AI tools for “memory”

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.

Create a coach with the face, voice, tone, memory, and pressure style you actually answer. YesCoach turns weight loss, procrastination, and adulting into today's smallest doable move.

Growing into the one place for the skills, keys and memory of every agent you use. Shipping today: a free Rust hook that trims output the model does not need and archives every byte it cuts.

Start chatting with an AI girlfriend for free. Pro adds memory and voice; tokens pay for photos when the scene calls for them. No card to start.

Open-source stack that gives AI coding agents persistent memory, a right-sized workflow, curated skills and evidence-based review. One command per machine.

Turn one memory into a personalized music gift. Preview the original song, then send a private page they can open without an account.

vLLM is a high-throughput and memory-efficient inference and serving engine for Large Language Models (LLMs). Deploy AI models faster with state-of-the-art performance. Easy, fast, and cost-efficient LLM serving for…

Your personal AI assistant, built for hardware you already own. Context, memory, and actions you approve. Available on Android, iOS, macOS, Windows, and Linux.

Pieces builds artificial memory from your work so you can recover decisions, resume where you left off, and bring real context into every AI tool.

The why layer of repo-native project memory: the reasoning behind a codebase as Markdown in the repo, versioned by Git, for coding agents and humans, so nothing rejected is proposed twice.

Context Engine is one memory for your AI agents and your team. Claude, ChatGPT, Cursor and Claude Code save to it as they work, and the people on your team read it, ask it questions and add files. Free to start.

Groupthink is a memory for the people in your life and work. Capture what happened, keep what matters about each person in one place, and book the next conversation, so the relationships you care about compound instead…

Ocai runs on open models and learns how you work. One prompt starts a self-evolving agent — sandboxed, no lock-in, no rate limits. Free credits.

Diagnose and optimize USD stages for slow loading, high memory, low FPS or validation; preserve asset boundaries and reuse shared definitions.

…up, free up / reclaim disk space, find what's eating CPU / memory / storage, check battery health and wear, audit login & startup items, see pending updates, or asks for a "tune-up", "checkup", "system report", "health…

…tasks should run side by side without consuming local CPU, memory or…