Persistent memory for agents.
An LLM wiki your coding agent writes — agent memory you can open and read. The agent does the writing; easymem does the storage, full-text search and knowledge graph. No embedding model, no vector database.
MCP server for Linux system monitoring — CPU, memory, disk, network, processes, systemd services, and system logs for Claude, Cursor, and AI agents
Persistent memory for Claude Code with hybrid search (BM25 + vectors + reranker) — MCP plugin
MCP server for searching past Claude Code conversation history. Local BM25 search over JSONL logs with persistent index, secret redaction, solved-hint, and instant claude --resume.
Living Memory MCP — a persistent memory store for coding agents, over stdio. Facts survive across sessions and processes; retrieval is semantic (MMR), not string matching. Pre-alpha.
Evidence-first reverse-engineering workbench for humans and AI agents
MCP server for LanceDB-backed long-term memory with hybrid retrieval (Vector + BM25), cross-encoder rerank, multi-scope isolation, and memory lifecycle management
Local Memory MCP Server - AI-powered persistent memory system for Claude Code, Claude Desktop, Gemini, Codex, OpenCode and other MCP-compatible tools
AI Memory & Knowledge Management MCP Server — 32 tools, BM25 R@5=95%, hybrid search (RRF), knowledge graph, analytics, cloud sync, Obsidian compatible. Works with Claude Code, Cursor, Gemini CLI, Windsurf, hermes-agent.
Provider-neutral agent runtime for coding workflows. Verified DAG execution with evidence gates, worktree isolation, and local graph memory.
MCP server with 18 tools for AI agent infrastructure — persistent memory, API drift detection, and HMAC-signed trust receipts
MCP server providing AI agents with persistent, PostgreSQL-backed virtual filesystem — session-isolated file operations, cross-session stores, glob/grep search, and Row Level Security
RushDB MCP Server - Model Context Protocol server for RushDB
A portable persona for MCP clients — the same agent in Claude Code, Codex, Cursor and VS Code. Runs locally; nothing leaves your machine.
Multi-language code graph memory system for LLMs
Local-first MCP memory and code intelligence that helps coding agents recall repo context, decisions, failures, and review impact.
Memories — agent-agnostic memory for AI coding agents. MCP server + installer CLI.
Engram — a self-hosted team knowledge wiki with semantic search, served as an MCP server. Propose-and-approve knowledge flow (human gate), shared data with the Engram desktop app.
CarpeOS CLI and local MCP server — capture context, compound knowledge.
Agentic workflow kit for any AI coding harness: graphyloop swarm + memory (plugin + MCP server), chadi squad agents, 5-gate workflow. Install via npx.