13 boosters for "agent-memory" — open source, verified from GitHub, ready to install
"name": "memsearch-plugins", "email": "support@zilliz.com" "description": "Semantic memory search plugin for Claude Code — markdown-first, backed by Milvus",
"description": "Open-source cross-agent memory layer for coding agents across Cursor, Claude Code, Codex, Windsurf, Gemini CLI, Copilot, Kiro, OpenCode, Antigravity, and Trae via MCP.", "sideEffects": false, "memorix": "./dist/cli/index.js"
Zettelkasten memory for AI agents. Markdown cards in with . npm package . Distributed as CLI + MCP server + Claude Code plugin + VS Code extension + Pi extension. Build has a known TS error ( optional dep). Ignore it — it compiles fine for distribution. If you add a new MCP tool:
"name": "prism-mcp-server", "mcpName": "io.github.dcostenco/prism-mcp", "description": "The Mind Palace for AI Agents — persistent memory (SQLite/Supabase), behavioral learning & IDE rules sync, multimodal VLM image captioning, pluggable LLM providers (OpenAI/Anthropic/Gemini/Ollama), OpenTelemetry
"name": "@touchskyer/memex", "mcpName": "io.github.iamtouchskyer/memex", "version": "0.1.29",
An MCP server that enables Claude to maintain persistent long-term and short-term memory across conversations using a local SQLite database. Developers and AI agents benefit from enhanced context retention and conversation continuity.
人脑不是硬盘，不会无差别存储所有信息。人脑会： DNA Memory 模拟这个过程，让 Agent 真正"进化"。 并且仅在有新的 写入后才执行 ，避免重复归纳同一批记忆。
DevContext is a cutting-edge Model Context Protocol (MCP) server designed to provide developers with continuous, project-centric context awareness. Unlike traditional context systems, DevContext continuously learns from and adapts to your development patterns and delivers highly relevant context pro
"name": "claude-mem-lite", "description": "Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external services. A lighter, lower-cost alternative to claude-me
The FIRST action in the BEGINNING of EVERY response MUST be to initialize the conversation with this single tool call and display the banner from the response immediately after. It MUST be called EXACTLY ONCE per conversation and ONLY at the very beginning after receiving user input: EVERY assistant
"name": "ai-brain-starter", "description": "Set up or upgrade an AI-powered Obsidian vault with journaling, knowledge graphs, pattern recognition, and meeting workflows. Includes skills for daily journaling, weekly insights, graphify knowledge graphs, humanizer, and more.", "name": "Adelaida Diaz-Ro
This booster enables AI agents to retrieve and summarize Zendesk ticket history and customer context, helping support teams provide informed, contextual responses without manual ticket searching.
