llm-inspector
The Htop for LLM Inference
Open-source projects. Clever little tools. Big ideas.
Unearthed from the Hacker News community.
The Htop for LLM Inference
AKM-CLR – pre-inference governance for vLLM-style LLM serving
A agentic nervous system for all DevOps tools
An AI agent that applies to jobs for me (Playwright and LLM form filling)
Loopers – Open-source fail-closed firewall for AI agent runtimes
I trained a 30M-param LLM from scratch and the scaling "floor" was a mirage
Agentty – A drop-in alternative to claude-code, written in C++26. 11.0 MB binary
Orbit, an Open-Source Toolkit for Retrieval-Based Inference
A signal engine with no training, no tokens, no neural net URL
Frontier model pricing became a rip-off, so I built an open-source CLI
LLM Colosseum – A zero-dependency browser RTS to test LLM tool calling
Sandboxd – Self-Hosted app Builder (agents, sandbox, preview url)
I scanned 10 MCP servers – here's what agents can't know before connecting
Sous-Chef, a Claude Code plugin where Fable reviews, Codex implements
A tool that prevent agents from cutting their own connection
Rowset – An open-source back end for AI agents
Browser automation CLI built for AI agents
Diary of Tom Riddle, for the ReMarkable with LLM responds