AI Peer Review
One AI writes the code. Two others tear it apart.
What it does
A browser-based tool that lets multiple AI models collaborate on your code. Describe what you want to build. Three modes handle the rest: 🔍 Review Mode — one model codes, another reviews and corrects it 🏗️ Companion Mode — one model architects, the other implements ⚔️ Challenge Mode — both models compete, results shown side by side Supports Gemini, ChatGPT and Claude Sonnet. No backend. Your API keys never leave your browser. 100% open source.
Does the same job
all alternatives →
- MCMysti – Claude, Codex, and Gemini debate your code, then synthesizeDec 2025 · github.com · ▲216
Hey HN! I'm Baha, creator of Mysti. The problem: I pay for Claude Pro, ChatGPT Plus, and Gemini but only one could help at a time. On tricky architecture decisions, I wanted a second opinion. The solution: Mysti lets you pick any two AI agents (Claude Code, Codex, Gemini) to collaborate. They each analyze your request, debate approaches, then synthesize the best solution. Your prompt → Agent 1 analyzes → Agent 2 analyzes → Discussion → Synthesized solution Why this matters: each model has different training and blind spots. Two perspectives catch edge cases one would miss. It's like pair…
- APAI Peer Reviewer – Multiagent system for scientific manuscript analysis2025 · github.com · ▲108
After waiting 8 months for a journal response or two months for co-author feedback that consisted of "looks good" and a single comma change, we built an AI-powered peer review system that helps researchers improve their manuscripts rapidly before submission. The system uses multiple specialized agents to analyze different aspects of scientific papers, from methodology to writing quality. Key features: 24 specialized agents analyzing sections, scientific rigor, and writing quality // Detailed feedback with actionable recommendations. // PDF report generation. //…
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
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
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
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
