ironcurtain
IronCurtain – A secure* runtime for autonomous AI agents
Open-source projects. Clever little tools. Big ideas.
Unearthed from the Hacker News community.
IronCurtain – A secure* runtime for autonomous AI agents
Agent Mesh: let Claude Code, Codex, Grok and other agents talk to each other
Two AI models exchanged a thought through raw activations on one consumer GPU
Metis by Arm: open-source agentic security harness
PortMarshal – Guard dev servers from cross-agent stops
Dart Framework – Systems Thinking Skill for AI Agents
Cloud for your AI Agent's tools/fuctions
Fidx – local semantic search in one SQLite file, no LLM at query
Quatuor – Kick back and watch 4 agents LLM talk to each other (FOSS)
Alluvia – mine your Claude Code/Cursor/ChatGPT history, locally
Ayghri/I-have-ADHD: skill for coding agent to stop it from burying the answer
BurstyRouter: local LLM first then burst to end-to-end encrypted LLM
Llm.c ported to Mojo with Metal kernels, 1.72x faster than PyTorch MPs
Power Coding – an AI-coding skill I audited on Claude Code and Codex
Nimbus - open-source AI agent that operates your AWS and GCP
KaaS – Knowledge as a Service: an out-of-the-box LLM wiki compiler
Search Console MCP – Talk to Google Search Console with Claude
Opendray – run Claude Code/Codex agents on your own box, drive from anywhere