Hacker News

Article URL: https://moshcoding.com

Comments URL: https://news.ycombinator.com/item?id=48856315

Points: 1

# Comments: 0

Article URL: https://geekyants.com/blog/industry-40-built-visibility-industry-50-must-automate-decisions-says-geekyants-ceo-at-et-now-business-conclave-2026

Comments URL: https://news.ycombinator.com/item?id=48856300

Points: 2

# Comments: 1

Article URL: https://www.ft.com/content/e5c6684b-f401-405a-86f2-b5e96cb535a1

Comments URL: https://news.ycombinator.com/item?id=48856290

Points: 1

# Comments: 0

Article URL: https://www.bbc.co.uk/news/articles/cly9r54e5r4o

Comments URL: https://news.ycombinator.com/item?id=48856287

Points: 1

# Comments: 0

Article URL: https://apps.apple.com/us/app/elvebredd/id6760745063

Comments URL: https://news.ycombinator.com/item?id=48856278

Points: 1

# Comments: 0

Article URL: https://www.theatlantic.com/technology/2026/06/world-cup-tourists-america/687572/

Comments URL: https://news.ycombinator.com/item?id=48856273

Points: 1

# Comments: 0

Article URL: https://zml.ai/posts/llmd/

Comments URL: https://news.ycombinator.com/item?id=48856255

Points: 1

# Comments: 0

Article URL: https://www.malwarebytes.com/blog/ai/2026/07/turn-off-this-meta-setting-before-someone-generates-ai-images-of-you

Comments URL: https://news.ycombinator.com/item?id=48856237

Points: 1

# Comments: 0

Article URL: https://github.com/guilt/TinyToT

Comments URL: https://news.ycombinator.com/item?id=48856229

Points: 1

# Comments: 1

Article URL: https://wellstsai.com/en/post/ai-subscription-shakeout-2026-claude/

Comments URL: https://news.ycombinator.com/item?id=48856213

Points: 1

# Comments: 0

Article URL: https://www.reuters.com/podcasts/reuters-world-news/

Comments URL: https://news.ycombinator.com/item?id=48856201

Points: 1

# Comments: 0

Article URL: https://www.chinabankingnews.com/p/chinas-provinces-asked-to-bail-out

Comments URL: https://news.ycombinator.com/item?id=48856124

Points: 2

# Comments: 0

Article URL: https://www.adweek.com/media/publishers-opt-out-google-search/

Comments URL: https://news.ycombinator.com/item?id=48856103

Points: 7

# Comments: 0

Article URL: https://michaelnielsen.org/ddi/lisp-as-the-maxwells-equations-of-software/

Comments URL: https://news.ycombinator.com/item?id=48856099

Points: 23

# Comments: 1

Article URL: https://www.sciencedaily.com/releases/2026/07/260709160632.htm

Comments URL: https://news.ycombinator.com/item?id=48856098

Points: 1

# Comments: 1

Article URL: https://portal.neuralwatt.com/pricing

Comments URL: https://news.ycombinator.com/item?id=48856088

Points: 2

# Comments: 0

Article URL: https://www.ft.com/content/7800ba0f-1420-49fe-b260-9838632a19a4

Comments URL: https://news.ycombinator.com/item?id=48856042

Points: 2

# Comments: 1

Article URL: https://www.youtube.com/watch?v=2dp98vEGWq0

Comments URL: https://news.ycombinator.com/item?id=48856019

Points: 2

# Comments: 0

Article URL: https://www.youtube.com/watch?v=4Y9p0yp8Mow

Comments URL: https://news.ycombinator.com/item?id=48856010

Points: 2

# Comments: 0

I've been building Tempest, an open-source token-efficient agent orchestration platform for AI coding agents.

Most orchestration tools focus on running more agents. Tempest focuses on making each agent use fewer tokens.

Tempest runs on top of your existing coding agents... Claude Code, Gemini CLI, GitHub Copilot CLI, Opencode, Goose, Cline, Cursor Agent, and others... so there's no separate AI subscription or usage billing from Tempest.

Instead of giving every agent the same repository context, Tempest builds a knowledge graph of the codebase and retrieves only the code that's relevant to the current task. In our testing, this reduced token usage by 64% compared with native CLI coding agents without increasing token usage.

Each agent runs in its own Git worktree inside an isolated process, so multiple agents can work on the same repository without interfering with one another. To make that work across platforms, we built Hephaestus, an open-source SDK for process isolation. It uses the native sandboxing mechanisms on each operating system... Seatbelt on macOS, Bubblewrap on Linux, and a custom implementation we built for Windows.

The goal isn't to increase context windows. It's to improve repository understanding. Better understanding lets agents spend fewer tokens searching through code and more tokens solving problems.

If you've used tools like Conductor, I'd love to hear how you've approached parallel execution, repository understanding, or token efficiency. I'm especially interested in feedback on the architecture and the overall developer experience.

Comments URL: https://news.ycombinator.com/item?id=48855970

Points: 1

# Comments: 0