destructive_command_guard
Block dangerous Git and shell commands from being executed by agents
Open-source projects. Clever little tools. Big ideas.
Unearthed from the Hacker News community.
Block dangerous Git and shell commands from being executed by agents
Crucible – your AI wrote the tests, so who tested the tests?
Rlsgrid – fuzz your Postgres/Supabase Row-Level Security for cross-tenant leaks
Interactive Jacobian-Lens visualizer and live steerer for GGUF models
Inkwell: It's a New Kind of Wrapper for Exposing LLVM in Safe Rust
Cage-lite:Prebind assurance for consequential AI agent actions
Libtsgo: TypeScript-Go embedded in C and C++
Focus: Platform-agnostic UI framework for resource-constrained embedded systems
Xllama – Local LLM Chat and Stable Diffusion on an Xbox Series S
Toast IDE Gets LSP Goto and Autocomplete
Visually orchestrate Claude Code agents
Grimoire – Best Practices for Everyone Installed for Your AI Agents
easy-tz – A fast, 10KB, dependency-free getTimeZonesAt(timestamp)
Otlet – Local LLM inference "inside" Postgres
Ghost Vessel – give your local LLM agent a face
MOQ5 – Open-Source C Library with MOQ Support for Both Ingest and Egress
CyberNom: Self-Hosted Threat Intel and SoC Monitoring Platform, Single Go Binary
Higgs, a local AI CLI for Proton Mail (no cloud, no telemetry)