Developer guuguo open-sourced MemoryGuardian, a native SwiftUI utility that attributes Node.js processes to ChatGPT, Codex, MCP services, projects, and application hosts on macOS. The author reports that one local snapshot showed 113 processes and 12.1 GiB attributed to ChatGPT and Codex, while another peak reached 403 processes and 17.4 GiB. Its cleanup features require manual confirmation and use conservative checks to avoid terminating active MCP connections or ongoing tasks.
The FBI and U.S. Department of Justice announced action against FaceStealer, a North Korean social-engineering campaign that uses spear-phishing, AI deepfakes, stolen contact details and recorded victim videos to conduct multi-stage attacks. The FBI said it seized cloud infrastructure containing 900 victim videos, attributed about $400 million in stolen cryptocurrency to the campaign, and found attempts to compromise JavaScript/NPM modules and Rust crates; Tom’s Hardware also reported linking the recent Binance hack, involving more than $5 billion, to the campaign.
The author of the DeepSeek Harness plugin dsh-plugin-roundtable reports that a read-only AI audit identified 58 issues, including three release-blocking defects in the publication workflow: an outdated pnpm lockfile, an npm publish command without an explicit tag, and a stale latest distribution tag. The author says each finding included a file path and line number, and that they cross-checked the findings against the codebase. The report also describes user-facing bugs, including a feedback prompt that reappeared, a session-switching issue that could affect another meeting, and a NaN budget value that prevented circuit breaking. It lists the test count as 170 before the changes and 182 afterward, without establishing that the fixes caused the increase.
The author released scx 0.11.0, a zero-dependency Rust tool that compresses logs, command output, diffs, and stack traces for LLMs while retaining original wording. It identifies evidence lines through IDF-weighted lexical matching, preserves their surrounding context, and enforces token limits by reporting overflow rather than silently discarding evidence. The release is available through crates.io, GitHub Releases, Homebrew, and npm, with an MCP server for integration into agent workflows.
After recording 517 approval prompts in one day while using DSH for AI-assisted coding, a developer created dsh-sandbox-tune to reduce interruptions without globally enabling danger-full-access. The plugin redirects tool caches, offers opt-in user-directory permissions, validates commands under opt-in approval rules, and supports session-level overrides for eligible settings. The developer reports that prompts no longer appeared in several common commands after installation and that daily development was largely uninterrupted. The same account says the project has about 3,700 lines of code, 171 unit tests, 10 integration tests, and support for macOS, Linux, and Windows; no independent testing or adoption data was provided.
Databricks published research on LLM triage of malicious npm packages, based on samples collected since November 2025: of 11,413 package-versions corroborated through OSV malware advisories, 96.2% hid payloads in source or fetched them externally, while 3.8% (432) bundled a binary. The authors report that binary-bearing packages fail to reach a decisive malicious verdict more than twice as often as source-only ones (14.4% vs 6.2%), and describe failure modes including dismissal, hedging, confabulation and lower assigned severity for more heavily obfuscated payloads. They propose injecting pre-computed static evidence and domain knowledge at inference, which they say improves detection quality for both budget and frontier models.
Bloom Security's SlugFest research identified more than 1,500 npm packages, with over 10 million combined downloads, vulnerable to a publishing attack involving GitHub repository addresses. The flaw stemmed from npm Trusted Publishing initially binding trust to a repository's human-readable slug rather than its immutable identifier, so old addresses could be reclaimed after renames, transfers or deletions. Bloom also reported that AI agents install about 70 packages a month on a typical endpoint and close to 350 on developer machines, and said npm has implemented and confirmed a fix.
What problem it solves
Coding agents need both exact design values and the rationale for applying them consistently. Without a structured, persistent representation of a design system, agents may miss design context or interpret visual guidance inconsistently.
Key features
Structured tokens and design rationale — The format combines machine-readable design tokens with human-readable Markdown ratio…
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
Technical teams need CRM structures that can accommodate complex business needs and change as those needs evolve. They also need a way to extend CRM objects, views, workflows, and agents through code while supporting cloud, self-hosted, and local development workflows.
