As AI agents become capable of using computers independently, Novastart is rethinking the traditional desktop with an infinite canvas where people, applications and AI agents can work together.
Organizations publishing on Pressando can now mark the original source of a release, so search engines credit the source rather than the copy, and verified organizations get dofollow links back to their own site on every release.
A public demonstration from Aido runs the same flawed pull request through Claude, ChatGPT, and Gemini with identical instructions, showing where the models agree, where they differ, and why a second reviewer catches what the first misses.
A rolling currency-review process means each TrueCert assessment is verified against current tools and practices before launch and on an ongoing basis, giving employers a hiring signal they can trust. The catalog has grown to 149 assessments across 18 categories.
A run of releases, 1.6.2 to 1.6.6, pins the tool's dependencies, closes shell and checkout injection paths, adds a prompt-injection guardrail, and documents a security posture for teams that run it on their own repositories.
Versions 1.5.0 and 1.6.0 of the open-source, multi-provider AI code-review tool for GitHub let teams point it at any OpenAI-compatible endpoint, including DeepSeek, Kimi, Grok, Mistral, OpenRouter, and self-hosted gateways, and add a scheduled summary of the pull requests merged each week.
A patch release makes the sampling temperature opt-in, so the AI code-review tool's Claude commands work again on Anthropic's newest models, which no longer accept that parameter.
A run of releases makes the open-source, multi-provider tool run automatically on pull requests from agents like Copilot, Claude Code, and Cursor, adds a composite GitHub Action for running it as a step in any workflow, and publishes it to the GitHub Marketplace.
A patch release, surfaced by the tool's first external adopter, keeps code reviews running when an AI provider returns a temporary error instead of failing the whole command.
Two updates make each release easier for journalists to act on and easier for readers to explore: a structured media contact and links to more from the same newsroom.
The open-source, multi-provider AI reviewer for GitHub can now be installed with one thin workflow instead of copying about 30 files, and upgrades become a one-line tag bump.
French joins Swedish, English, German, Norwegian, Danish, and Finnish as a fully supported publishing language, each release on its own search-optimized page.
The Swedish service offers timed online assessments across more than 175 certifications in DevOps, cloud, and AI, each producing a verifiable Open Badges 2.0 credential.
The open-source multi-provider AI code-review tool for GitHub ships 66 unit tests, an internal library refactor that removes roughly 945 lines, and two dependency security fixes.