browser-use Team Launches Open-Source AI Video Editor Powered by Coding Agents

·1 views

The browser-use team released video-use in April 2026, an open-source tool that lets AI coding agents such as Claude Code and Codex edit video files entirely through shell access. Instead of processing raw frames, the system converts footage into a phrase-level Markdown transcript using ElevenLabs Scribe, allowing the AI to 'read' the video rather than watch it. The tool uses an ffmpeg orchestration layer to express edits as structured JSON data, then renders a final output file without requiring any manual timeline or menu interaction. Since its launch, the project has accumulated over 13,000 GitHub stars, with more than 3,000 added in a single week by early July 2026. The reviewer tested it across podcast recordings, product demos, and travel footage, describing it as one of the fastest-growing repositories in the browser-use organisation.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

How AI coding agents rack up costs through small, reasonable-seeming decisions

Agentic coding tools can become surprisingly expensive not through obvious mistakes but through many individually justifiable micro-decisions that accumulate over time. A developer analyzing their own billing identified five key cost drivers: keeping too many files in the main agent's context, reading more files than necessary, using powerful frontier models for simple lookup tasks, generating long outputs inline instead of delegating to cheaper sub-agents, and allowing context bloat that silently inflates costs on every subsequent turn. Because each decision feels harmless in the moment, the author argues that personal discipline alone cannot solve the problem. Instead, they built a structural solution comprising a per-tool-call spending hook, a model router, and a parent-child agent delegation system. Notably, the cost-cutting measures also improved output quality by keeping the main agent more focused and accurate.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Open-Source Blazor JWT Starter Template Released for .NET 10 with Radzen UI

A developer has published a production-ready open-source starter template that demonstrates secure JWT authentication in Blazor applications built on .NET 10. The template combines JWT Bearer authentication for API communication with cookie-based authentication for the Blazor front end, alongside Radzen UI components. It follows a clean layered architecture separating Domain, Application, Infrastructure, and Shared concerns. The project includes a WebAPI acting as a JWT token authority and a Blazor Server app handling user sessions via secure HttpOnly cookies. The template is aimed at developers looking to skip repetitive authentication boilerplate when building enterprise or experimental Blazor applications.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

How Durable Execution with DBOS Delivers Exactly-Once Automation in TypeScript

A developer migrated 34 production automations from a no-code visual platform to TypeScript, citing durable execution with exactly-once semantics as the key motivation. Traditional automation tools typically offer retry-on-failure, which risks re-executing side effects like sending messages or writing records when a process crashes mid-workflow. DBOS addresses this by checkpointing each completed step in Postgres, so if a workflow crashes between steps, it resumes from where it left off rather than restarting entirely. The framework uses TypeScript decorators to distinguish workflow orchestration logic from individual steps, enforcing a rule that steps are never re-executed once recorded as complete. This approach eliminates the need for manual idempotency keys and progress-tracking boilerplate, reducing automation code to pure business logic.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Developer Rewrites 34 No-Code Automations in TypeScript, Cuts Memory Use by 90%

A developer recently migrated 34 daily business automations — including WhatsApp AI bots, CRM syncs, and PDF report generation — from the visual no-code platform n8n to hand-written TypeScript code. The primary motivation was growing difficulty maintaining complex workflows on a visual canvas, which made changes slow and debugging opaque. The rewrite, built on the DBOS framework with Postgres-backed durable execution, reduced memory usage from approximately 1.4GB to 150MB — a roughly tenfold improvement — while handling around 1,167 workflows per second. The solo migration was completed with the help of AI coding assistant Claude Code, and a Caddy reverse proxy ensured no client-facing disruption during the switchover. The developer noted that AI bot response times did not improve, since latency is dominated by the underlying language model, not the surrounding infrastructure.

0 comments Read more at DEV Community