Show HN: Halo – open-source, tamper-evident runtime evidence for AI agents

Show HN: Docx-CLI: agents read/edit Word docs using 1/2 the time and tokens

Show HN: KiCad in the Browser

Show HN: Imagent – agentic image/video/speech generation

Show HN: I trained a language model that thinks the capital of Japan is Paris

Show HN: Neil the Seal Game

Show HN: Bramble – Local-first password manager

Show HN: I built an open-source alternative to Claude Cowork

Show HN: Opbox – CRDT based sync for text files on disk

Show HN: GolemUI – Declarative Form Engine

Self-Hosted AI news aggregator using Cloudflare Workers, Vectorize, and Nostr

Show HN: Frond – a frontend runtime for your app's dependency graph

Show HN: TaskPeace – a task queue my AI coding agents pull work from over MCP

Show HN: ZeroFS – A log-structured filesystem for S3

Researchers show that intermittent fasting maintains long-term weight loss, regardless of meal timing

Show HN: Kastor – Terraform-style specs for AI agents

Show HN: PostgreSQL performance and cost across 23 EC2 instance types

Show HN: ctx – Search the coding agent history already on your machine

Show HN: Searchable directory of 22k+ products from worker-owned co-ops

Show HN: Salt – a systems language with Z3 theorem proving in the compiler

Show HN: AnalystAIPack – 118 runnable agent skills for malware analysis and RE

Show HN: Follow London Trains in 3D

Show HN: Claudoro, Pomodoro timer embedded in the Claude Code statusline

Show HN: Sidenote – comment on your rendered blog, an LLM writes the Git diff

Show HN: ContextCodeCache in Rust

Show HN: Onboard-CLI, a LLM powered and AST-based tool to visualize codebase

Show HN: Foreman, a self-hosted LLM gateway for cost aware model routing

Show HN: LIBR tracing with source ledger rows and byte-exact PDF verification

Show HN: Frugon – Find which LLM calls a cheaper model could handle (local, MIT)

Show HN: Kontext – Move an AI chat's full context to another AI in one click

More →