nowfound

AI · August 26, 2026

mikrokhoros

Open source AI agent harness for object-first worlds

What it does

Open source AI agent harness for object-first worlds. Every persistent world capability an agent can invoke is an exact concrete object with declared functions, identity, state, location, authority, and history; the runtime enforces locality, possession, permissions, bounded actions, and replayable trajectories.

Open source AI agent harness for object-first worlds. - sonatapublisher/mikrokhoros

Does the same job

all alternatives →
  • DeepSeek Harness23d ago · github.com · ▲169

    Composable agent harness where everything is a plugin

  • OpenAI Agents SDKApr 2026 · ▲122

    Build production agents with harness and sandbox

  • HarnessRouterJul 2026 · ▲238

    Bring the world's best AI agents into your app, with one API

  • OpenMoltMar 2026 · ▲132

    Let your code create and manage AI Agents (OpenSource)

  • Agentic Website Builder 2.0 by LokumaMay 2026 · ▲183

    Design, build, and run your site with a design agent harness

  • BUMar 2026 · ▲138

    Openclaw in the cloud

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 · 16d 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 · 26d ago · cactuscompute.com

  • Make your software self-driving

    AI · 30d ago · coldtea.ai

  • Soloop472

    Approval-first Agent OS for solo founders

    AI · 30d ago · soloop.io

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

  • 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 · 16d ago · simedw.com