2026 swarm Agent 年，swarm Agent 、Agent team、 ai coding、skill、memory、evolve、agentic RL 等 AI Agent集合

Transforms file-based memory banks into a centralized, remotely accessible service for multi-project management with consistent structure and validation.

The project operating system for AI agents.

MemoryBear Equip AI with human-like memory capability

Integrates with Memory Box to provide persistent, context-aware interactions through semantic memory storage and retrieval using vector embeddings and search capabilities.

Lightweight, file-based memory storage for maintaining persistent context across conversations using simple text operations.

Provides a knowledge graph-based memory system for creating, managing, and querying structured information with features like custom file paths, timestamping, and advanced search capabilities.

Local-first context engineering layer for AI agents with feedback capture and failure pattern blocking.

MCP server for memory journal from local photos (iCloud Photos)

Local-first memory for AI agents: SQLite FTS5, deterministic recall, no vector DB, no cloud.

Persistent memory and conversation search across multiple AI coding assistants.

A Model Context Protocol server that provides knowledge graph management capabilities.

A Model Context Protocol server that provides knowledge graph management capabilities.

Store and query structured data in local knowledge graphs.

Adaptive memory for AI agents — FAISS search, chat extraction, cross-project linking

Memory Palace is a long-term memory operating system purpose-built for AI Agents.

MCP server for MemoryPlugin API integration

🧠 𝑴𝒆𝒎𝒐𝒓𝒚-𝑷𝒍𝒖𝒔 is a lightweight, local RAG memory store for MCP agents. Easily record, retrieve, update, delete, and visualize persistent "memories" across sessions—perfect for developers working with multiple AI coders (like Windsurf, Cursor, or Copilot) or anyone who wants their AI to actually remember them.

Provides a knowledge graph-based memory system using PouchDB for storing and retrieving entity relationships and observations, enabling persistent conversational context across interactions.

Audit and manage Claude Code memory files with quality scoring and conflict detection.

High-performance Rust drop-in replacement for mcp-memory-service with SQLite storage and ONNX embeddings.

This repository is designed to automate the detection and cleanup of in-memory web shells using MCP in combination with the memory-shell-detector tool. / 本仓库旨在结合 MCP 与 memory-shell-detector 工具，实现对内存 WebShell（内存马）的自动化检测与清除。

Provides persistent text memory storage with tagging capabilities for storing, retrieving, searching, and managing information across conversations using a local JSON file.

Local-first AI memory layer with hybrid search. Postgres + pgvector. Self-hosted, MIT.

A Model Context Protocol (MCP) server for Memos API with search, create, retrieve, and tag listing capabilities.