LayerFS: The filesystem for AI coding agents(layerfs.ai)
59 points by l2dy | 47 comments
Landing page for LayerFS, a filesystem giving AI coding agents ephemeral writable workspaces over shared committed history.
#multi-agent on Hacker News
10 stories tagged multi-agent, newest first.
How I manage persistent Claude Code loops: Spool(github.com)
7 points by enesalatas | 3 comments
GitHub repository for Spool, a self-hosted fleet of persistent Claude Code agents in containers that users interact with via Telegram and Slack.
AI agents in a stand-up call(atoll92.github.io)
32 points by jonbaer | 37 comments
Landing page for Agent Standup, a tool that visualizes Claude Code sessions as a live stand-up meeting where a lead agent directs sub-agents who report back.
Show HN: Raven – The harness of harnesses, built for RSI(github.com)
49 points by cyfyifanchen | 39 comments
GitHub repository for Raven by EverMind-AI, a self-evolving multi-agent ecosystem billed as a 'harness of harnesses' for recursive self-improvement.
CEO fired developers to make room for AI. Developers create open source AI CEO(github.com)
852 points by GrumpySciGuy | 585 comments
GitHub repository for OpenExecutive, an open source AI virtual executive team built from 8 specialist Claude agents using FastAPI and Next.js.
Codex starts encrypting sub-agent prompts(github.com)
375 points by embedding-shape | 226 comments
GitHub issue in openai/codex reporting a regression where encrypted MultiAgentV2 sub-agent messages remove the readable task audit trail.
ZCode – Harness for GLM-5.2(zcode.z.ai)
484 points by chvid | 322 comments
Landing page for ZCode 3.0, a desktop AI coding agent tool by Z.ai optimized for the GLM-5.2 model, with download links for macOS.
We tasked Opus 4.6 using agent teams to build a C Compiler(anthropic.com)
690 points by modeless | 664 comments
Anthropic engineering blog post describing how teams of parallel Claude Opus 4.6 agents built a C compiler with minimal human involvement.
Orchestrate teams of Claude Code sessions(code.claude.com)
371 points by davidbarker | 202 comments
Claude Code documentation page explaining experimental agent teams, which coordinate multiple Claude Code sessions with shared tasks, inter-agent messaging, and a team lead.
Claude Code's new hidden feature: Swarms(twitter.com)
472 points by AffableSpatula | 305 comments
An X post describing a hidden multi-agent 'Swarms' feature in Anthropic's Claude Code, linked alongside a GitHub tool for enabling unreleased features.