backendjs
Curious case, comparing output from multiple LLMs
Open-source projects. Clever little tools. Big ideas.
Unearthed from the Hacker News community.
Curious case, comparing output from multiple LLMs
Rabbitty – a native Mac terminal for running AI coding agents in parallel
Ask HN: Which CVEs should I add to my Python security benchmark for AI agents?
PinFix – Click any UI element and edit its source with Claude Code
Making 10-minute AI movies with Claude Code and Higgsfield ($200 each)
Open Source Game Dev Agent
Bike4Mind – open-core AI workbench; any model, agents, RAG, self-host
Economist Style Plugins for Claude Code
Wallfacer: A terminal session manager for Claude Code
Glass – a see/act/debug loop over any GUI app for agents (MCP)
Open Source AI Harness Profiler – discover where tf your tokens are going
ConlangCrafter: Constructing Languages with a Multi-Hop LLM Pipeline
Bound – A deterministic control harness for AI agents
Agent runtime reduces LLM turns by 80% with a higher success rate in DeepSWE
Hive_review: Multi-agent AI code-review loop
Engineer made built in memory, loop detection and audits mandatory for agents
Bothread – a local room where AI coding agents collaborate and communicate.
Termaxa – A cooperative gate for the shell commands AI agents run