AI tools for “memory”

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…

Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup. Sends the file's text to the configured model provider. Trigger: /caveman-compress.

Perfect Memory reads your screen and transcribes meetings on your Mac or PC. Search anything you've seen or heard, or ask Claude and ChatGPT. No meeting bots.

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

Prompt Genie cuts your Claude Code costs with context memory that stops Claude re-reading files it already knows. Install with npx prompt-genie.

…framework guide for building agents, workflows, tools, memory, workspaces, and storage with current APIs. Use for native capability discovery, logging, tracing, metrics/cost estimates, dataset experiments,…

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

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.

Persistent memory, autonomous scheduling, and multi-surface access — all on hardware you control. Open source, self-hosted AI agent.

Capture conversations and ideas with TwinMind, your AI memory app. Search your memories and use them in ChatGPT, Claude, and compatible AI tools.

Inspects and tunes the shared-vs-dedicated memory split on AMD Ryzen APUs with unified memory (UMA) so larger LLMs and image-gen models fit on the iGPU, or so reserved GPU memory is returned to the CPU. Use when the…

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.

Agents need memory. supermemory is building the default engine for memory and continual learning for agents. Skip to contentHumanAgentMenuCloseHomeProductBlogChangelogPricingResearchDocsConsoleMissionWhat we doIn…

18+ AI lovers with a personality, a memory, and no filter. Companions with memory, scenes you walk into. Flirting, sex, the rest — in your language. Free to start.

Chat, dictation, voice, meeting notes, documents and agents in one Mac app, joined by one memory of your work. Your memory stays on your Mac.

Append a session/state snapshot to MEMORY.md (regardless of where it lives — for this repo it's `founder/MEMORY.md`). Use when the user says "snapshot memory", "save state to memory", "/memory-snapshot", "log what…

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.

…billing, shared UI kit, local LLM boilerplate, RAG, AI memory, agents — production-ready codebase, one-command…

Preserve family stories and memories with Remento's life story book. Capture family history with no writing required. As seen on Shark Tank!

Diagnoses and reduces Qdrant memory usage. Use when someone reports 'memory too high', 'RAM keeps growing', 'node crashed', 'out of memory', 'memory leak', or asks 'why is memory usage so high?', 'how to reduce RAM?'.…