nowfound

AI · August 31, 2026

Itsuki

The memory layer under every AI tool you use.

Visit itsuki.appAlternativestop 12% of August 2026

What it does

Itsuki is a shared memory layer under 26 AI tools. It extracts typed objects — facts, dated events, relationships — links each to the exact message it came from, and versions them so any fact can be rolled back. A relationship is only stored if the model can quote the sentence proving it. Open source (Apache 2.0), connect via MCP, REST API, or Node/Python SDKs. Free during early access.

Connect Itsuki once with one key. It extracts structured memories from any of 26 connected tools — assistants, agents, workflows — links each to the words it came from, and serves them back across all the rest.

Connect once with one key. Itsuki extracts structured memories from any of 26 connected tools and serves them back across all the rest. One store sits under all twenty-six. Type the fact once, in whichever tool happens to be open, and the next tool to ask gets it back — no export, no re-paste, no second store to keep in sync. “We’re on Postgres. No ORM — raw SQL only.” Everyone else replays the transcript and hopes the model finds the point. Itsuki keeps the point, the exact words it came from, and the shape of what it connects to. “hey are we still on for the review” “let me check the calendar one sec” “ok so september is completely…from itsuki.app

Does the same job

all alternatives →
  • AtlasoAug 2026 · atlaso.ai · ▲216

    One memory for every AI you use

  • MengramFeb 2026 · ▲108

    AI memory API with 3 types: facts, events, and workflows

  • MyLens.AI2023 · ▲183

    Generate timelines for any topic with AI

  • memories.shFeb 2026 · ▲50

    One layer for memories, skills, and rules across any agent

  • Mnexium AIJan 2026 · ▲83

    Persistent, structured memory for AI Agents

  • MCP Memory – Fast Agent Memory Using Google's OKF and SQLite FTS524d ago · github.com · ▲70

    An OKF-backed Model Context Protocol (MCP) server delivering persistent long-term memory and SQLite FTS5 search for AI agents. - fellowgeek/mcp-memory

More ai this month

the category →
  • I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.

    AI · 17d ago · simedw.com

  • Astute585

    Automate your B2B brand going viral, with new media creators

    AI · 18d ago · company-app.joinastute.com

  • Grok Bot547

    AI teammates that you can give real work to

    AI · 25d ago · x.ai

  • Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…

    AI · 27d ago · cactuscompute.com

  • Turn website visitors into qualified pipeline

    AI · 19d ago · clarasdr.ai

  • Kane CLI446

    Natural language browser & mobile app tests from terminal

    AI · 24d ago · testmuai.com

Launched alongside, August 2026

the whole month →
  • TL

    Life & fun · 10d ago · louisabraham.github.io

  • Hey Noah641

    A proactive AI executive assistant for founders

    AI · Aug 2026 · heynoah.io

  • Let agents source clips from terabytes of your local video

    Work · 18d ago · clipto.com

  • SA

    Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…

    Life & fun · Aug 2026 · toneyalexander.github.io

  • AdAnt AI608

    Claude for viral, high-converting social ads

    AI · Aug 2026 · adant.ai

  • I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.

    AI · 17d ago · simedw.com