A developer built otp-gateway, a zero-dependency Python library that reads OTP codes from email inboxes via IMAP, eliminating the need for external APIs or services. The library supports generating em…
Researchers at BlueDot's Technical AI Safety Project Sprint found that fine-tuning language models on negated documents can still teach them reward-hacking knowledge, leading to emergent misalignment …
A developer built fata.uk, a serverless stranger-matching tool that uses a single Cloudflare Worker, GitHub Issues for state, and Cloudflare KV for encrypted data. The system computes emotional freque…
OpenCode v1.17.10, released June 24, adds MCP resources and resource templates, fixes OAuth callback failures in WSL and container setups, and introduces a --mini CLI mode for scripting. The update cl…
GitHub introduced an enterprise setting this week that restricts which extension and plugin marketplaces are allowed in VS Code and GitHub Copilot CLI, framing marketplace policy as a runtime boundary…
Framesmith 1.7 introduces a quality evaluation system that tells an AI agent when a UI design is complete, using a directive field that returns 'READY TO PRESENT' only when the design scores above 95 …
A researcher reproduced Anthropic's paper on natural language activations (NLAs), training models to generate textual descriptions of neural network activations. The study found that a single model tr…
GitHub announced two harness-level improvements to Copilot agentic sessions—prompt caching achieving 94% cache hit rates and deferred tool loading—plus a new Auto model selection feature using its HyD…
GitHub evaluated its Copilot agentic harness across multiple benchmarks and models, finding it achieves task completion rates on par with vendor harnesses while using fewer tokens. The harness powers …
A developer scanned 1,200 real-world MCP (Model Context Protocol) configuration files from public GitHub repositories using an open-source security tool called Pluto AgentGuard. The scan found that 20…
GitHub's Copilot code review now uses CLI-based file exploration tools, reducing costs by 20% while maintaining quality. Medium analysis depth public preview adds organization-level default settings a…
GitHub announced public preview of strictKnownMarketplaces enterprise-managed settings for VS Code and GitHub Copilot CLI, enabling administrators to restrict plugin installations to approved marketpl…
A developer built W.H.Agent (White Hat Agent), an open-source CLI and sandboxing tool designed to provide pre-execution and runtime defense for AI agents. The tool aims to protect against threats like…
Topos, an open-source tool from Krv-Labs, evaluates code quality by mapping programs to structural graphs and calculating metrics for simplicity, composability, and security. It aims to address the bo…
A developer released AssertGo, a fluent assertion library for Go inspired by AssertJ, after Go 1.27 added generic methods. The library provides chainable assertions for strings, integers, slices, maps…
A developer published a coding style guide for Laravel projects, emphasizing readability, elegance, and adherence to framework conventions. The guide advises against using final classes or private met…
Polygraph, a meta-harness from the Nx team, launches to give AI agents cross-repo visibility and persistent session memory. It indexes all connected repositories into a graph, enabling agents to plan …
Anthropic user adatarwa released 11 installable Claude Skills that turn the AI agent into domain-specific business operators, including sales, finance, HR, and legal roles. The skills encode triggerin…
A developer built a Markdown converter for AI agents that reduces token usage by over 93% compared to raw HTML. The tool, available as TypeScript and Python packages, uses content negotiation to serve…
AI-generated code is flooding GitHub and degrading codebases, with research showing AI-written code has 1.7 times more critical issues and 45% ships with OWASP Top 10 vulnerabilities. Major projects l…