Shell projects — indie software
-
5dive
Run a company of AI agents on a server you own. Spin up named agents (claude, codex, grok…), put them on an org chart with a shared backlog, let them hand off work and ping your phone only when a human must decide. MIT.
-
AgentAlertsSkill
Agent skills for Codex/Claude to set up automations that send iPhone Live Activity, widget, notification, and Control Widget updates to your iPhone.
-
niro
Security that keeps up with your developers.
-
base-bash-libs
Sourceable Bash helper libraries for reliable shell scripts: error handling, logging, files, Git, strings, temp paths, cleanup hooks, and command runners.
-
full-upgrade
Orquestrador modular de upgrade para Arch Linux — pacman/AUR, Flatpak, Docker, toolchains, firmware e auditorias doctor num único comando
-
DO-Agent
A lightweight, self-hosted Azure DevOps agent based on Linux. Feedback is welcome.
-
dotagents
Personal AI development toolkit — skills, hooks, and verification gates that work in both Claude Code and Cursor. Installed once globally; product repositories stay untouched.
-
phel-doom
Terminal DOOM-lite raycaster built in Phel (Lisp on PHP). 256-color ANSI, 5 procedural levels — a real-world Phel showcase app.
-
forge-harness
Forge your Claude Code projects — pass them through, they come out faster.
-
5-scripts
Automate terminal tasks for file organization, disk cleanup, network scanning, duplicate detection, and window management on macOS, Linux, and Windows.
-
clikae
clikae (CLI-Kae / ｷﾘｶｴ) — an on-ramp for AI coding CLIs: type clikae and land on your recent sessions across every Claude Code, Codex & Antigravity account, each with a recap of where you left off, in a burn order whose fuel dots show which tank still has quota. Pure bash, MIT. (also switches gh/kubectl/aws…)
-
atlas-method
Build your own Claude Code OS. Forest of small domain docs. Agents do the work.
-
bigpowers
72 agent skills synthesizing 17 years of software engineering discipline into a prescriptive methodology for solo developers
-
xpam-script
Bash automation to deploy a private VLESS + Telegram (MTG) proxy stack on a clean VPS: 3x-ui/Xray behind HAProxy, nginx masking, Let's Encrypt, health/repair, DoubleHop, safe self-update.
-
spotter
Spotter is a governance layer for Claude Code. It catches scope drift, keeps honest cost telemetry, and holds every change at an approval gate. Free for individuals.
-
agent-memory
Agent Memory is a project-local Workspace Memory for AI coding agents. It is a small set of versioned Markdown files in `.agents/memory/`, so work continues across sessions, tools, local, cloud and teammates without chat history and without external infrastructure (no server, vector DB, or embeddings).
-
s-vhs
Your terminal video recorder 🖭
-
model-workspace-protocol-tool
Deterministic workspace mapper that assembles layered LLM context from your project's folder tree.
-
claude-session-tint
Know which Claude Code session needs you. Tints your terminal window by project and lights it up when a response lands unseen. MIT.
-
dracon-utilities
Invisible infrastructure for Dracon developer workspaces: git sync, system guard, and warden encryption utilities.
-
cli
Trade-intelligence CLI for AI agents
-
instincts
Working-instinct skills for Claude Code: verify claims against the source, log for the bug you can't reproduce, write like a human, test so the test bites. A reflex layer on top of superpowers.
-
openclaw-n8n-stack
Deploy an OpenClaw and n8n Docker stack for AI agents, MCP, and workflow automation in one setup
-
llm-wiki-bootstrap
An LLM builds and maintains your personal wiki. Vectorless, cited, git-native markdown — five slash commands, no SaaS.
-
contextium
Build an AI operating system for context, memory, and agent workflows
-
scoop-bucket
Scoop manifests for Glyndor's Windows binaries — the Windows counterpart to apt.glyndor.net
-
godplans
Plan everything before anything. Single-command AI agent skill that emits a complete, audit-proof, agent-executable master plan (PLAN.mdx) before any code is written. Claude Code, Codex, Cursor, OpenCode, and every Agent Skills client.
-
claude-studio-pro
A governized pipeline fit for Claude Code to deliver quality output comparable to an established team of software and web engineers within modern standards
-
ccproxy
Use Cursor IDE with your Claude Pro/Max subscription. A one-command, self-hosted bridge that connects Cursor (Agent + chat) to Claude via OAuth — no per-token API key needed.
