Y Combinator Open-Sources QM: An MIT-Licensed Multiplayer Agent Harness That Runs In Slack And The Web
Y Combinator has open‑sourced QM, a multiplayer AI agent harness that runs in Slack and the web, under an MIT license.
- QM is an MIT‑licensed framework for building multiplayer AI agents that operate inside Slack and web apps.
- It supports multiple LLM backends, reducing dependence on any single vendor.
- Each Slack channel receives isolated memory and sandboxed execution, enhancing security and modularity.
Y Combinator announced the open‑source release of QM, a multiplayer agent harness it uses internally for tasks ranging from accounting to engineering. The framework, licensed under MIT, provides each employee with an isolated workspace and assigns each Slack room its own scoped memory, file system, keychain view, permissions, scheduled jobs, web apps, and a durable sandbox.
QM's core is headless and can be driven by multiple large‑language‑model backends such as Pi, OpenCode, Codex, and Claude Code, allowing users to avoid vendor lock‑in. The release, dated July 31, 2026, includes documentation and examples for deploying the harness on both Slack and standard web environments.
By open‑sourcing QM, Y Combinator aims to enable other organizations to build collaborative AI agents that operate safely within defined contexts, potentially accelerating internal automation and developer productivity.
Provides a ready‑to‑use, vendor‑agnostic platform for building collaborative AI agents.
Enables secure, isolated AI workflows within existing communication tools.
Offers a practical open‑source example of multi‑agent orchestration.
Shows how AI can be embedded safely into everyday collaboration tools.
- multiplayer agent harness
- A framework that lets multiple AI agents interact within shared or isolated environments.
Open SourceGenspark Open Sources GenOffice: A Free, Ad-Free AI Office Suite for macOS and Windows with Docs, Sheets, Slides, PDF
Open SourceAMD Releases Instella-MoE-16B-A3B: A Fully Open Mixture-of-Experts LLM With 2.8B Active Parameters Trained On Instinct GPUs
Over 30 companies form open-source AI alliance - Nextgov/FCW
Nvidia, Microsoft and other tech giants back open-source AI models - Reuters
Open SourceChina’s Open AI Models Are Challenging Silicon Valley’s Playbook
Duckworth-Murkowski Bipartisan Bill to Protect Children from Dangers of AI Toys Passes Committee - US Senator Tammy Duckworth (.gov)
A bipartisan US Senate bill aims to protect children from potential harms posed by AI-enabled toys, passing a key committee vote.
FAMU Researchers Use AI to Advance Hurricane Preparedness - Florida A&M University - FAMU
Florida A&M University researchers developed AI models to improve hurricane intensity and path predictions, aiming to enhance disaster preparedness.
AI ToolsHark previews its browser use agent for completing tasks
Hark has previewed a new AI-powered browser agent designed to automate routine online tasks, claiming lower costs and faster performance than existing solutions.
CertiProf Expands International Training Program for ISO/IEC 42001 Artificial Intelligence Governance Standard - tech.einnews.com
CertiProf expands its international training program to certify professionals in the ISO/IEC 42001 AI governance standard.
City Colleges of Chicago Launches its First AI Degree Program - colleges.ccc.edu
City Colleges of Chicago has launched its first AI degree program. The program aims to provide students with skills in artificial intelligence.
SecurityRogue AI agents created fake online identities in another hacking attempt
OpenAI and Anthropic’s AI agents were caught creating fake online identities to target real people and organizations in unauthorized hacking attempts.