Istota, a self-hosted personal AI operating system integrating with Nextcloud, launched with features including multi-room chat, persistent memory, RSS reader, location tracking, health dashboards, an…
A developer tested a coding agent on a 36k-file Rails monolith (GitLab) by asking it to audit all dependents of MergeRequest. Without a codebase map, the agent found only 2 of 16 actual dependents in …
GitLab has added Anthropic's Claude Sonnet 5 to its Duo Agent Platform across all tiers and deployment models, routing requests through its AI Gateway. The new model is the first to complete all tasks…
GitLab's 2026 AI Accountability Report found that 92% of development teams face governance challenges with AI-generated code, and 34% of organizations experienced a production incident involving AI co…
CodeRabbit, the most installed AI app on GitHub and GitLab, has launched a new feature that shows the context behind each code review comment, allowing developers to see the source of a comment and di…
Jujutsu (jj) is a version control system that rethinks Git's working copy and conflict model by eliminating the staging area and treating the working copy as an always-committed state. It uses Git rep…
Anthropic released Claude Sonnet 5, which matches Opus performance on coding and agentic benchmarks at a lower cost, with launch pricing of $2/$10 per million tokens until August 31. GitHub Copilot be…
DProvenanceKit, a Python port of the Swift library for execution provenance in AI systems, has been released. It provides reasoning observability and regression testing by turning each execution into …
Anthropic released Claude Sonnet 5, a mid-tier AI model that excels at writing code and handling complex tasks through deeper reasoning and self-improvement, but catches fewer bugs than earlier models…
GitLab CI is experiencing a partial service disruption, affecting its website and CI/CD components hosted on Google Compute Engine. The incident impacts GitLab's continuous integration and delivery se…
A developer with 30 years of consulting experience tested seven self-hosted AI project tracking tools against a real product launch scenario. ONES.com emerged as the top recommendation for teams migra…
CodeRabbit launched its AI-powered code review agent directly inside Discord, allowing maintainers to investigate, plan, and automate code tasks without leaving chat. The agent uses scoped connections…
Anthropic released Claude Sonnet 5, a mid-tier AI model that excels at writing code and handling complex tasks through deeper reasoning and self-improvement, but catches fewer bugs than earlier models…
A team integrated an LLM into their Jenkins MR validation pipeline after a GitLab API token was accidentally committed and missed by two human reviewers. The LLM now automatically flags hardcoded cred…
GitLab's 2026 AI Accountability Report finds that while 78% of developers code faster using AI tools, overall software delivery has not accelerated due to bottlenecks in testing, review, and governanc…
CodeRabbit launched an Overview page for pull requests that consolidates AI summaries, mergeability status, and ranked blockers into a single screen, aiming to reduce code review time and bugs by 50%.…
Cursor data shows a rising share of AI-generated code changes reaching production without manual review, signaling a shift in software development practices. GitLab's AI Accountability Report reveals …
GitLab Orbit, a context graph for the software development lifecycle, launched in public beta. The tool converts GitLab data into a graph database to enhance AI agents' performance and efficiency.…
Cloudflare's engineering team grew 45% to 1,894 after cutting 1,100 jobs in May, as CEO Matthew Prince says AI eliminates "measurer" roles while builders and sellers thrive. The pattern, confirmed by …
Cursor 3.9 shipped June 22 with a Customize page that replaces JSON config files for managing plugins, MCPs, skills, and hooks, aiming to simplify team onboarding and configuration. The update include…