GitHub announced custom agents for Copilot CLI, allowing developers to define reusable, team-specific workflows using Markdown files. The feature aims to reduce friction by encoding context, tools, an…
Microsoft Security's multi-model agentic scanning system, codenamed MDASH, has moved from benchmark validation into active use by engineering teams across Windows, Azure, and identity systems to disco…
A 1972 paper on an infinitely differentiable soft sparsity engine, based on metrics and tensors, is being rediscovered in modern ML/AI. The author has released Fortran code and mathematics on GitHub a…
Together AI released DeepCoder-14B, an open-source 14B model that matches o3-mini on coding benchmarks, with full training recipe and dataset published for reproducibility. Biome v1.5.0 introduced a -…
A developer released Python and Node.js SDKs for Ajah, an open-source self-hosted LLM observability gateway. The SDKs simplify integration by replacing manual header injection with a single import, en…
GitHub announced a public preview of duplicate issue detection, which flags potential matches against existing issues during issue creation. The company also added issue fields support to its MCP serv…
Google sunset Gemini CLI and Gemini Code Assist IDE extensions for individual users on June 18, 2026, citing a shift toward multi-agent systems. Affected users are directed to migrate to Antigravity C…
A developer released DOS, an open-source tool that verifies AI agents' completion claims by checking git history and other artifacts instead of trusting the agents' own statements. The tool, available…
RTK, a tool that compresses terminal output for LLM agents, claims to cut token usage by 60-90% but faces skepticism due to misleading savings metrics, silent failure risks, lack of accuracy benchmark…
Cursor, GitLab, and Zed agree that GitHub is breaking but disagree on how to rebuild it, highlighting a growing divide in developer tooling approaches. The debate centers on the future of code collabo…
A longtime skeptic of Amazon's AI efforts finds himself impressed by two new products: the Bee wearable and Quick Desktop, an enterprise AI assistant. Despite initial setup frustrations and limited co…
BuildForever has integrated an AI teammate named Avery into its engineering workflow, which autonomously wrote 31% of the code shipped by its five-engineer team last week. Avery identifies issues, dia…
A developer built Agent Island, a macOS tool that monitors Claude Code and Codex CLI sessions by reading local transcript files to detect when an agentic coding session is working, stalled, or waiting…
A developer who maintains Safari MCP, an open-source browser-automation server for macOS, analyzed a competitor's tool, safari-devtools-mcp, and ported its four best ideas—iOS-Safari web-dev validatio…
GitHub now includes Copilot-authored pull requests in author searches on github.com and GitHub Mobile, allowing users to see all pull requests they authored, whether directly or via Copilot, with a si…
A developer built VibeRaven, an open-source tool that scans repositories to map production readiness gaps, addressing the challenge of moving AI-generated prototypes to reliable production systems.…
GitHub has introduced pull request limits to help open-source maintainers manage the surge in contributions, which has grown from 25 million to 90 million monthly pull requests since January 2023. The…
Kilo launched Kilo for GitHub, an AI agent that lives inside GitHub and can be @mentioned in issues, pull requests, and review comments to answer questions, triage bugs, and open pull requests without…
A developer documented a secret scanning setup that prevents credentials from entering the context window of Claude Code, an AI coding assistant. The system uses trufflehog with 700+ detectors to inte…
A developer built Proofline, a 5-skill Markdown pack that catches fake-ready output from AI agents before it becomes a release or handoff. The tool works as a review route after agent output, asking q…