#developer-tools

D2 is a modern diagram scripting language that turns text to diagrams.

Free, local tool to track AI coding token usage and cost across 37 tools and agents (Claude Code, Cursor, Codex, Gemini and more), by model, project, and task. npx codeburn

Run Claude Code, Codex, and Gemini side by side — each in its own git worktree

Runtime security for AI agents: discover agents, map their permissions, and enforce what they can do.

One secret mapping for local dev, CI/CD, and runtime. Envilder resolves cloud secrets from your own vaults without SaaS middlemen, duplicated config, or .env drift.

1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in Anthropic's plugin directory. Plus a typed decision layer: which skill, is it safe, ship or slip. Free in-browser or npx pm-claude-skills add.

Codex CLI multi-account OAuth manager with account switching, health checks, runtime rotation, diagnostics, and recovery tools for @openai/codex

Tool for debugging LiveView applications

A native Rust terminal interface for Claude Code

Where people and agents build in tune.

Semantic version control => entity-level diffs, blame, and impact analysis on top of git. 28 languages via tree-sitter. Built for coding agents.

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

The decision layer for personal AI. Local-first runtime where agents automate across GitHub, Slack, Gmail & 45+ services — but every risky action can stop for your yes, workers (agents) earn autonomy from track record, and every decision leaves a receipt. Your models, your machine, your policy. Includes an MCP bridge: 180 IDE tools for Claude Code.

Command line tool and Go module for managing and troubleshooting Ramen

The remote-native terminal: your shell, the machine it runs on, and its files in one window. Durable SSH sessions, remote files, GPU and port views, and Command AI with the AI you already use.

Open-source context retrieval layer for AI agents

A Model Context Protocol (MCP) server for Langfuse, enabling AI agents to query Langfuse trace data for enhanced debugging and observability

Run your existing pre-commit hooks without installing Python. An independent Go reimplementation of pre-commit, measured against it on every PR.

Continuously sync your AI setups with one command. Codebase tailor suited agent skills, MCPs and config files for Claude Code, Cursor, and Codex.

Connect your users to their apps

Claude Code plugin — AI-powered autopilot for managing open source contributions. Track PRs, respond to maintainers, discover issues, maintain velocity.

Spec-to-Release for Kubernetes: turn a short app spec into a real Helm release. Zero Helm knowledge, zero cluster-side setup, one binary.

CLI proxy that reduces LLM token usage by 60-90%. Declarative YAML filters for Claude Code, Cursor, Copilot, Gemini. rtk alternative in Go.

Faker is a pure Elixir library for generating fake data.

Understand, analyze, and govern software systems across repositories, languages, and technologies.

MoFlo — an opinionated, local-first AI agent orchestration toolkit for Claude Code: semantic memory, learned routing, gates, and spells. No API keys, no cloud, works out of the box.

the runtime your coding agents live on

Encrypted secrets manager for developers and agents.

Memory and Context Orchestration for Coding Agents

The best agent harness.