- Columbus OH
-
03:42
(UTC -04:00) - https://armyofminions.com
- @jrgifford
Highlights
Lists (29)
Sort Name ascending (A-Z)
claude
codex
containers
db migrations
Education
🚂 gems
Go
hackweek ideas
kube
linux tools
LLM
mac tools
Nifty tools
obsidian
Org Stuff
pentest
rails
rails debugging
raspberry pi projects
remarkable 2
remote llm
ruby
security tools
self hosting
Sidekiq Tools
social media
temporal
testing
Workflowy
- All languages
- ActionScript
- ApacheConf
- AppleScript
- Arduino
- Assembly
- Astro
- Batchfile
- Bikeshed
- C
- C#
- C++
- COBOL
- CSS
- Clojure
- CoffeeScript
- Common Lisp
- Crystal
- Dart
- Dockerfile
- Elixir
- Elm
- Emacs Lisp
- Erlang
- Fortran
- Genshi
- Go
- Groff
- Groovy
- HCL
- HTML
- Handlebars
- Haskell
- Java
- JavaScript
- Jinja
- Jupyter Notebook
- Kotlin
- Less
- Lua
- M
- MDX
- Makefile
- Markdown
- NSIS
- Nunjucks
- Objective-C
- Objective-C++
- OpenEdge ABL
- OpenSCAD
- PHP
- PLpgSQL
- Pascal
- Perl
- PowerShell
- Processing
- Puppet
- Python
- R
- Raku
- Rebol
- Roff
- Ruby
- Rust
- SCSS
- Scala
- Shell
- Smarty
- Svelte
- Swift
- TSQL
- Tcl
- TeX
- Twig
- TypeScript
- Vala
- Vim Script
- Vue
- XSLT
- YAML
- hoon
Starred repositories
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-rep…
Synapse: Matrix homeserver written in Python/Twisted + Rust
An Open-Source Asynchronous Coding Agent
Agentic AI security tool that applies proactive, attacker-first analysis directly to source code.
GLM-5.2-NVFP4-REAP-469B serving on SM120 (4× RTX PRO 6000 Blackwell) — one-command vLLM launch recipe, 250K context, DeepSeek Sparse Attention + MTP speculative decode
Think Claude Code's auto mode but for pi. Selectable model, sensible defaults.
Give coding agents a disposable Linux VM, not your laptop
macOS CLI for OCR and searchable PDFs using Apple's Vision framework
Crabbox: warm a box, sync the diff, run the suite.
Golem Cloud is the agent-native platform for building AI agents and distributed applications that never lose state, never duplicate work, and never require you to build infrastructure.
Tencent Hy3 295B MoE (NVFP4) on 2x NVIDIA DGX Spark — TP2 over 200GbE, 256K context, 26 tok/s end-to-end. Tuned, benchmarked, agent-ready.
A native macOS terminal for agent-driven development, built on Ghostty.
A desktop app for isolated, parallel agentic development
AI-powered macOS development workspace. Git worktrees, Claude Code sessions, and dev servers in a single native app.
Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability.
🦦 ADHDev — Agent Dashboard Hub. Monitor & control AI coding agents from a single dashboard. Self-hosted, open-source.
A self-hosted email client with an AI agent, running entirely on Cloudflare Workers
Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents.
keys-Nvidia — TRUE Two-Tower diffusion, NVFP4 APPLIED: Nemotron-Labs-TwoTower-30B split across two DGX Sparks over 200G fabric; NVFP4 experts + grouped Triton W4A16 GEMM = 38.9 tok/s, beats AR 1.4-…
The open-source skills that turn your agent into a full PR team.
Patterns for building software that handles money
DeepSeek V4 Flash DSpark 1M NVFP4 KV recipe for 2x DGX Spark