marketnow-memory
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@marketnow-memory remember that I prefer dark mode in all my tools"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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.jsonNo 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 profileRelated 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 |
| Session start: top rules/preferences + recent + optional query matches |
| TF-IDF cosine similarity + lexical fallback, recency/importance boosts |
| Store a decision / rule / preference / fact (importance 1-5, tags, topic) |
| Full profile grouped by topic |
| Remove by id or query (dry-run by default, |
| Wipe everything (requires |
| Health + storage info |
| 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-ableNever 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 storemarketnow-memory.js exports its operations (op_add, op_search, …) for
programmatic use.
License
MIT — (c) 2026 AliceLabs LLC. Part of MarketNow.
Available Tools
8 toolsmemory_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_searchA
Semantic search over stored memories (local TF-IDF cosine similarity, boosted by recency and importance).
Inputs: query (required), limit.
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
Scored across 8 tools
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.
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.
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.
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
Persistent memory for AI agents across Claude, ChatGPT and any MCP client.
Persistent memory for AI agents. Search and store durable facts, preferences and decisions.
Persistent memory, knowledge graph, task management and more for AI agents via MCP.
Hosted memory for AI agents over MCP. One memory shared by all your agents.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceProvides 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
- AlicenseAqualityDmaintenanceProvides 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.129 npmMIT
- AlicenseNot gradedqualityBmaintenanceProvides 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
- AlicenseNot gradedqualityCmaintenanceEnables 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 npmMIT