Key features
Code-defined CRM extensions — Developers can define objects, fields, and views as code, then p…
What problem it solves
Building agents often requires distributing core capabilities across conventions that make projects harder to inspect and operate. Eve places instructions, tools, skills, channels, schedules, and runtime configuration in conventional filesystem locations so agents can be inspected, extended, and maintained directly.
Key features
Filesystem-based authoring — Agent capabilitie…
What problem it solves
Web teams and developers can need to rebuild an existing site in a modern codebase when migrating platforms, recovering lost source code, or learning how a production site is constructed. This template gives an AI coding agent a repeatable workflow for recreating a site as an editable Next.js application while comparing its appearance and behavior with the source.
Key featur…
What problem it solves
jQuery provides DOM operations for browser and non-browser environments. Projects can also tailor a build to include or exclude the modules they need.
Key features
Broad environment support — jQuery can be used in browsers, Node, browser extensions, and other non-browser environments.
Source: README
Customizable module builds — The build script can exclude unnecessary module…
What problem it solves
Turning an app idea into a clear screen design and implementation brief usually requires assembling layouts, interactions, and Material 3 Expressive styling before handing work to an AI coding tool. This project provides a browser-based sketchpad that turns those design choices into an editable prompt.
Key features
Sketch with Material 3 Expressive parts — Build phone or des…
What problem it solves
Package managers can duplicate identical package files across projects, consuming substantial disk space. Monorepos also need deterministic dependency resolution and clear rules that prevent packages from accessing dependencies they have not declared.
Key features
Content-addressable storage — Package files are kept in a single content-addressable store and linked into proje…
What problem it solves
Building AI applications and agents requires coordinating models, tools, execution flows, context, integrations, and production operations. Mastra provides a TypeScript framework that supports these concerns across prototypes and production-ready applications.
Key features
Model routing — Connect applications to models from multiple providers through a common interface.
Sour…
What problem it solves
Agents connecting to proprietary business data need high-quality context without context explosion, decay, pollution, or excessive token use. They also need executable actions that are explainable, traceable, permission-aware, and protected by governance controls.
Key features
Context Loader — Organizes and ranks multi-source candidates through the BKN semantic network, then…
What problem it solves
Web projects need consistent formatting and linting workflows that can be used from both command-line and editor environments. The project provides these maintenance capabilities as a unified toolchain.
Key features
Integrated formatting and linting — Format project code and identify lint issues through a unified toolchain.
Source: packages
Command-line workflow — Run format…
What problem it solves
Backend applications need an architecture that remains organized as they grow from small APIs into systems used by multiple teams. They also need consistent places for dependency injection, validation, authentication, error handling, and other common backend concerns.
Key features
Progressive application architecture — The framework provides application modules and dependenc…
What problem it solves
Monitoring global news, geopolitical activity, markets, conflicts, infrastructure, and other live signals requires bringing information from many domains into one view. The project addresses this with a unified situational awareness interface that combines curated feeds, maps, correlation, analytics, and programmatic access.
Key features
Curated global intelligence — Curated…
What problem it solves
Building AI chat experiences in React requires assembling chat primitives, runtime integrations, generative UI, and production UX details. The project provides a composable library that supports multiple backends, custom styling, and strongly typed APIs.
Key features
Composable Chat Primitives — Build a chat interface from primitives including Thread, Message, Composer, Thre…
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
Story creation often requires coordinating ideas, settings, characters, continuity, review, revision, covers, interactive state, and multilingual delivery. InkOS addresses this by giving different creative formats a shared workbench and harness that manages context, state, and artifacts.
Key features
Unified production harness — Studio Chat, the TUI, CLI interaction, and pro…
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 coding tools often expect particular provider protocols, making it difficult to use the models and providers a user prefers. A local gateway can translate between supported client APIs and provider APIs while preserving capabilities such as streaming, tool calls, reasoning, and images.
Key features
Provider protocol translation — The gateway translates Responses, Chat Com…
What problem it solves
Coding agents need a consistent way to inspect, control, debug, and verify applications across mobile, web, TV, and desktop targets. They also need repeatable workflows and reviewable evidence across local devices, simulators, CI, and remote device clouds.
Key features
Inspect and control app interfaces — Agents can read accessibility snapshots, act through refs and selector…