AI tools for “memory”

Launch public assistants for customer-facing conversations and personal assistants with memory, follow-ups, and recurring workflows.

Open source agent memory. Your agents learn from mistakes and get better over time. 94.6% on LongMemEval-S. MIT licensed.

Create captivating novels and stories easily with ONE sentence. No prompt, unlimited memory, infinite length. Read others' stories for inspiration!

Mem0 is the memory layer for AI agents and applications, enabling them to learn from past interactions and deliver personalized experiences.

Gortex indexes a repo into an in-memory knowledge graph and serves it to coding agents over MCP, HTTP, and a web UI. A 21-tool MCP surface (100+ operations), 18 resources, 257 languages — one graph query replaces a…

Raven is the harness of harnesses, built for RSI: it brings your agents, tools, skills, and memory together and turns one task into one finished result.

AI agents with memory that compound. From service to collections to payments, every conversation sharpens the next decision in customer-to-cash operations.

Open-source AI Operating System: your agents, skills, memory, and connectors in one repo you own. Any model. Self-host or cloud.

The open-source workspace where agents and teammates share one project memory — any runtime, your infra, no per-agent fees.

An AI coding agent for the CLI and your IDE, with one memory that follows your account across chat, the terminal, and your own code. It learns from a correction and applies it everywhere.

A reverse proxy that detects recursive agent loops and enforces spend caps in volatile memory, without retaining prompt payloads.

Turn daily work into searchable AI memory. Discover recurring workflows, document the steps, and find opportunities to automate across your apps.

The open-source agent harness with sandboxes, permissions, memory and durable sessions built in. Run team agents or embed them in your product. Any model, any cloud.

Create your best work, faster. GPT, Claude, Gemini, and Grok with memory, project files, AI tasks, and automations in one workspace and editor. Free to start.

A personalized song built from your memories. Hear a free 30-second preview before you pay. Unlock the full song and MP3 for $39.

purpal is your product's decision memory: every customer signal pooled into themes, every call tied to its evidence, every release watched. Ask it in purpal or from Claude and your other AI tools.

Rent NVIDIA H200 GPUs with 141GB memory at $4.59/hr for LLM training and inference. On-demand access, per-minute billing. H100 GPUs also available.

Create an aiAllure AI girlfriend or AI GF for private NSFW AI chat, fictional images, companion memory, and AI video. Adults 18+ only.

Knowl is an MCP memory server for Claude Code, Cursor and Codex. What your agents work out survives the session, and a change retires what it replaced — so the answer they read back is the current one.

LazyCodex installs the OmO agent harness inside Codex: project memory, planning, parallel agents, skills, hooks, routing, and verified completion for complex codebases.