Full-text search across 65502 articles. Combine with topic and date filters; results sorted by relevance.
A developer built Receipts, an open-source CLI tool that verifies claims in project documentation by running Google's Gemma locally through Ollama and cross-checking README, configuration, results, and dataset files. The…
A practitioner's guide published October 4, 2026 outlines a four-step loop for writing evaluations of agentic AI systems: freeze and version every agent run's prompts, files, tools and MCP responses; have a subject matte…
A developer used Anthropic's Claude as a pair engineer to take a Spring Boot application from code to a live deployment on Amazon EKS, documenting the process as a repeatable set of one-script-per-step instructions. The …
Memorable launched a memory layer that stores how an agent completed a task and replays the procedure when a similar task returns, with storage kept on the user's side and consent enforced fail-closed. The tool offers fo…
A developer walkthrough highlights eight underused features of the ElevenLabs voice API, including low-latency voice cloning, granular prosody controls, multilingual code-switching, and client-side voice activity detecti…
System76's COSMIC project updated its pull request template to reject any pull request containing LLM-generated content, including source code, comments, and PR descriptions, and will close submissions that omit the requ…
GitHub deprecated four models across all GitHub Copilot experiences on October 2, 2026: Gemini 3.5 Flash, Gemini 3.6 Flash, Kimi K2.7 Code, and Claude Opus 4.7. GitHub recommends Gemini 3.8 Flash for both Gemini models, …
A developer published AGENTS.md, a set of operating instructions for AI coding agents that emphasizes asking clarifying questions, preferring simple and maintainable solutions, and using retrieval-led reasoning via the C…
Noodle, a free and open-source Mac app released under the Apache 2.0 licence, lets users run multiple named AI agents that each get their own workspace, desktop, and browser while connecting to AI accounts they already p…
Worktrunk, a new command-line tool for Git worktree management, launched with three core commands — `wt switch`, `wt remove`, and `wt list` — designed to let developers run 5-10+ parallel AI coding agents such as Claude …
Engrams, a self-hosted orchestrator for AI coding agents, launched as an open source alternative to Devin, running each agent in its own Firecracker microVM and snapshotting idle VMs so sessions cost nothing to keep. Eng…
A developer launched a small company run by Claude Code agents on a GitHub Actions schedule and documented five launch-day bugs, each fixed with roughly one line of code. Three of the bugs passed every automated check: a…
A paper published in October 2026 by Kirill Brilliantov, Alejandro Hernández-Cano and Emmanuel Abbé finds that open-source state-of-the-art MLE agent harnesses provide no advantage over a single session of a minimal-harn…
Developer Zesuperaker released scratchcad, an open-source Rust solid-modelling API and MCP server that lets AI assistants generate CAD geometry from text prompts, licensed under Apache License 2.0. The MCP server runs on…
A Vienna-based founder running Postservice.at through Claude Code built a "How I fool myself" section in the project's CLAUDE.md that logs every agent error with its date and root cause, and each new session reads it bef…
A developer running a daily autonomous Claude Code agent on a single Windows PC reported that a separate auditor agent's mutation testing caught two changes whose tests passed even after the auditor deliberately broke th…
Nvidia launched OpenShell at GTC San Jose, an Apache 2.0 open-source runtime that sandboxes AI agents using Linux Landlock LSM and seccomp BPF kernel-level enforcement rather than application-layer allow-lists. OpenShell…
Anthropic's Claude Sonnet 5.5 is now available on Vercel's AI Gateway under the identifier anthropic/claude-sonnet-5.5, the gateway announced. Sonnet 5.5 improves on Claude Sonnet 5 for well-scoped everyday work, carryin…
A developer benchmarked their AI coding agent Empryo against the rival agent pi on four real bug fixes drawn from the hono and opencode TypeScript repositories, with both agents fixing all four bugs on Opus 5. Empryo's r…
Simon Willison used Anthropic's Claude Opus 5.5 to generate an HTML5 canvas pixel-art animation of at least 20 kākāpō parrots partying with confetti, then had a local Claude Code session drive Playwright to record a 15-s…