Ai Agents

Page 4 of 10

  1. LLM Council: Run Your Own Multi-Model Debate Panel with Karpathy's 400-Line App

    Andrej Karpathy's LLM Council (23.8k stars) turns one AI into a boardroom: multiple frontier models answer your query independently, anonymously review each other's work, …

    Open Source
  2. Jeff Dean's 1% Rule: How to Choose What to Build in the Age of Frontier AI

    Google's Chief Scientist Jeff Dean gave founders a brutally simple framework at YC Startup School 2026: build only where frontier models succeed 0-1% of the time, never …

    AI
  3. Pi Coding Agent: The Minimalist Harness That's 2x Cheaper Than Claude Code (Databricks Benchmark)

    Pi is the terminal-first coding agent with only 4 tools and a 200-token system prompt. Databricks found simple harnesses like Pi cut cost-per-task by 2x at equal quality …

    AI
  4. QM: YC's Open-Source Multiplayer Agent Harness for Slack and Web

    QM is Y Combinator's open-source multiplayer agent harness that gives every employee an isolated workspace while letting teams collaborate with AI in Slack channels. …

    Open Source
  5. Symphony: OpenAI's Multi-Agent Collaboration Framework

    Single AI agents are powerful, but complex real-world tasks often require more than one perspective. A software project needs someone to write code...

    AI
  6. OpenManus: Open-Source Framework for Building General AI Agents with 55K Stars

    The open-source AI agent landscape has a new leader. OpenManus, developed by FoundationAgents (the same team behind MetaGPT), has rapidly grown to...

    Open Source