Feed aggregator

Hi HN!

I built this tool specifically for Claude Code users who hit the 5-hour rate limit wall mid-flow. There's no official plan between Pro ($20/mo) and Max ($100/mo). it's a fixed gap with nothing in between.

The workaround most people do manually: running multiple Pro accounts and switching when one is limited. This actually works, but naive rotation wastes a lot of capacity. When you activate an account turns out to matter as much as which one you use. A single throwaway prompt sent a few hours before your coding session can unlock an extra full cycle.

PolyClaude automates this. You tell it your accounts, your typical coding hours, and how long you usually take to hit the limit. It uses combinatorial optimization to compute the exact pre-activation schedule, then installs cron jobs to fire those prompts automatically. When you sit down to work, your accounts are already aligned.

It's free and open source. Install is one curl command, then an interactive setup wizard handles the rest.

Repo: https://github.com/ArmanJR/PolyClaude

Hope you find it useful!

Comments URL: https://news.ycombinator.com/item?id=47292043

Points: 1

# Comments: 0

Article URL: https://frederikbraun.de/perfect-types-with-sethtml.html

Comments URL: https://news.ycombinator.com/item?id=47292039

Points: 1

# Comments: 0

Article URL: https://code.claude.com/docs/en/scheduled-tasks

Comments URL: https://news.ycombinator.com/item?id=47292033

Points: 1

# Comments: 0

Article URL: https://github.com/mistivia/lmp

Comments URL: https://news.ycombinator.com/item?id=47292029

Points: 3

# Comments: 0

Article URL: https://www.reuters.com/business/energy/after-iraq-kuwait-uae-may-be-next-cut-oil-output-iran-crisis-analysts-say-2026-03-05/

Comments URL: https://news.ycombinator.com/item?id=47292024

Points: 2

# Comments: 0

Article URL: https://github.com/Patrick0shea/DDD

Comments URL: https://news.ycombinator.com/item?id=47291975

Points: 3

# Comments: 0

Article URL: https://github.com/NikitaDmitrieff/auto-co-meta

Comments URL: https://news.ycombinator.com/item?id=47291955

Points: 1

# Comments: 1

Article URL: https://vecstore.app

Comments URL: https://news.ycombinator.com/item?id=47291954

Points: 1

# Comments: 1

Article URL: https://dnsmichi.com/2026/03/07/building-an-interactive-conference-badge-with-tufty-2040-a-step-by-step-guide/

Comments URL: https://news.ycombinator.com/item?id=47291945

Points: 1

# Comments: 0

Article URL: https://dangerousminds.net/history/battle-corpse-of-charles-manson/

Comments URL: https://news.ycombinator.com/item?id=47291942

Points: 2

# Comments: 0

Hey HN,

I kept rebuilding the same infrastructure every time I wanted to put a Claude Agent SDK into production. Sessions, streaming, sandboxing, persistence, a REST API, file hooks. So I built Ash.

An agent is a folder with a CLAUDE.md file, skills folder, etc, and one-line deploy from cli, or tsx/python sdks.

Some things I cared about when building this:

Sandboxing. Each agent runs in its own isolated process with an environment allowlist, cgroups resource limits, and bubblewrap filesystem isolation on Linux.

Session persistence. All state lives in CRDB. If the server crashes mid-conversation, resume picks up where it left off. You can also snapshot workspaces to S3/GCS and resume on a different machine.

Keeping it thin. The SDK's `Message` types flow through the whole pipeline untranslated, from the Unix socket to SSE to the client. Ash adds session routing, sandbox pooling, and lifecycle management. It doesn't re-wrap or translate the SDK's types.

I've been measuring overhead pretty carefully. Ash adds <0.5ms per message at p99. Warm resume is 1.7ms. Cold resume (restore workspace, spawn process, reconnect) is 32ms.

OSS, Self-hostable, MIT licensed: https://github.com/ash-ai-org/ash-ai

Comments URL: https://news.ycombinator.com/item?id=47291795

Points: 1

# Comments: 0

I vibe coded this! It is a nice little game I use to send secret message to my girlfriend, I guess you could also use it to encourage a little one to learn spelling? Let me know if you can think of a use for it!

Comments URL: https://news.ycombinator.com/item?id=47291792

Points: 1

# Comments: 0

Article URL: https://twitter.com/i/status/2029992315532759435

Comments URL: https://news.ycombinator.com/item?id=47291777

Points: 1

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=47291771

Points: 1

# Comments: 0

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

Comments URL: https://news.ycombinator.com/item?id=47291768

Points: 1

# Comments: 0

Article URL: https://www.tbray.org/ongoing/When/202x/2026/03/05/Because-Algospeak

Comments URL: https://news.ycombinator.com/item?id=47291767

Points: 1

# Comments: 0

Article URL: https://purl.stanford.edu/yb785sx5019

Comments URL: https://news.ycombinator.com/item?id=47291761

Points: 1

# Comments: 0

I built DBWarden for Python projects which use SQLAlchemy and need a simple migration workflow.

Most tools add large frameworks and complex configuration. DBWarden focuses on a small CLI and readable SQL migrations.

Core ideas

• Auto detect SQLAlchemy models from a models directory • Generate raw SQL migration files from model changes • Keep migrations transparent and easy to review • Track migration history and database state • Minimal setup through a small warden.toml file

Typical workflow

1. Write SQLAlchemy models 2. Run dbwarden make-migrations "name" 3. Review the generated SQL 4. Run dbwarden migrate

Commands include

• init • make-migrations • migrate and rollback • history and status • diff between models and database

Supported databases

• PostgreSQL • SQLite • MySQL

Project status: experimental. I look for feedback from developers who work with SQLAlchemy migrations.

Comments URL: https://news.ycombinator.com/item?id=47291748

Points: 1

# Comments: 0

Article URL: https://github.com/malandrakisgeo/qRPC

Comments URL: https://news.ycombinator.com/item?id=47291733

Points: 1

# Comments: 0