cli

Chamber is a local-first CLI that prevents AI citation fabrication by never exposing document IDs to the model, then verifies cited passages via hashing. It supports any OpenAI-compatible endpoint and runs without config, database, or network.

A tweet by @tobi demonstrating how to use herdr, a CLI tool, by launching an agent and running `herdr --skill` to create a sci-fi-style hacker terminal setup.

Recommends installing Office CLI; combined with large language models and PPT/data-analysis Skills, it can significantly boost office productivity.

Us vs. Them is a CLI/library that analyzes git history to provide line-level provenance, showing which lines of text were written by humans versus AI agents under agentic editing.

Hermes Wingtips #41 introduces `hermes approvals suggest`, a command that mines past approvals to propose allowlist suggestions for recurring commands, letting users pick what to auto-approve while keeping manual control.

httptap is a Python CLI that dissects HTTP requests into phases like DNS, TCP, TLS, and data transfer to generate detailed waterfall timelines for troubleshooting and performance analysis.

An open-source CLI tool that scaffolds production-ready AI agent projects in seconds, simplifying setup for Python developers.

PentesterFlow is an open-source terminal assistant for authorized offensive-security work that plans against scoped targets, uses pentesting tools, requests approval for sensitive actions, retains lessons across sessions, and writes evidence-backed findings. It includes built-in skills for recon and web vulnerabilities, session continuity features, local continuous learning, and Burp integration.

Recommended to pay attention to Claude Code's capabilities, from which you can migrate harness-related features into your own product. Claude Code is a terminal agent programming tool introduced by Anthropic that supports natural language operations.

Slap is a free, open-source, multiplatform ROM patcher that supports twenty patch formats, with a CLI and web version, designed for scripting and robust error reporting.

CCPlugins is a curated set of 24 professional commands that extends Claude Code CLI with structured development workflows including cleanup, commits, formatting, testing, refactoring, and security checks, with safety controls and MIT license.

A cheat sheet of essential slash commands for Google Antigravity's CLI, covering planning, customization, subagents, and workspace utilities to improve developer workflow.

Dembrandt is an open-source CLI tool that extracts a website's design system—logos, colors, typography, borders, spacing, and more—into design tokens. It supports MCP integration for AI agents and offers a companion app for drift tracking and visual diffs.

Introducing the open-source AI coding agent tool Cline, supporting the SDK, CLI, VS Code, and the JetBrains suite. It can automatically read code, create files, and run commands in the IDE and terminal, and supports kanban-based parallel multi-agent workflows and CI/CD integration.

Fius is a unified AI model aggregator tool that combines multiple AI providers like OpenAI, Google, Mistral, and DeepSeek into one code editor and API, with simple pricing plans.

Whop CLI lets you run your entire business from the terminal, as showcased on Product Hunt.

Una librería en Rust que convierte documentos Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV y PDF a Markdown, disponible vía npm, Python y CLI, destacando su utilidad para LLMs.

Kiro Crew is an open-source AI agent platform, originally built inside Amazon, that coordinates engineering work across tools and runs tasks autonomously. It has been adopted by over 39,000 Amazon builders with nearly 500 contributors, and is now released publicly to let developers inspect, run, and extend it.

A technical deep-dive that records and analyzes the exact HTTP requests Codex CLI sends to the model, measuring token counts and how instructions, tools, and context are bundled.

LLM 0.32 adds visible reasoning traces, server-side tools, new GPT-5.6 models, and redesigned logging, plus a new llm openai endpoint command for any OpenAI-compatible endpoint.