#developer-tools

Select text in Claude Code, Codex CLI, GitHub Copilot CLI or Kiro CLI output and get a short explanation right under it, inside the terminal. Or ask your own question about it.

Lumo — a plugin-based, cross-language project scaffolding CLI with a versioned plugin protocol, Go SDK, and production-grade distribution (npm, Homebrew, Scoop, and more).

Опис репозиторію не опубліковано.

An OpenCode plugin that hoards tiny project-context notes so agents read less and waste fewer tokens.

AI config governance for every repo: mount layered agent instructions, skills, commands, and MCP config without copy-paste.

Forge-backed DevNotes and bug reporting for React and Next.js apps

A CLI for managing Chrome Web Store extensions: upload, publish, rollout, and more via the V2 API.

Verify that every PR review comment was addressed. CLI + GitHub Action for agentic and human review workflows.

Pause, inspect, and resume GitHub Actions locally. Stop push-and-pray debugging.

Опис репозиторію не опубліковано.

Опис репозиторію не опубліковано.

Edit on Mac. Build and test in Linux. Local workspaces for developers and coding agents.

Local-first RAG server for developers. Semantic + keyword search for code and technical docs. Works with MCP or CLI. Fully private, zero setup.

A transparent reverse-proxy for dynamic port-forwarding to Kubernetes.

Deterministic, evidence-based build harness for autonomous coding agents — FSM sprint gates, execution-evidence verification, and adversarial critics. Proof, not opinion.

Safe, observable and reversible Python environments for developers and AI coding agents. CLI, TUI and MCP server in one Go binary.

One workflow framework, every coding agent. Install your AI-coding discipline into Claude Code, Cursor, GitHub Copilot, Gemini CLI, Codex, and Windsurf from one tool-agnostic core. Apache 2.0.

Git TUI for code review in the AI-generated-code era — structural diffs, review tracking, and a --tests lens that reads a change by the tests it touches

Shortcut task picker and coding-agent launcher for Herdr

A local IPC mesh so any AI coding agent harness (Claude Code, Codex CLI, Antigravity, pi, opencode, ...) can find, message, and reactively wake up any other.

Portable context memory across local agent tools. Discovers Claude Code, Codex, Devin, Copilot and OpenCode session stores and emits a context bundle you can load into any of them.

Git-native typed knowledge + a unified, self-verifying PR view. Deterministic, LLM-free, no datastore.

Rust-native frontend build system built to replace Vite, Webpack, and Rollup.

Route the easy work your expensive Claude model keeps repeating down to haiku/sonnet — post-hoc session analysis, no realtime router, no extra LLM calls.

A terminal-native HTTP client with TUI. Uses .http files — the same format as JetBrains and VS Code REST Client. Import from Postman, Insomnia, Bruno, curl, OpenAPI. Response assertions for CI/CD. Code generation in 8 languages.

Uncompromising test isolation: your tests structurally cannot touch your real files, secrets, or git identity -- First-class support for Go, Python with pytest, and TypeScript with Node

Secure your selected route by using a middleware with static password for developers only

Опис репозиторію не опубліковано.

Turn ChatGPT Web into a real coding agent on your own repos - read, edit, build, test, git, PRs. MCP server with OAuth 2.1, driven by GPT-5.6 Sol on ChatGPT Plus/Pro. No OpenAI API key, no per-token API bill.

.gitignore for AI coding agents — tell Claude/Cursor what NOT to read