LHIC (Local Human Intent Computer) is a deterministic browser automation runtime that executes known workflows locally without calling LLMs or relying on screenshots, achieving millisecond-level respo…
A Quesma researcher burned through an entire Claude team x5 plan token limit in 30 minutes while researching AI agent tokenomics, prompting a redesign that uses multiple subscription services and chea…
A developer built Docket, a control plane for running OpenClaw AI agents across projects, rewriting it from Bash to Python. The tool manages pods of agents with context isolation, spend caps, and appr…
Google LLC rebranded its AI-powered research assistant NotebookLM as Gemini Notebook, integrating it into the Gemini app and Google Search's AI Mode while adding secure cloud computing for deeper anal…
Google has renamed NotebookLM to Gemini Notebook and announced that the Gemini 3.5 and Antigravity upgrade, which began rolling out to AI Ultra users last month, will soon be available to AI Pro subsc…
A developer built Caider, a Mac app that turns a computer into a hands-off coding agent by integrating with GitHub issues to resolve them using local AI agents without needing to open separate AI apps…
Google has been named a Leader in the 2026 IDC MarketScape for Worldwide Foundation Model Software, highlighting its integrated AI stack and enterprise-focused approach. The company attributes the rec…
A developer built Gubernator, a lightweight container orchestrator in Go that combines Docker Compose simplicity with Nomad-like decentralized targeting. The project, co-authored with Google DeepMind'…
Agentmetry, an open-source flight recorder and security layer for AI agent tool-use, captures every tool call with MITRE ATT&CK enrichment and SHA-256 argument hashing, storing the trail locally in JS…
A developer built Bothread, a free, open-source local server that coordinates multiple AI coding agents via the Model Context Protocol to prevent file overwrites. In a demo, three agents from differen…
A new open-source project, the Coding Agent Skill Library, introduces 'Skills as a Service' to treat coding agent skills as governed, trusted data assets for regulated enterprises. The library offers …
A developer created FARE and BARE, npm CLI tools that generate AI rules and skills tailored to a specific project's stack, supporting multiple AI coding tools like Cursor, Claude Code, Windsurf, Copil…
Developer saadev0 has published a portable setup for OpenCode using the opencode-antigravity-auth plugin, enabling Google OAuth-based access to Antigravity quota for Gemini and Claude models. The conf…
Researchers at the University of Missouri-Kansas City disclosed the Ghostcommit attack, which hides malicious prompt-injection instructions inside a PNG image referenced by an AGENTS.md file to turn A…
A developer built a deforestation identification tool using an AI agent, which downloads satellite images, generates NDVI, and identifies potentially deforested locations. The project, created by Shas…
A developer built Kote, a tool that automatically captures engineering context from AI chats, Git pushes, and voice notes to prevent knowledge loss, and made it self-hostable with support for custom L…
Google Cloud Tech outlines a method to agentify the software development lifecycle by using AI agents to summarize issues, review code, and design features, addressing the problem of increased bugs fr…
Google Antigravity 2.0 and OpenAI Codex represent two competing architectural approaches to AI-assisted coding, with Antigravity keeping developers in the loop via a local visual IDE and Codex executi…
Researchers at ASSET Research Group published a proof-of-concept attack called GhostCommit that exploits coding-agent pipelines by hiding exfiltration instructions inside image files in pull requests.…
A comparison of coding agent plans reveals that Anthropic's Claude Code Pro plan offers the highest monthly value at $1,217, while OpenAI's Codex Pro 20x plan provides the most tasks per dollar. The a…