test.js          # verify: 29 checks pass
node marketnow-memory.js status
node marketnow-memory.js add "We use pnpm, never npm" --type rule --topic tooling --importance 5
node marketnow-memory.js search "package rules"
node marketnow-memory.js profile

Related MCP server: light-agent-memory-mcp-server

Register with your agent

Add to your MCP client config (see mcp-config.example.json for Claude Code, Cursor, Codex CLI, Windsurf, Cline, Continue, Aider, OpenCode, Goose, Amp):

{
  "mcpServers": {
    "marketnow-memory": {
      "command": "node",
      "args": ["/absolute/path/to/marketnow-memory/marketnow-memory.js"]
    }
  }
}

Then ask your agent:

what do you remember about me?

and it will call memory_profile.

The 8 MCP tools

Tool

What it does

memory_bootstrap

Session start: top rules/preferences + recent + optional query matches

memory_search

TF-IDF cosine similarity + lexical fallback, recency/importance boosts

memory_add

Store a decision / rule / preference / fact (importance 1-5, tags, topic)

memory_profile

Full profile grouped by topic

memory_forget

Remove by id or query (dry-run by default, confirm:true to delete)

memory_clear

Wipe everything (requires confirm:true)

memory_status

Health + storage info

memory_export

Full backup as JSON or Markdown

Memory model

{
  "id": "mem-mu5vezi6-6654ad",
  "type": "rule",                     // decision | rule | preference | fact
  "topic": "tooling",
  "tags": ["pnpm", "package-manager"],
  "content": "We use pnpm, never npm",
  "importance": 5,
  "created_at": "2026-09-17T18:36:17.221Z"
}

How search works (honest notes)

Local search = TF-IDF vectors + cosine similarity over content, topic and tags, with small recency and importance boosts, plus a lexical substring fallback when token overlap is zero. It needs no API keys and runs offline, which is the point. The trade-off is honest: it is statistical recall, not embedding-grade world knowledge — "package manager" will match "pnpm" only if the memory text mentions it. Write memories with descriptive keywords and recall stays sharp. If you need vector-database recall over millions of documents, point a real vector DB at your data instead — this tool is the lightweight, zero-dependency option.

Storage & privacy

  • Default: ~/.marketnow-memory/memory.json (override: MARKETNOW_MEMORY_HOME)

  • Atomic writes (.tmp + rename)

  • Plain JSON — inspectable, portable, memory_export-able

  • Never store credentials, tokens or private keys in agent memory

Development

node test.js                          # integration test (spawns real server)
MARKETNOW_MEMORY_HOME=/tmp/mem node marketnow-memory.js add "x"   # isolated store

marketnow-memory.js exports its operations (op_add, op_search, …) for programmatic use.

License

MIT — (c) 2026 AliceLabs LLC. Part of MarketNow.

Available Tools

8 tools
memory_addA

Store a memory: a decision, rule, preference or fact worth remembering across sessions.

Inputs: content (required), tags, type, topic, +2 more.

memory_bootstrapA

Load relevant memories to bootstrap a new session: top rules and preferences by importance, plus recent memories and optional query matches. Call at session start.

Inputs: query, match_limit, rules_limit, recent_limit.

memory_clearA

Wipe ALL memories. DANGER ZONE: requires confirm:true. Suggest memory_export first.

Inputs: confirm.

memory_exportA

Export all memories as JSON or Markdown for backup or portability.

Inputs: format.

memory_forgetA

Remove specific memories by id, or by semantic query (dry-run by default; pass confirm:true to delete).

Inputs: id, query, confirm, min_similarity.

memory_profileA

Show the full memory profile grouped by topics, with counts by type and topic. Use when the user asks "what do you remember about me?".

Inputs: no named parameters.

memory_statusA

Service health: storage path, counts, search backend, version. No parameters.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 8 tools

    Disambiguation5/5

    Each tool targets a distinct memory operation: bootstrap, search, add, profile, clear, forget, status, and export. Even memory_bootstrap and memory_search are clearly separated by purpose and description.

    Naming Consistency5/5

    All tools follow a consistent memory_<action> pattern, making the tool set predictable and easy to navigate. The two noun-like names (profile, status) still read as actions in context and do not break the pattern.

    Tool Count5/5

    Eight tools is well-scoped for a memory service, covering retrieval, storage, deletion, inspection, export, and health checks without redundancy. Each tool earns its place.

    Completeness4/5

    The core memory lifecycle is covered: add, search, forget, clear, profile, export, and bootstrap. Minor gaps exist around updating an existing memory in place and importing memories back after export, but these can be worked around.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      A
      maintenance
      Provides persistent memory for AI coding agents via MCP, enabling agents to store and semantically recall facts, events, and lessons across sessions, all running locally without cloud dependencies.
      Apache 2.0
    • A
      license
      A
      quality
      D
      maintenance
      Provides persistent, searchable memory for AI agents across any MCP-compatible client, storing project context, user preferences, and session learnings locally in SQLite with tools to save, retrieve, search, and manage them.
      12
      9 npm
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Provides local-first persistent memory with a typed knowledge graph and bounded multi-hop retrieval via MCP, letting coding agents and local LLM systems store, search, and recall facts across sessions without hosted services or model dependencies.
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to store and recall durable facts, decisions, and lessons over MCP using hybrid semantic and keyword search, typed memories, graph relations, sessions, and time-travel queries. Runs locally with no server process or API key, persisting everything to files that both agents and a CLI can share.
      28 npm
      MIT