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) ``` 1. **Setup once** — `npx @aitytech/agentkits-memory` configures your platform 2. **Auto-capture** — Hooks record decisions, tool usage, and summaries as you work 3. **Context injection** — Next session starts with relevant history from past sessions 4. **Background processing** — Workers enrich observations with AI, generate embeddings, compress old data 5. **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 — memories, sessions, observations, embeddings. No scattered files to sync, no merge conflicts, no orphaned data. Backup = copy one file | | **Native Node.js, zero Python** | Runs wherever Node runs. No conda, no pip, no virtualenv. Same language as your MCP server — one `npx` command, done | | **Token-efficient 3-layer search** | Search index first (~50 tokens/result), then timeline context, then full details. Only fetch what you need. Other tools dump entire memory files into context, burning tokens on irrelevant content | | **Auto-capture via hooks** | Decisions, patterns, and errors are recorded as they happen — not after you remember to save them. Session context injection happens automatically on next session start | | **Local embeddings, no API calls** | Vector search uses a local ONNX model (multilingual-e5-small). Semantic search works offline, costs nothing, and supports 100+ languages | | **Background workers** | AI enrichment, embedding generation, and compression run asynchronously. Your coding flow is never blocked | | **Multi-platform from day one** | One `--platform=all` flag configures Claude Code, Cursor, Windsurf, Cline, and OpenCode simultaneously. Same memory database, different editors | | **Structured observation data** | Tool usage is captured with type classification (read/write/execute/search), file tracking, intent detection, and AI-generated narratives — not raw text dumps | | **No process leaks** | Background workers self-terminate after 5 minutes, use PID-based lock files with stale-lock cleanup, and handle SIGTERM/SIGINT gracefully. No zombie processes, no orphaned workers | | **No memory leaks** | Hooks run as short-lived processes (not long-running daemons). Database connections close on shutdown. Embedding subprocess has bounded respawn (max 2), pending request timeouts, and graceful cleanup of all timers and queues | --- ## Web Viewer View and manage your memories through a modern web interface. ```bash npx @aitytech/agentkits-memory web ``` Then open **http://localhost:1905** in your browser. ### Session List Browse all sessions with timeline view and activity details.  ### Memory List Browse all stored memories with search and namespace filtering.  ### Add Memory Create new memories with key, namespace, type, content, and tags.  ### Memory Details View full memory details with edit and delete options.  ### Manage Embeddings Generate and manage vector embeddings for semantic search.  --- ## Quick Start ### Option 1: Claude Code Plugin Marketplace (Recommended for Claude Code) Install as a plugin with one command — no manual configuration needed: ```bash /plugin marketplace add aitytech/agentkits-memory /plugin install agentkits-memory@agentkits-memory ``` This installs hooks, MCP server, and memory workflow skill automatically. Restart Claude Code after installation. ### Option 2: Automated Setup (All Platforms) ```bash npx @aitytech/agentkits-memory ``` This auto-detects your platform and configures everything: MCP server, hooks (Claude Code/OpenCode), rules files (Cursor/Windsurf/Cline), and downloads the embedding model. **Target a specific platform:** ```bash npx @aitytech/agentkits-memory --platform=cursor npx @aitytech/agentkits-memory --platform=windsurf,cline npx @aitytech/agentkits-memory --platform=all ``` ### Option 3: Manual MCP Configuration If you prefer manual setup, add to your MCP config: ```json { "mcpServers": { "memory": { "command": "npx", "args": ["-y", "@aitytech/agentkits-memory", "server"] } } } ``` Config file locations: - **Claude Code**: `.claude/settings.json` (embedded in `mcpServers` key) - **Cursor**: `.cursor/mcp.json` - **Windsurf**: `.windsurf/mcp.json` - **Cline / OpenCode**: `.mcp.json` (project root) ### 3. MCP Tools Once configured, your AI assistant can use these tools: | Tool | Description | |------|-------------| | `memory_status` | Check memory system status (call first!) | | `memory_save` | Save decisions, patterns, errors, or context | | `memory_search` | **[Step 1]** Search index — lightweight IDs + titles (~50 tokens/result) | | `memory_timeline` | **[Step 2]** Get temporal context around a memory | | `memory_details` | **[Step 3]** Get full content for specific IDs | | `memory_recall` | Quick topic overview — grouped summary | | `memory_list` | List recent mem ---