Memory & State
Persistent memory and state management layers for AI agents. These tools store, retrieve, and reason over long-term user context, conversation history, and knowledge across sessions. Without memory, every interaction starts from scratch — these agents give your AI continuity and personalization.
Hermes Agent
Runs a self-improving personal agent from a terminal TUI or a Telegram/Discord/Slack gateway, creating its own skills,…
Screenpipe
Records your screen and audio 24/7 locally, then serves that history as searchable context to Claude, Codex and other c…
Beads
Stores issues and agent memory as a dependency graph so coding agents keep durable working context and track outstandin…
claude-mem
Captures Claude Code tool usage as searchable observations and replays summarized context into new sessions, giving cod…
CodeAlmanac
Turns your coding-agent conversations into a local-first codebase wiki, capturing architectural decisions and instituti…
Codebase Memory MCP
Indexes repositories into a persistent tree-sitter knowledge graph of functions, classes, call chains, and HTTP routes,…
Cognee
Builds queryable memory for agents by turning documents and conversations into a knowledge graph plus vector store, sel…
CowAgent
Runs a self-hosted personal agent that plans multi-step tasks, calls built-in and MCP tools, installs skills, and answe…
Graphify
Maps a codebase, docs, PDFs, and media into a queryable knowledge graph so AI coding assistants trace and cite paths in…
Graphiti
Builds temporally aware knowledge graphs for agents in real time, tracking when each fact became true so memory reflect…
Honcho
User state management platform for AI apps. Stores user context, preferences, and interaction history to enable persona…
Letta
Stateful agent framework with built-in memory. Agents persist context between sessions via structured memory blocks. Fo…
Mem0
Persistent memory layer for AI agents and LLMs. Stores, searches, and retrieves user and session memories across framew…
nanobot
Runs a self-hosted personal AI agent from a WebUI, terminal, or chat apps, combining tools, long-term memory, MCP serve…
OpenViking
Serves agent memories, resources and skills as a virtual filesystem under viking:// URIs, loading context on demand acr…
OzBrain
Shared knowledge layer that lets multiple agents read and write to a common memory, so context learned by one agent is…
Redis MCP
Official Redis MCP server for agentic applications to read, write, and search Redis data structures including JSON, has…
Rowboat
Builds a backlinked knowledge graph from your email, meetings and Slack in a local desktop app, then lets agents query…
Stash
Open-source self-hosted memory layer for AI agents. Gives any agent persistent, semantic memory across sessions — model…
Supermemory
Memory API for AI applications. Store and retrieve user memories, bookmarks, and knowledge with semantic search. One un…
Zep
Long-term memory store for AI assistants. Extracts and indexes facts, entities, and summaries from conversations. Fast…