Paul Sawers writes that Amazon Web Services (AWS) has released an open-source application called Pizza Bot, which provides developers with an email-inspired inbox to manage autonomous AI agents. Designed specifically for tasks that continue after a user has finished their session, the tool moves away from chat interfaces toward an asynchronous model where completed jobs arrive as threads and urgent decisions are surfaced for human triage.
- The project is now a standalone community project rather than an AWS service.
- It supports multiple models including Anthropic, Amazon Bedrock, Google Gemini, OpenAI, OpenRouter, or local models via Ollama.
- Built using LangGraph and DeepAgents to enable stateful agent execution and persistence through checkpoints.
- Available as a desktop app for macOS, Windows, and Linux, with browser and terminal clients also available.
- The project is now a standalone community project rather than an AWS service.
- It supports multiple models including Anthropic, Amazon Bedrock, Google Gemini, OpenAI, OpenRouter, or local models via Ollama.
- Built using LangGraph and DeepAgents to enable stateful agent execution and persistence through checkpoints.
- Available as a desktop app for macOS, Windows, and Linux, with browser and terminal clients also available.
Y Combinator is open-sourcing an agent harness called QM (short for quartermaster) designed to manage a fleet of agents for startups and YC employees. The system aims to provide flexible, easy-to-administer tools that can be used as personal assistants or assigned to specific projects to handle work-related tasks.
- It is intended to allow every employee and project to have their own agent as needed.
- This follows previous internal experiments with Ruby-based loops and Hermes agents.
- The codebase is available at github.com/yc-software/qm.
- It is intended to allow every employee and project to have their own agent as needed.
- This follows previous internal experiments with Ruby-based loops and Hermes agents.
- The codebase is available at github.com/yc-software/qm.
The QM repository provides a multiplayer agent harness designed specifically for startups, allowing multiple employees to have isolated workspaces while still collaborating via Slack or web interfaces. The system is built with an architecture that separates the core logic from specific model harnesses and deployment configurations, enabling users to switch between various providers like Claude Code or Codex without being tied to a single vendor. It offers tiered security postures—ranging from strict human approval for all tools to high-speed autonomous operation—and supports background work through scheduled crons and webhooks.
- Supports multiple backends including Pi, OpenCode, Codex, and Claude Code.
- Offers three distinct security modes: Strict (human intervention required), Auto (AI-driven screening), and Dangerous (no screening).
- Provides per-scope memory, files, keychain views, permissions, and durable sandboxes for each user or room.
- Includes an "individual auth" feature where users can connect their own AI accounts to keep usage credentials separate from the organization's shared keys.
- Supports multiple backends including Pi, OpenCode, Codex, and Claude Code.
- Offers three distinct security modes: Strict (human intervention required), Auto (AI-driven screening), and Dangerous (no screening).
- Provides per-scope memory, files, keychain views, permissions, and durable sandboxes for each user or room.
- Includes an "individual auth" feature where users can connect their own AI accounts to keep usage credentials separate from the organization's shared keys.
Pedro Cuenca writes Meta released Muse Glimmer-30B, a local, open-source multimodal model distilled from its larger Muse architecture. Designed for agentic workflows, it combines a 28B text decoder with a 2B vision encoder, supporting image, video, and multimodal tool calling out of the box. The release includes immediate compatibility with major inference frameworks like transformers, llama.cpp, and vLLM, alongside built-in speculative decoding for faster generation.
- Features a hybrid attention pattern alternating between three sliding window layers and one full attention layer.
- Incorporates a DFlash block-diffusion drafter to accelerate structured text generation like coding.
- Supports fine-tuning via TRL with practical minimums ranging from one to eight H100 GPUs depending on the method.
- Demonstrates autonomous agent capabilities such as self-quantization, self-deployment, and hardware-specific optimization.
- Features a hybrid attention pattern alternating between three sliding window layers and one full attention layer.
- Incorporates a DFlash block-diffusion drafter to accelerate structured text generation like coding.
- Supports fine-tuning via TRL with practical minimums ranging from one to eight H100 GPUs depending on the method.
- Demonstrates autonomous agent capabilities such as self-quantization, self-deployment, and hardware-specific optimization.
Asif Razzaq writes that NVIDIA Labs has open-sourced NOOA, a model-agnostic Python framework designed to streamline agentic development by consolidating prompt templates, tool schemas, and state into single class structures. By treating LLM-driven actions as standard methods with docstrings serving as prompts, the framework allows developers to build autonomous workflows that can be tested, traced, and version-controlled like ordinary software.
- Achieves 82.2% on SWE-bench Verified while using roughly half the tokens required by existing open harnesses.
- Employs a "pass by reference" mechanism for live Python objects via bounded previews to conserve context window space.
- Features an optional memory subsystem that utilizes SQLite and ACT-R activation ranking for record retrieval.
- Achieves 82.2% on SWE-bench Verified while using roughly half the tokens required by existing open harnesses.
- Employs a "pass by reference" mechanism for live Python objects via bounded previews to conserve context window space.
- Features an optional memory subsystem that utilizes SQLite and ACT-R activation ranking for record retrieval.
Page Assist is an open-source browser extension that provides a sidebar and web interface for interacting with local large language models from any webpage. It allows users to chat about current website content by connecting the tool to providers like Ollama or OpenAI API compatible endpoints. The software supports several browsers, including Chromium-based options and Firefox.
