Zenith: sota harness for normal models to beat Fable on FrontierSWE

What it does

Zenith is our long-running agent harness. Point it at a hard, long-running engineering task, and it builds a harness tailored to that task, runs the work, and tests it to the finish. On Frontier SWE, seventeen of the hardest public long-horizon software-engineering tasks we know of, Zenith took GPT-5.5 from 5th place to 1st, ahead of Claude Fable, by building the right harness around the model instead of swapping in a bigger one. That matters now because the strongest models are increasingly hard to reach. Fable 5's access was suspended under a US export-control directive and remains gated; GPT-5.6 launched as a limited preview for a small group of trusted partners. The system around the…from ii.inc

• 
  HarnessRouter Community EditionAug 2026 · harnessrouter.ai · ▲397

  Open-source unified interface for agent harnesses

• 
  Harness by Autonomous9d ago · autonomous.ai · ▲295

  Every coding agent, every machine, one command center.

• 
  Nemotron 3 Ultra by NVIDIAJun 2026 · developer.nvidia.com · ▲179

  Powers faster, efficient reasoning for long-running agents

• 
  GPT-6 Sol & LunaSep 2026 · openai.com · ▲350

  Frontier AI intelligence, now at half the price

• 
  Zot – Yet another coding agent harnessMay 2026 · zot.sh · ▲107

  A lightweight, single-binary coding agent harness written in Go. Anthropic, OpenAI, Kimi, DeepSeek, Google Gemini, Ollama, managed llama.cpp models, five built-in tools, three run modes, extensions in any language, and a built-in Telegram bridge.

• 
  FrontierHarness Eval – 9 harness, same model, cost per pass varies 17xSep 2026 · frontierharness.org · ▲82

  Same model. Similar pass rates. 17.5x cost differences across 12 harness configurations.

• 
  Spira Maxima▲578

  Video model that turns script into viral social media videos

  AI · 19d ago · spira.ai

• 
  Rill Browser▲540

  The browser where Claude Code and Codex work beside you

  AI · 19d ago · rill.love

• 
  Germany's new sovereign AI model Kolibri▲424

  Kolibri is Aleph Alpha

  AI · 21d ago · tej.as

• 
  Giving Opus 5.5 a simulated paint canvas▲392

  Paintings by AI models: programs run through a simulation of oil paint.

  AI · 22d ago · stillwet.art

• 
  Beam.win▲379

  Run AI agents on one Mac and use its windows on another

  AI · 6d ago · beam.win

• 
  FastRouter.ai▲364

  Route requests to the right LLM for cost, latency & quality

  AI · 23d ago · fastrouter.ai

• 
  Fundraisly▲1,537

  AI fundraising agent that finds investors and books meetings

  AI · Jun 2026 · fundraisly.com

• 
  Homebrew 6.0.0▲1,481

  Today, I’m proud to announce Homebrew 6.0.0. The most significant changes since 5.1.0 are a new tap trust security mechanism, the new faster, smaller, default internal Homebrew JSON API, sandboxing on Linux, better defaults informed by our user survey, many brew bundle improvements, improved performance and initial support for macOS 27 (Golden Gate). Happy to discuss any questions here!

  Dev tools · Jun 2026 · brew.sh

• 
  Performative-UI – A react component library of design tropes▲1,181

  Hi HN! I was super frustrated at apps like tiktok and wechat preventing me from saving or downloading the animated gifs, so I made a little tool to turn a screen recording into a slack-sized emoji. Hope you get some value from this!

  Life & fun · Jun 2026 · vorpus.github.io

• 
  Upstream▲976

  The inbox designed for humans and agents

  AI · Jun 2026 · upstream.do

• 
  Goldfish▲958

  Press Option. It knows your work and replies like you

  AI · Jun 2026 · goldfish.sh

• 
  I made Google Trends for Hacker News by indexing 18 years of comments▲822

  Search 18 years of Hacker News and chart how any topic, tool, or person trended. Overlay terms to compare their rise and fall across 45M posts and comments.

  Life & fun · Jun 2026 · hackernewstrends.com