At its developer conference, Box announced Box Content Retrieval, a feature that embeds Nvidia's Nemotron embedding system into the core of its product so agents can answer queries using Nemotron-generated embedded metadata. Box says this yields faster, more accurate and less expensive queries, while Nvidia's Kari Briski told TechCrunch she expects answers four times faster, 20% fewer errors and 90% fewer tokens used. The feature implements Nvidia's Nemotron Embed project and its open-weight embedding models, and will roll out to all Box Enterprise Advance customers early next year.
What problem it solves
Pi is designed for developers who need to adapt an agent to their own workflows rather than work within a fixed feature set. It provides interactive, automated, RPC, and SDK interfaces while leaving optional capabilities such as sub-agents and plan mode to extensions or packages.
Key features
Extensible agent harness — Customize the harness with extensions, skills, prompt te…
What problem it solves
Building WebGL2 and WebGPU visualizations for large data sets requires handling rendering, updates, interaction, cartographic projections, and basemap integration. deck.gl addresses these concerns through composable layers and an extensible architecture that can also be adapted to custom use cases.
Key features
Composable visualization layers — Data is mapped into visual lay…
What problem it solves
AI-generated presentation workflows can produce decks that are difficult to refine because elements are flattened or confined to a fixed template. PPT Master addresses this by generating native PowerPoint objects that remain editable, while supporting multiple source formats, existing templates, transitions, animations, and narration.
Key features
Native, editable PowerPoint…
What problem it solves
Computer-use projects need environments where agents can operate applications, run code, and interact with graphical interfaces within the same task. They also need repeatable ways to create tasks, evaluate agents, export trajectories, and generate data for training and research.
Key features
Shared desktop Spaces — Cua Spaces gives agents full desktops hosted on computers o…
What problem it solves
AI agents need isolated environments that can execute code and workloads while supporting fast creation, secure network access, and manageable state. They also need an interface that can integrate with existing agent tooling and deployment workflows.
Key features
Hardware-level isolation — Each sandbox runs in its own MicroVM with a dedicated operating system kernel. Kernel-…
What problem it solves
UI components and pages need to be developed, tested, and documented independently from a complete application. Storybook provides an isolated workshop and an extensible API for these activities.
Key features
Isolated component workshop — Build and inspect UI components and pages in isolation, supporting focused work across development, testing, and documentation.
Source: RE…
What problem it solves
Running and training models locally requires tools for model execution, fine-tuning, agent integration, and deployment across different model formats and hardware. The project brings these workflows into a desktop app, a web UI, and a code-based version.
Key features
Run and train models — Run and train language, diffusion, decision, embedding, audio, image, and video models…
What problem it solves
Web applications need a straightforward way to add animations, gestures, layout transitions, scroll-linked effects, and timelines across JavaScript, React, and Vue. The project provides a shared animation library with a simple API, TypeScript support, a test suite, and tree-shakable packages.
Key features
Framework Packages — Motion provides dedicated packages for React, Jav…
What problem it solves
Autonomous agents accumulate state, require strict isolation, call model APIs and tool servers, and can continue consuming resources without supervision. AX addresses these requirements through declarative primitives for sandboxed execution, prepared workspaces, model configuration, lifecycle control, and direct inspection.
Key features
Declarative task manifests — Tasks, wo…
What problem it solves
People need a way to delegate research, writing, code review, recurring tasks and work across connected tools to AI agents without giving up control over actions and data. They also need a foundation for embedding agent loops, tool calls, approvals, streaming and durable sessions into their own applications.
Key features
Everyday AI coworker — The desktop app supports resear…
What problem it solves
AI clients change between sessions, making it difficult to preserve context, recover earlier decisions, and continue unfinished work. The project provides a local Markdown-based memory that records selected information and retrieves it with its source in later sessions without automatically converting the entire conversation history into knowledge.
Key features
Persistent Ma…
What problem it solves
Local videos, capture cards, game streams, and images need a unified way to preview and enhance visual output in real time. Veyra addresses this with a Windows pipeline that combines multiple enhancement stages, configurable processing workflows, capture sources, and export tools.
Key features
Real-time enhancement pipeline — Combine super-resolution, noise reduction, HDR pr…
What problem it solves
AI agent skills need to be checked for quality, security, duplication, and their actual effect on agent behavior. Static checks alone cannot establish whether guidance improves task results, so evaluation must also support live comparison with and without a skill.
Key features
Three-tier evaluation pipeline — Independent tiers validate skill safety and structure, detect over…
What problem it solves
Quantum programs require circuits, measurements or observables, and execution through primitives. Preparing those programs for real quantum hardware also requires rewriting circuits to account for hardware basis gates and connectivity.
Key features
Quantum circuit construction — Build quantum programs with circuits and standard quantum gates using the Python API.
Source: REA…
What problem it solves
Terminal users need a workspace that combines an approachable initial experience with advanced layout, collaboration, and automation capabilities. The project aims to support both beginners and experienced users without requiring them to trade simplicity for power.
Key features
Approachable terminal workspace — The workspace is designed to provide a useful out-of-the-box exp…
What problem it solves
A coding-agent run can skip planning, omit tests, review its own work, or stop before completion, making delivery inconsistent and difficult to supervise. Teams need repeatable workflows that separate roles, execute work in sandboxes, preserve review evidence, and require human approval before changes ship.
Key features
Repeatable SOP delivery — Standard operating procedures…
What problem it solves
Database users need a client that remains responsive while browsing large tables and connecting to multiple database engines. DBDelve addresses this with a native Rust and GPUI interface that avoids Electron and JVM dependencies while keeping its core features free and open source.
Key features
Broad database support — Connect to Postgres, MySQL, MariaDB, SQLite, Turso, Duck…
What problem it solves
The project aims to provide a complete, usable browser for the modern web while using an independent engine built around web standards. It also separates site rendering and sensitive workloads into sandboxed processes to improve robustness against malicious content.
Key features
Standards-based engine — The browser uses a novel engine based on web standards and includes libr…
Performance optimization usually starts with a clear goal: completing the same work faster. What really takes time is identifying bottlenecks, designing experiments, comparing candidates, and then determining whether the differences come from the code or from measurement noise. After handing this process to an Agent, there is another kind of cost: repeatedly organizing logs, waiting for long-runni…
What problem it solves
Personal AI agents need to connect language model providers, communication channels, and tools while remaining under the user's control. They also need configurable autonomy, security boundaries, and operational features such as background services, approvals, and persistent workflows.
Key features
Multiple channels and providers — The agent can receive messages through conf…