- Data is stored locally within browser storage to maintain privacy
- Features keyboard shortcuts such as Ctrl+Shift+Y for rapid sidebar access
- Compatible with various local model providers, including Chrome AI (Gemini Nano)
- Data is stored locally within browser storage to maintain privacy
- Features keyboard shortcuts such as Ctrl+Shift+Y for rapid sidebar access
- Compatible with various local model providers, including Chrome AI (Gemini Nano)
The community-led open-source hosting site Codeberg has announced bans on two types of projects: cryptocurrency-related projects and those whose code is substantially or entirely generated by Large Language Models (LLMs) such as Claude or OpenAI Codex. Following a community vote, the ban on LLM-generated code passed with 358 votes in favor to 144 against. The reasoning for these decisions includes concerns over "license whitewashing," the massive increase in hardware and energy costs caused by AI datacenter scaling, and the potential negative impact of generative AI tools on the Open Source Software (OSS) community.
The comments reflect a deep division within the tech community regarding this decision:
* **Supporters** argue that current LLM practices are unethical because they undermine software rights, increase environmental strain, and create massive amounts of "junk" code that is difficult to maintain or scale.
* **Critics/Skeptics** suggest the ban is a "Luddite" reaction to an unstoppable trend (comparing it to people refusing cell phones). They argue that LLMs are already integrated into most workflows ("the toothpaste is out of the tube") and that banning them might be impossible or impractical.
* **Nuanced Perspectives** emerge from users who distinguish between using LLMs as a "reasoning tool" for scientific/mathematical scaffolding versus pure "vibe coding." Some argue that while full generation creates maintenance risks, LLM tools are essential assets for hobbyists and professionals alike to solve problems efficiently.
The comments reflect a deep division within the tech community regarding this decision:
* **Supporters** argue that current LLM practices are unethical because they undermine software rights, increase environmental strain, and create massive amounts of "junk" code that is difficult to maintain or scale.
* **Critics/Skeptics** suggest the ban is a "Luddite" reaction to an unstoppable trend (comparing it to people refusing cell phones). They argue that LLMs are already integrated into most workflows ("the toothpaste is out of the tube") and that banning them might be impossible or impractical.
* **Nuanced Perspectives** emerge from users who distinguish between using LLMs as a "reasoning tool" for scientific/mathematical scaffolding versus pure "vibe coding." Some argue that while full generation creates maintenance risks, LLM tools are essential assets for hobbyists and professionals alike to solve problems efficiently.
Google's release of Gemma 4 marks a major turning point for open-source AI, offering a versatile family of multimodal models under a permissive Apache 2.0 license. Built using Gemini 3 technology, these models demonstrate massive leaps in math and coding performance, rivaling much larger proprietary systems while remaining efficient enough to run on local hardware ranging from smartphones to high-end GPUs. This release positions Google as a formidable competitor in the open-weights ecosystem, prioritizing user ownership and deployment efficiency.
* Apache 2.0 license
* Multimodal intelligence
* Local hardware deployment
* Massive benchmark leaps
* Efficient MoE architecture
**Models**
* E2B: Mobile efficiency
* E4B: Edge specialist
* 26B MoE: Speed meets intelligence
* 31B Dense: Top-tier performance
* Apache 2.0 license
* Multimodal intelligence
* Local hardware deployment
* Massive benchmark leaps
* Efficient MoE architecture
**Models**
* E2B: Mobile efficiency
* E4B: Edge specialist
* 26B MoE: Speed meets intelligence
* 31B Dense: Top-tier performance
Open Code Review is an AI-powered CLI tool designed for automated, high-precision code reviews. Originally developed as Alibaba Group's internal assistant, the project uses a hybrid architecture that combines deterministic engineering with LLM agents to provide stable and accurate feedback. Unlike general-purpose agents, it employs smart file bundling and fine-grained rule matching to maintain context and prevent issues like position drift or incomplete coverage on large changesets.
Key features:
- AI-driven line-level review comments
- Hybrid architecture combining hard constraints with dynamic decision-making
- Support for various LLM endpoints including OpenAI and Anthropic
- Seamless integration with CI/CD pipelines and coding agents like Claude Code
- Customizable rule sets for specific project requirements
Key features:
- AI-driven line-level review comments
- Hybrid architecture combining hard constraints with dynamic decision-making
- Support for various LLM endpoints including OpenAI and Anthropic
- Seamless integration with CI/CD pipelines and coding agents like Claude Code
- Customizable rule sets for specific project requirements
Anthropic has released an open-source project called Claude Desktop Buddy that allows ESP32-S3 hardware to act as a physical companion for the Claude desktop application. By utilizing a new Bluetooth Low Energy (BLE) API, these small devices can provide real-time updates on AI agent activity and allow users to approve or deny permission requests directly through physical buttons.
Key features and details:
- Connects via BLE to macOS and Windows desktop apps for fast, local interaction
- Features Tamagotchi-style animations that reflect the AI's status, such as sleep, busy, or attention modes
- Supports custom character skins using user-provided GIF packs
- Optimized for ESP32-S3 boards like the M5StickC Plus and M5Stack Cardputer
- Developed using the Arduino framework and PlatformIO
Key features and details:
- Connects via BLE to macOS and Windows desktop apps for fast, local interaction
- Features Tamagotchi-style animations that reflect the AI's status, such as sleep, busy, or attention modes
- Supports custom character skins using user-provided GIF packs
- Optimized for ESP32-S3 boards like the M5StickC Plus and M5Stack Cardputer
- Developed using the Arduino framework and PlatformIO
