README.md
AgentKits Memory
by AityTech
Persistent Memory System for AI Coding Assistants
Your AI assistant forgets everything between sessions. AgentKits Memory fixes that. Decisions, patterns, errors, and context — all persisted locally via MCP.
Website • Docs • Quick Start • How It Works • Platforms • CLI • Web Viewer
English · 简体中文 · 日本語 · 한국어 · Español · Deutsch · Français · Português · Tiếng Việt · Русский · العربية
Features
| Feature | Benefit |
|---|---|
| 100% Local | All data stays on your machine. No cloud, no API keys, no accounts |
| Blazing Fast | Native SQLite (better-sqlite3) = instant queries, zero latency |
| Zero Config | Works out of the box. No database setup required |
| Multi-Platform | Claude Code, Cursor, Windsurf, Cline, OpenCode — one setup command |
| MCP Server | 9 tools: save, search, timeline, details, recall, list, update, delete, status |
| Auto-Capture | Hooks capture session context, tool usage, summaries automatically |
| AI Enrichment | Background workers enrich observations with AI-generated summaries |
| Vector Search | sqlite-vec semantic similarity with multilingual embeddings (100+ languages) |
| Web Viewer | Browser UI to view, search, add, edit, delete memories |
| 3-Layer Search | Progressive disclosure saves ~87% tokens vs fetching everything |
| Lifecycle Mgmt | Auto-compress, archive, and clean up old sessions |
| Export/Import | Backup and restore memories as JSON |
How It Works
Session 1: "Use JWT for auth" Session 2: "Add login endpoint"
┌──────────────────────────┐ ┌──────────────────────────┐
│ You code with AI... │ │ AI already knows: │
│ AI makes decisions │ │ ✓ JWT auth decision │
│ AI encounters errors │ ───► │ ✓ Error solutions │
│ AI learns patterns │ saved │ ✓ Code patterns │
│ │ │ ✓ Session context │
└──────────────────────────┘ └──────────────────────────┘
│ ▲
▼ │
.claude/memory/memory.db ──────────────────┘
(SQLite, 100% local)
- Setup once —
npx @aitytech/agentkits-memoryconfigures your platform - Auto-capture — Hooks record decisions, tool usage, and summaries as you work
- Context injection — Next session starts with relevant history from past sessions
- Background processing — Workers enrich observations with AI, generate embeddings, compress old data
- Search anytime — AI uses MCP tools (
memory_search→memory_details) to find past context
All data stays in .claude/memory/memory.db on your machine. No cloud. No API keys required.
Design Decisions That Matter
Most memory tools scatter data across markdown files, require Python runtimes, or send your code to external APIs. AgentKits Memory makes fundamentally different choices:
| Design Choice | Why It Matters |
|---|---|
| Single SQLite database | One file (memory.db) holds everything — memor |
Tools 7
memory_saveSaves a new memory entry.memory_searchSearches for memories using keyword or semantic similarity.memory_detailsRetrieves full details of a specific memory entry.memory_listLists recent memory entries.memory_updateUpdates an existing memory entry.memory_deleteDeletes a memory entry.memory_statusReturns the status of the memory system.Try it
→Search my memory for the decision we made regarding the authentication flow in the last session.
→Save a note that we decided to use Tailwind CSS for the new dashboard UI.
→List the last 5 coding patterns I have saved to my memory.
→Find all memories related to the 'login' endpoint and summarize them.
→Delete the memory entry with ID 123 as it is no longer relevant.