Persistent multi-agent research loop
A research system that runs competing implementations in parallel, evaluates them into structured evidence, and uses that evidence to guide later generations.
From Github Awesome — GitHub Trending Monthly #10（2026.08） at 03:36
Problem: Makes iterative agent research repeatable, inspectable, resumable, and evidence-driven.
For: Teams with an already runnable project that need persistent agent-based research.
Products from this video
Amadeus Protocol Node Amagine3D Amazon S3 Anatomy Atelier Anti Slop anydoc ARC-AGI-1 Task Generator arc-task-gen claudish-to-english claudish-to-english code-server Comp AI CRM Comp AI CRM Cumora DeepSeek Harness FrontierAgent FuXi fx Gemma Translator Gemma Translator h3.c IP as Logo IP as Logo Skill JoyAI-Video-Edit Kage Kimi K3 in C macOS MangoDisk Model Context Protocol (MCP) Moli morphicons MyContext npm OpenBot openGym Phone Harness Phone Harness Praxist Python Raspberry Pi 5 React Rust Scroll Craft Sol Advisor SQLite terminal-code Three.js ThreeUI TypeScript unlazy V8 Virtual Mac on iPad walgit Xcode Zig ZSvirt
Examples
- PRAXIST provides parallel research runs with task-owned evaluation.