Hacker News

Subscribe to Hacker News feed
Hacker News RSS
Updated: 38 min 33 sec ago

Moltler the Skills Framework for Elasticsearch

Fri, 02/27/2026 - 5:58pm

Article URL: https://hub.moltler.dev/

Comments URL: https://news.ycombinator.com/item?id=47187085

Points: 1

# Comments: 0

Categories: Hacker News

Ask HN: Can our bootstrapped startup keep up?

Fri, 02/27/2026 - 5:56pm

fuck - it's been a rough week. we've been pouring our hearts and souls into building an agent orchestration layer with streaming desktops for months, and on wednesday, cursor launched the exact same feature. THREE DAYS BEFORE WE MANAGED TO LAUNCH OURS! and claude code launched remote control on the same day - you can see where it's going. keeping an edge in this white hot market is basically impossible

oh well, take a look at what we built anyway, you can at least run it on your own infra, in your enterprise: https://helix.ml/

Comments URL: https://news.ycombinator.com/item?id=47187040

Points: 3

# Comments: 0

Categories: Hacker News

Show HN: QF STEM Ledger – Logging Structured Cognitive Work

Fri, 02/27/2026 - 5:55pm

I built a tool to log structured cognitive work, including proofs rebuilt from first principles, research notes drafted, and concepts properly mastered, after noticing that serious technical effort is rarely recorded in any structured way.

Curious to hear what HN thinks.

Comments URL: https://news.ycombinator.com/item?id=47187014

Points: 1

# Comments: 0

Categories: Hacker News

Rank5.io – a party game about the people you play with

Fri, 02/27/2026 - 5:50pm

Article URL: https://rank5.io/howTo

Comments URL: https://news.ycombinator.com/item?id=47186922

Points: 2

# Comments: 2

Categories: Hacker News

Show HN: AgentGuard – a QA engine that sits between AI coding agents and LLMs

Fri, 02/27/2026 - 5:16pm

AI coding agents are great at generating code, but terrible at respecting architecture. We kept getting code that looked correct but didn’t type-check, had hallucinated imports, or ignored project boundaries.

AgentGuard is an open-source quality-assurance engine that sits between an AI coding agent and the LLM. It enforces a top-down generation pipeline:

Skeleton → Contracts → Wiring → Logic

Each stage constrains the next, and we validate syntax, imports, linting and types before any human sees the code. The LLM also self-reviews its output against explicit criteria.

AgentGuard supports MCP (Claude Desktop, Cursor, Windsurf, Cline) and tracks token cost per model and run.

Python 3.11+, MIT licensed.

Comments URL: https://news.ycombinator.com/item?id=47186484

Points: 1

# Comments: 0

Categories: Hacker News

Otters as Bioindicators of Estuarine Health

Fri, 02/27/2026 - 5:13pm
Categories: Hacker News

MasterClass Executive

Fri, 02/27/2026 - 5:11pm
Categories: Hacker News

Pages