Concept
multi-agent systems
A full explainer for this concept is being written. In the meantime, here's what's in the news.
In the news
agent-link — An end-to-end encrypted channel between coding agents, anywhere
GitHub · Aug 11, 2026
agent-claim-network — 面向终端的通用 AI 助手,让 Agent 之间共享可检索、可追溯且允许分歧的知识。让下一次判断,带着来源出发。
GitHub · Jul 31, 2026
council-lab — Local-first, human-participatory four-agent AI deliberation workspace
GitHub · Jul 27, 2026
The path to artificial superintelligence
MIT Tech Review · Jul 27, 2026
nova — AI-powered multi-agent classroom that turns any topic into an interactive learning experience
GitHub · Jul 20, 2026
collective-intelligence — Ailin¹ is an open-source collective intelligence engine where tens of thousands of AI models collaborate through dozens
GitHub · Jul 20, 2026
Multi-Agent Teams Hold Experts Back
Apple ML Research · Jul 2, 2026
Which Agent Causes Task Failures and When?Researchers from PSU and Duke explores automated failure attribution of LLM Multi-Agent Systems
Synced · Aug 14, 2025