ai-memory — Persistent Memory for Any AI

Created By
AlphaOne LLC2 months ago
Persistent memory for any AI assistant. Zero token cost until recall. Stores memories locally in SQLite, ranks by 6-factor scoring, returns results in TOON compact format (79% smaller than JSON). 17 MCP tools, 20 HTTP endpoints, 25 CLI commands. 4 tiers from keyword to autonomous with local LLMs via Ollama. 97.8% recall accuracy on ICLR 2025 LongMemEval benchmark. Works with Claude, ChatGPT, Grok, Cursor, Windsurf, Continue.dev, OpenClaw, Llama, and any MCP client. Open source, MIT licensed, written in Rust.
Overview

ai-memory

If that works, paste this block into the left pane:

ai-memory — Persistent Memory for Any AI

Zero token cost until recall. Built-in memory systems inject 200+ lines into every message. ai-memory uses zero context tokens until memory_recall is
called. Only relevant memories return, ranked by 6-factor scoring. TOON format responses are 79% smaller than JSON.

ICLR 2025 LongMemEval Benchmark

97.8% R@5 (489/500) · 99.8% R@20 (499/500) · 232 q/s · $0 cloud cost

17 MCP Tools

memory_store · memory_recall · memory_search · memory_list · memory_get · memory_update · memory_delete · memory_promote · memory_forget · memory_link · memory_get_links · memory_consolidate · memory_capabilities · memory_expand_query · memory_auto_tag · memory_detect_contradiction · memory_stats

4 Tiers (all local, no cloud)

keywordsemantic (default) → smart (Ollama) → autonomous (Ollama)

8 AI Platforms

Claude · Codex · Gemini · Cursor · Windsurf · Continue.dev · Grok · Llama

Install

cargo install ai-memory

Rust + SQLite + FTS5 + HNSW. 161 tests. MIT licensed.

Server Config

{
  "mcpServers": {
    "memory": {
      "command": "ai-memory",
      "args": [
        "--db",
        "~/.claude/ai-memory.db",
        "mcp",
        "--tier",
        "semantic"
      ]
    }
  }
}
Project Info
Created At
2 months ago
Updated At
2 months ago
Author Name
AlphaOne LLC
Star
-
Language
-
License
-
Category

Recommend Servers

View All
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