Open source
18 RohitAI articles on Open source: news, explainers and practical guides, newest first.
Pupavision’s fly camera kept recording with its AI logged out
For small labs, Pupavision shows how AI-assisted cameras can keep recording without the model—and why biological timing still needs validation.
When to self-host Vigilo for AI security reviews
For software and security teams, assess Vigilo’s model access, hosting costs, licence terms and alpha support before planning a controlled trial.
How to add ACP coding agents to Vibe Kanban
Vibe Kanban users can check agent compatibility, terminal sign-in, model controls, permission limits and provider costs before starting work.
Wharton’s Primer asks students to teach the AI
For teachers exploring AI practice, Primer puts students in the explainer’s role. Its open design is inspectable, but learning gains remain unproven.
Anthropic OSS Scanner: Should Your Open-Source Project Enroll?
A maintainer’s guide to Anthropic OSS Scanner: eligibility, offline setup, maintainer-led triage, candidate patches and disclosure rules.
BootLoops 1.0: Reusable AI Science Tools and Their Verification Limits
What research teams can reuse from BootLoops 1.0, how its package checks differ, and why numerical validation still needs independent scientific review.
Olmo-core 3: What Changed and How to Plan a MoE Training Migration
Ai2’s Olmo-core 3 adds a MoE training stack. Check benchmark limits, PyTorch extras, cluster topology and checkpoint behavior before migrating.
Cloudflare OS Managed Waitlist: Self-Deploy Now or Wait?
Compare self-deployment and the managed waitlist for Cloudflare OS’s agent workspace, including operating duties, GitHub and Google permissions, and costs.
vLLM 0.30 Gives Model State New Lifetimes. Budget Them.
Fast Start and HiSparse move weights and KV across new lifetimes and memory tiers. The vLLM 0.30 upgrade question is who owns warm state—and its cost.
vLLM 0.27.0 Expands the Runtime—and the Blast Radius
vLLM 0.27.0 adds Kimi K3, MRv2 workloads, Rust control APIs, and fault recovery—but its PyTorch 2.13 jump makes this a fleet migration.
SGLang 0.5.17 Gives Agent Sessions a Vote in GPU Memory
SGLang 0.5.17 adds session-aware KV caching, faster recovery, Rust ingress, and frontier-model paths—shifting serving toward agent runtime policy.
WeatherNext 2 Turns Cyclone Forecasts Into Programmable Risk Infrastructure
Google DeepMind opens WeatherNext 2 and Cyclones, turning fast ensemble forecasts into programmable risk infrastructure for builders.