Show HN: MCP Memory – Fast Agent Memory Using Google's OKF and SQLite FTS5

MCP-Memory, a Model Context Protocol server, provides AI agents with persistent memory using Google's Open Knowledge Format v0.2 and SQLite FTS5, enabling sub-20ms key lookups and full-text search. The server exposes four MCP tools for storing, retrieving, and searching memory records, and supports namespace isolation and automatic setup for tools like Claude Desktop, Cursor, and Codex.

MCP-Memory is a Model Context Protocol MCP server that equips AI agents such as Claude Desktop, Cursor, Antigravity, Windsurf, or Codex with persistent, long-term memory capabilities. Memory records are formatted using the Open Knowledge Format OKF v0.2 https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md standard and indexed with a local SQLite instance supporting FTS5 full-text search for fast key-value lookups, tag filtering, and content search. Fast Track: Jump directly to Quick Start Persistent State Across Sessions: Enables AI agents to read, store, search, and delete stateful memory snippets that persist across chat turns and sessions. OKF Standard Compliance: Stores every memory item formatted as an OKF v0.2 Markdown document with YAML frontmatter type , key , namespace , tags , generated , sources , verified , status , stale after , adhering strictly toand SPEC.md . OKF RULES.md Dual-Layer Architecture: Human-Browseable OKF Directory : Automatically dumps and syncs every memory to disk as a raw .md file inside the memory/ bundle directory with hierarchical index.md progressive disclosure files root index.md versioned with okf version: "0.2" and log.md update history tracking. High-Performance SQLite Indexing : SQLite FTS5 Full-Text Search and automatic triggers for sub-20ms key lookups and instant keyword searches. Namespace Isolation: Supports contextual separation e.g. user/preferences , project/architecture , default . Zero Boilerplate Setup: Quick setup wizard python3 setup.py auto-configures installed MCP tools Antigravity, Claude, Cursor, Windsurf, Codex . The server exposes four primary MCP tools to interacting agents: Stores or updates a memory record in OKF v0.2 format. Parameters: key string, required : Unique identifier or path for the memory e.g. user/preferences/coding style or project/architecture . content string or object, required : Core information to store. project root string, required : Absolute path to the active project root directory e.g. /Users/user/Projects/my-app . tags array of strings, optional : Classification tags for filtering. namespace string, optional, default: : Scope/namespace. "default" concept type string, optional, default: : OKF concept type e.g. "Agent Memory" Metric , Playbook , Attested Computation . title string, optional : Display name. description string, optional : One-line summary. resource string, optional : Canonical URI of underlying asset. status string, optional, default: : Lifecycle state "stable" draft | stable | deprecated . stale after string, optional : ISO date YYYY-MM-DD . sources array of objects, optional : Provenance sources {resource, id, title, author, usage count, last modified} . verified array of objects or object, optional : Verification events {by, at} . generated by string, optional : Actor identifier following actor convention <producer /<version , human:<id , process:<id . Retrieves a specific memory by its key and namespace. Parameters: key string, required : The memory key to look up. project root string, required : Absolute path to the active project root directory. namespace string, optional, default: : Scope/namespace. "default" Finds memories matching keywords, tags, or namespace filters. Parameters: project root string, required : Absolute path to the active project root directory. query string, optional : Keyword search query across keys, frontmatter, and content. tags array of strings, optional : Filter by specific tags. namespace string, optional : Scope search to a namespace. limit integer, optional, default: 10 : Maximum number of results. AGENT DIRECTIVE Session Start : Retrieves the last recorded session checkpoint system/last memory so the AI agent immediately knows where work was left off when opening a project or starting a session. Parameters: project root string, required : Absolute path to active project root directory. namespace string, optional, default: : Scope/namespace. "default" AGENT DIRECTIVE Milestones & Progress : Updates the canonical session checkpoint system/last memory whenever completing a milestone, making key changes, or pausing work. Parameters: content string or object, required : Brief note or structured dictionary summarizing progress and referencing key memory files. project root string, required : Absolute path to active project root directory. namespace string, optional, default: : Scope/namespace. "default" summary string, optional : One-sentence description of the milestone achieved. Every stored memory strictly adheres to the OKF v0.2 specification SPEC.md /fellowgeek/mcp-memory/blob/main/SPEC.md & : /fellowgeek/mcp-memory/blob/main/OKF RULES.md OKF RULES.md --- type: Agent Memory title: Coding Style key: user/preferences/coding style namespace: default tags: - preferences - style status: stable generated: by: mcp-memory/0.2.0 at: '2026-08-12T19:23:35Z' created at: '2026-08-12T19:23:35Z' updated at: '2026-08-12T19:23:35Z' --- User prefers functional programming style with explicit type annotations. git clone https://github.com/fellowgeek/mcp-memory cd mcp-memory Run setup.py to auto-detect and register mcp-memory with your AI tools: python3 setup.py Note:Once setup.py finishes configuring your tools, your AI client will launch mcp-memory automatically in the background whenever needed. You do not need to manually start or keep a server process running in your terminal. If you want to manually verify startup, inspect stdio output, or pre-initialize the virtual environment .venv , you can run run.sh directly: ./run.sh If you prefer to configure your MCP client manually, add the "memory" server entry pointing to run.sh : Add to your client's mcp config.json or claude desktop config.json : { "mcpServers": { "memory": { "command": "/ABSOLUTE/PATH/TO/run.sh" } } } Add to ~/.codex/config.toml : mcp servers.memory command = "/ABSOLUTE/PATH/TO/run.sh" Claude Code CLI: claude mcp add --scope user memory -- /ABSOLUTE/PATH/TO/run.sh Codex CLI: codex mcp add memory -- /ABSOLUTE/PATH/TO/run.sh Run the automated test suite to verify OKF serialization, SQLite database operations, and FastMCP tool execution: python3 test memory.py By default, mcp-memory creates project-isolated memory stores inside each project's root directory: OKF Markdown Files Human-readable : memory/ folder in project root. SQLite Database Hidden index : .mcp memory/memories.db in project root. You can customize this behavior using environment variables: MCP MEMORY PROJECT ROOT : Project root directory default: process current working directory cwd . MCP MEMORY DB PATH : SQLite database file path default: .mcp memory/memories.db relative to project root . MCP MEMORY DIR : Directory for Open Knowledge Format OKF .md files default: memory relative to project root . Tip:If you prefer a single global memory store shared across all projects, set MCP MEMORY DB PATH=~/.mcp memory/memories.db and MCP MEMORY DIR=~/.mcp memory/memory in your client's MCP configuration.