Agent Memory

Event-sourced graph runtime for durable and stateful agents

Search all your coding-agent chats, then resume any session in any agent.

Cortext

Event-driven long-horizon memory for real-time wearable AI and LLM agents.

evermemo

A tiny, universal memory engine for humans and AI agents — CLI, HTTP API, MCP server, and shared memory hub in one small Go binary

HelixDB

Knowledge graphs, vectors, temporal, and full-text search in one Rust engine — for agent memory, RAG, and company brains. Build memory yourself, or build your memory product on top of it.

Comparison of self-hostable memory providers for the Hermes agent on the MemConflict benchmark

Hindsight

Hindsight: Agent Memory That Learns

Honcho

Memory library for building stateful agents

Hyperspell

A detailed real-time model of your company. Designed with your security, privacy, and control in mind.

Letta

Making machines that learn. Create stateful agents that remember everything, learn continuously, and improve themselves over time.

Mem0

Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.

Permanent memory for AI agents. A 426-token prompt, a script, plug and play.

Plasma Wiki

Indexed knowledge bases with command-line tools for agents.

PromptQL

Curating context is a second job nobody wants. PromptQL is the team brain that organizes itself. Work with your team in shared AI threads, and PromptQL turns the context you generate into suggested edits to your wiki - interconnected pages that span skills, knowledge, and the semantic layer. You just accept.

Sentra

Sentra records what teams know — interactions, facts, actions — and structures that knowledge at write-time into a single queryable graph. The substrate beneath your stack.

smfs

A filesystem designed for agents, with SOTA retrieval, automatic memory profiles, sync engine. Drop any file type (pdf, images, videos), and grep through them.

Stash

Stash connects your tools and captures every agent session into one context graph your agents — and your team — can read. Open source, MIT licensed, self-hostable.

Supermemory

Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.

Watercooler

Watercooler: your team's shared reasoning layer for agentic coding. Preserve the "why" around your code.