-
hikizan
Claude Code plugin / Agent Skills pack — verb-split skills for design, review, TDD, and PR flow, with deterministic git hooks as safety floors
-
scrubjay
Recall what · where · when. Sync your AI coding agents across machines: git config-sync + a peer-to-peer transcript relay to your own NAS (or GitHub), with topic recall over MCP. Claude Code, opencode, codex.
-
cc-skills
Build reusable AI agent skills for marketing and engineering tasks with on-demand, domain-specific guidance.
-
ai-workflow-wizard
AI-Native Development Workflow Wizard — Bootstrap, configure, and maintain professional AI development workflows in any project
-
dgx-spark-ai
Run GPT-OSS 120B on NVIDIA DGX Spark with vLLM, build an API server, and create a local AI coding assistant
-
judgment-pack-demo
Research preview: clone-and-go sandbox demo for Judgment Packs — browser workspace with file explorer, BYOK, and the runtime pre-wired over MCP.
-
jeffy-loop
Autonomous audit-fix-verify loop for Claude Code. Run against 17 open source projects in 8 languages, 15 converged, 2 fixes merged upstream (one shipped in chalk v6.0.0). Public journal for every run.
-
notebooklm-toolkit
Manage Google NotebookLM tasks with command-line scripts that replace browser extensions for bulk imports, transcript downloads, and cross-notebook searches.
-
lmctl
A provider-agnostic control plane for teams of AI coding agents — across providers, with independent review and durable memory. Homepage + docs source for lmctl.com.
-
second-shift
The dev team that works while you're away — an autonomous ticket-to-PR development toolkit for Claude Code: pipeline, multi-agent review, intake/elicitation, design fidelity, and session auditing.
-
evolab
A² · Agentic AI × Anything：多 agent 编排方法论与治理 skill 合集（旗舰 cto-orchestration）
-
agent-native-cli
Evaluate and design CLI tools that function reliably for humans, AI agents, and orchestration systems through automated schema, safety, and interface reviews.
-
tmux-spotlight
A minimalist tmux session manager and a window spotlight for tmux because others was just too noisy. Rounded popups, live previews, and zero clutter.
-
claude-code-plugins
Melodic Software — Claude Code plugin marketplace: reusable, repo-agnostic skills, hooks, agents, and MCP servers.
-
terminalphone
Send encrypted voice and text messages via Tor hidden services with this self-contained Bash script for anonymous, serverless communication.
-
claude-tab-status
Spinning ring on your terminal tab while Claude Code works; stopped ring + bell when it needs you. OSC 9;4 hooks for Windows Terminal, Ghostty, iTerm2, GNOME Terminal.
-
headscale-install
Install and configure a Headscale server on Linux with automated setup, user management, and verified binaries
-
claude-power-setup
Orchestrate multi-agent workflows and automate complex pipelines for Claude Code with recursive self-improvement tools.
-
tconvert
A fast, fully offline command-line file converter and compressor. Convert videos, audio, images, documents, and data formats instantly with absolute privacy and zero cloud dependency.
-
tdocker
A lightweight terminal-based container manager for Docker and Podman. Deploy, update, encrypt, and manage your containers from a single interactive CLI without heavy web dashboards.
-
terminal-shortcuts
Simple one-word terminal commands for Linux and macOS to automate common tasks.
-
nat-reality-bridge
Low-resource NAT VPS Xray Reality deployment with 9929/CMI entry and ISP Residential Exit architecture.
-
tux2lab
Build your own automated KVM-based Linux VM provisioning virtual datacenter/homelab with your own internal domain. Powered by JBOBS.
-
claude-plugins
NebInfra Claude Code plugin marketplace
-
autopilot
Two Claude Code slash commands: /autopilot drives JS/TS fullstack tasks to verified, unattended completion; /autopilot-eval grades each run hands-on (re-runs tests + browser, not self-report).
-
ark-fleet
Bare metal to a clustered ARK: Survival Evolved deployment, entirely as code — PXE netboot install, Ansible configuration management, version-pinned and checksum-verified tooling, NFS cluster storage, and unattended weekly patching. The game servers are the excuse; the pipeline is the point.
-
huntkit
Automate OSINT investigations and threat intelligence workflows with this Claude Code toolkit for case management and evidence collection.
-
agent-md
Install portable agent rules, hooks, and task state for coding agents to stop guessing and verify work across Claude, Codex, Cursor, and Windsurf
-
oss-stack
oss-stack is a collection of scripts, blocklists, and labs you can run to self-host your own professional IT infrastructure.
-
ghostty-agent-forge
Terminal visibility, zsh/Homebrew bootstrap, and ContextLattice hooks for local AI agents on macOS.
-
gh-pr
cli to run some frequently use gh pr commands