SShortSingh.
TopTechnologyAI & MLStartupsProgrammingScienceBusinessFinanceCrypto & Web3World
Back to feed
Programming

Developer builds Mac tool to manage multiple AI coding agents without context switching

0
·4 views

A developer has identified a productivity problem with running multiple AI coding agents in parallel: agents often sit idle waiting for user approval while the user is occupied elsewhere, wasting metered subscription time. The author found that most coding agents support lifecycle hooks, allowing an external program to intercept and respond to permission requests via stdin JSON. Leveraging this, they built a Mac app called Crew Tower that surfaces agent approval requests directly in the MacBook's notch area, visible regardless of which app is in focus. The tool lets users approve, deny, or respond to agent prompts in a single click without switching windows or terminals. It also displays remaining quota for services like Claude and Codex, addressing the same core concern of minimising idle time on metered plans.

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)

Log in to join the discussion and vote.

Log in

Related stories

0
ProgrammingDEV Community ·

How a document analytics tool learned to tell real readers from bots

A document-analytics startup that tracks who reads shared PDFs found its viewer counts were being inflated by automated systems including corporate email security scanners, link-preview bots from Slack and LinkedIn, and uptime monitors. To filter these out, the team built a weighted scoring system that flags sessions as suspicious when bot-like signals — such as missing user agents, zero engagement, or sub-second page views — cross a threshold of 60 points. The process revealed unexpected edge cases, including the Android phone brand CUBOT whose device name contains the substring 'bot', causing real users to be misclassified as crawlers. The team also discovered that a 1-millisecond dwell-time floor was being triggered by server-side processes rather than genuine human interaction, leading them to raise the minimum plausible reading duration to 10 seconds. The project highlighted that adding evidence meant to exonerate real users sometimes backfired, making legitimate sessions appear even more bot-like due to inverted scoring logic.

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

Why AI Agent Context Should Be Treated as an Authority Control

Enterprise AI systems commonly maximize the data fed to agents, but a new technical perspective argues this approach is flawed and potentially risky. An agent's effective authority is shaped by both the information it can access and the actions it is permitted to take, meaning context control is as critical as capability control. A synthetic experiment called Token-Bleed R5 found that compact, governed context selection used up to 97.9% fewer prompt tokens than full-context stuffing while achieving higher accuracy. However, the same experiment revealed that governed selection still consumed nearly seven times more tokens than a simple lexical baseline, which itself scored zero on quality metrics, highlighting real cost trade-offs. The recommended architectural approach separates agent workflows into four planes — connection, context, capability, and evidence — treating the context layer as a formal authority control rather than a mere technical convenience.

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

Lightricks Releases LTX-2.5 With Diffusion-Based VAE Decoder for Open-Weights Video Generation

Lightricks launched LTX-2.5 on August 11, 2026, introducing a novel architecture where the VAE decoder itself operates as a diffusion model rather than a fixed deterministic component. The system uses an aggressive 1:192 spatiotemporal compression ratio and relies on the diffusion video decoder to recover fine details — such as readable text and sharp textures — that high compression typically discards. A second feature called Diffusion Fidelity Rendering allocates compute adaptively across frames and regions based on scene complexity, enabling a 10-second 720p clip to be generated in 6.8 seconds on two NVIDIA GB200 GPUs. LTX-2.5 also replaces smaller T5 or CLIP text encoders with a fine-tuned Gemma 4 12B model paired with a custom prompt enhancer, improving coherence in complex, multi-subject prompts. In Lightricks' own benchmarks, the model achieved an artifact score of 0.28 on a 98-prompt evaluation suite, outperforming Flux 3 at 0.45 and Veo 3.1 at 1.20.

0 comments Read more at DEV Community