#developer-tools

subagent-mcp is an MCP stdio server that turns AI coding assistants (Claude Code, Codex, Gemini CLI) into managers of local Claude and Codex sub-agents on macOS, Linux, and Windows. It orchestrates locally authenticated claude and codex CLIs and can route tasks to direct API providers.

The live network for high-quality Agent Skills — discover the latest verified versions, publish your own, and communicate agent-to-agent via MCP.

orchcli — the KubeOrch CLI for initializing, deploying, and managing Kubernetes clusters from the terminal

Structured planning and persistent context for AI coding agents. Plan multi-phase work once and any agent (Claude Code, Codex, OpenCode) executes it across sessions without losing the thread.

Stop AI agents from hallucinating progress. Generate, validate, and sync roadmaps from real repository evidence.

swarmdo — self-contained AI agent orchestration for Claude Code (swarmdo.com)

Development tools backing a-novel and a-novel-kit. Home of the a-novel CLI and AI skills.

Convention over configuration for agentic development teams

A local-first Git history explorer in your browser. One npx command gives you the commit graph, pickaxe search, side-by-side diffs, blame, PR grouping, hotspots, and a shareable Git Wrapped recap.

Multiplayer Claude Code and Codex. Self-hosted team workspace for Claude Code and Codex. Multi-user, browser-based, AI mates with memory.

Sharper context. Fewer tokens. Open-source middleware for Claude Code.

A self-hosted, keyboard-driven cockpit for running a whole fleet of Claude Code agents at once. Worktrees, command palette, scheduler, voice — every layer stacks, so you ship far more than hand-juggling terminals. Your machine, your keys, no telemetry.

Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history, tool output, and code before they're sent: -31% input / -74% output, measured live. Any provider, no extra model calls. Also an MCP server and embeddable library (Rust, Python, Ruby, Kotlin, Swift, JS/TS).

PostgreSQL compiler. One source, many faithful forms.

Laminas development mode script

A TUI markdown file browser and viewer built with Rust and ratatui

Canonical Agent Skills library for Claude Code, Cursor, Codex, and other agents.

Fast CLI for Claude Code and OpenAI Codex token/cost usage analytics

Local OpenTelemetry viewer for traces, metrics, and logs — single binary, persistent DuckDB storage, browser UI.

Production-grade SEO, AEO, and GEO agent skill with auditable detection, claim governance, evidence validation, and multi-agent installation.

AI pull-request reviewer: hybrid RAG + a code graph + Claude Code/Codex. Whole-repo context, inline GitHub comments grounded on exact code. MCP server + Claude Code/Codex plugin.

A "Token Firewall" for MCP - reduce AI token costs by 50-80% while securing your code from secret leaks.

Claude Code usage tracker and local dashboard for Pro/Max subscription limits - weekly cost-per-percent trend, quota forecasts, threshold alerts. ccusage-compatible.

Track AI API quotas across Synthetic, Z.ai, Anthropic (Claude Code), Codex, GitHub Copilot & Antigravity in real time. Lightweight background daemon (<50MB RAM), SQLite storage, Material Design 3 dashboard. Zero telemetry.

Yet another coding agent harness, lightweight and written in go.

Git-anchored decentralised intent(conversation) ledger for teams who build with AI

Structured, spec-driven development workflow for AI coding agents.

One reliable canonical source for AI coding agent rules, commands, skills, MCP, hooks, and permissions — synced across AI coding assistants.

Pin AI Skill behavior. Block unapproved drift in CI. See exactly what changed in every PR.

Professional-grade AI coding toolkit: 94 skills, 44 agents, multi-platform (Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, Augment, Antigravity, Codex CLI, opencode).