DriftGuard, a new open-source tool for detecting response drift in LangGraph agents, was released on Hacker News. It uses embedding-based comparison to flag when an LLM strays from its intended domain…
Ploof, an agent-native CLI for generating images, video, and audio, has been released on GitHub. The tool is designed to be operated by coding agents like Claude Code, Cursor, or Codex, which can inst…
A new open-source Playwright CLI tool called 'brow' achieves 82% task success at approximately $0.22 per task, outperforming browser-use, playwright-mcp, and agent-browser on 22 benchmark tasks. The t…
ZUSE Automat Agent v1.11 achieves 69.1x causal compression of a period-15 cellular automaton oscillator, reducing 25 cells over 12 steps to recover defect_state0 in 20/20 trials. The deterministic sys…
Talon, an open-source agentic AI harness, launched with support for Telegram, Discord, Microsoft Teams, and terminal, offering pluggable backends including Claude Agent SDK, Kilo, OpenCode, Codex, and…
Developer Ayush has released Screenmind, an open-source, privacy-first alternative to Microsoft Recall that runs vision models locally on device. The tool captures and indexes screenshots, enabling se…
A developer created cmux-orchestrate, a Claude Code skill that enables driving cmux terminal panes, splits, tabs, and agents via the cmux CLI. The skill provides comprehensive control over terminal la…
A developer created 'orchestrate-plan', a Claude Code skill that executes a locked PLAN.md by delegating implementation to cmux worker panes one phase at a time, clearing context between phases. The s…
FAME Knowledge Agent Gateway, an open-source external memory and tool-safety gateway for local coding agents, has been released. It combines a graph knowledge net, project memory, tool-call governance…
A developer released 25 open-source executable skills for AI coding agents that fix common problems like token waste, bug multiplication, and context loss. The skills, available for Claude, Cursor, Op…
An open-source benchmark for prompt-injection detectors has been released, measuring both attack catch rate and false positives on real traffic in a threshold-agnostic way. The benchmark evaluates ten…
Brain.md, an open standard for persistent project memory, allows coding agents to store and retrieve durable knowledge as plain Markdown files in a repository, ensuring decisions and constraints outli…
VibeRaven, a new open-source tool for AI coding agents, provides production workflows that enforce evidence-based task completion, separating code fixes from provider dashboard work and requiring appr…
Sidequest, a new extension for the Pi AI agent, provides a side channel for context-aware questions without disrupting the main conversation. It offers threaded, persistent, and tool-capable interacti…
Developer Matthias Nordwig released pdf-struct-chunker, an open-source PDF chunker written in pure Rust that splits documents into semantically meaningful chunks by analyzing layout features like X/Y …
SpecManager, a Claude Code plugin that replaces ad-hoc vibe coding with a gated spec-driven development lifecycle, has been released as an MIT-licensed open-source tool. The plugin enforces a PRD-to-w…
A new open-source tool allows developers to create sandboxed Telegram agents with rich-text formatting using a single YAML config file. Built on Deno, the tool supports customizable system prompts and…
A developer released a plugin for Claude Code that allows users to draw feedback directly onto a frontend and send it to Claude for implementation. The tool uses Playwright MCP and an annotation toolb…
Microsoft and NVIDIA's new Spark PCs, featuring Grace CPU and Blackwell GPU, enable local frontier-model execution. The Spark Governance SDK introduces a governance layer for agent-native Windows RTX …
Developer Constantinos Pigiotis released an open-source Agent Skills plugin that teaches AI coding agents how to build hypermedia-driven UIs with htmx. The plugin covers htmx attributes, triggers, tar…