Open-source Rust dashboard centralizes Claude Code agent sessions and costs

·1 views

A developer has released Episko, an open-source MIT-licensed dashboard built in Rust to help manage multiple Claude Code agent sessions from a single interface. The tool was created after the developer struggled to track numerous terminal windows, sessions, and projects while working with Claude. Episko offers features including project overviews with branch and worktree details, an integrated terminal, auto-discovered run scripts, and full Claude conversation history. It also tracks context usage, session costs, daily token consumption, and provides short-term spend predictions to help users avoid hitting limits. The project is available on GitHub, with support for additional AI coding tools like Codex planned for the future.

Read the full story at Hacker News

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

Discussion (0)

Morph (YC S23) Hiring Member of Technical Staff

Morph, a Y Combinator Summer 2023 batch startup, has posted an opening for a Member of Technical Staff. The job listing was shared on Hacker News, though it received no points or comments at the time of reporting. The position details are available through Y Combinator's company job board. No further information about the role's requirements or responsibilities was provided in the listing summary.

0 comments Read more at Hacker News

ProgrammingHacker News ·

"Everyone Has Been Sold a Lie" on AI

Article URL: https://www.youtube.com/watch?v=pHcZpvIfho0 Comments URL: https://news.ycombinator.com/item?id=49139325 Points: 9 # Comments: 0

0 comments Read more at Hacker News

ProgrammingDEV Community ·

Audio Prompt Injection Attacks Fool AI Voice Agents 69% of the Time, Study Finds

Researchers have demonstrated that multimodal AI agents such as Gemini 3 Pro and GPT-4o-audio can be manipulated through hidden commands embedded in ambient sound or overlapping speech, achieving a 69% attack success rate under lab conditions. The vulnerability is an audio-based extension of prompt injection, a well-documented flaw in text-based AI systems, now made more potent by the always-listening design of modern voice agents. Because these models continuously parse incoming audio for instructions, any sound near a microphone becomes a potential attack surface. A proposed defense called cross-modal consistency detection (CADV) was able to identify such attacks over 90% of the time, suggesting the problem is a pipeline design gap rather than an unfixable architectural flaw. Developers building voice assistants, call-center bots, or ambient-listening agents are urged to treat all incoming audio as untrusted input and implement input segmentation and provenance checks.

0 comments Read more at DEV Community

ProgrammingHacker News ·

MIT Study Finds AI Can Deliver Strong Financial Advice When Prompted Well

A study from MIT Sloan found that AI-generated financial advice is surprisingly effective, particularly when users ask the right questions. The research highlights that the quality of guidance depends significantly on how queries are framed. MIT Sloan researchers explored AI's potential as a financial advisory tool, assessing its accuracy and usefulness. The findings suggest AI could serve as a viable resource for personal finance guidance, though the approach to questioning plays a critical role in outcomes.

0 comments Read more at Hacker News