Инструменты

All-in-one LLM fine-tuning framework: llamafactory-cli handles pretraining, SFT, PPO/DPO alignment and LoRA/QLoRA training, plus chat inference, weight merging and export, and OpenAI-style API serving for 100+ open models. Has a Web UI; training usually needs a GPU.

HeyGen's official HyperFrames skill set: lets agents write deterministic MP4 videos in HTML, CSS and animation, with workflows for promo videos, explainers, captions and beat-synced music. Needs Node.js 22+ and FFmpeg.

HeyGen's official video plugin: compose scenes with HTML, CSS and animation and render deterministic MP4s, with skills for promo videos, captions, voiceover and music, and PR walkthrough videos. Needs Node.js 22+ and FFmpeg.

Runs GitHub Actions workflows locally in Docker, so you can test .github/workflows changes without repeated commits and pushes, or use workflows as a local task runner. Needs Docker installed.

Write videos in HTML, CSS and frame-seekable animations, preview them from the CLI and render deterministic MP4s. Comes with agent skills for product launch videos, captions and talking-head re-edits. Maintained by HeyGen; needs Node.js 22+ and FFmpeg.

Open-source agentic video production: open Claude Code or Codex in the cloned repo, describe the video, and the agent handles research, script, voiceover, footage, subtitles and editing, confirming storyboard and cost first. Needs Python, Node.js and FFmpeg; free assets work without API keys.

Agentless IT automation: uses SSH and playbooks for configuration management, app deployment, cloud orchestration and ad hoc commands at scale, with nothing to install on target machines. Maintained primarily by Red Hat.

Official Cline CLI sharing its agent core with the VS Code extension: plan/act modes, MCP, checkpoints and subagents; --yolo and --json run it unattended in CI and scripts. Sign in with Cline or a ChatGPT subscription, or bring your own API key.

Parses PDF, DOCX, PPTX, XLSX, HTML, images and audio, recovering layout, reading order, tables and formulas, and exports Markdown, HTML or lossless JSON. Started by IBM Research, now hosted by the LF AI & Data Foundation; runs fully locally.

Fast regex search across directories (command rg) that respects .gitignore, skips hidden and binary files by default and filters by file type. A go-to command for coding agents searching a codebase.

Write videos in React and render them from the command line with npx remotion render, letting agents batch-produce data-driven videos. Free for individuals, nonprofits and companies of up to 3 people; larger for-profit companies need a license.

Command-line toolkit for transcoding, cutting, joining, frame extraction and streaming of audio and video, including ffmpeg, ffprobe and ffplay. A core dependency for agents handling media. The GitHub repo is the official mirror.

Community-maintained simplified command help with example-first pages for common CLI tools, easier to read than man. Install an official client (Python, Rust or Node.js), then run tldr followed by a command name.

A cat replacement with syntax highlighting, line numbers and Git change markers, plus --line-range to print specific lines. Falls back to plain text in pipes and other non-interactive use, and pairs with git diff or tail -f for code and logs.

'rsync for cloud storage': sync and copy files across dozens of providers such as S3, Google Drive, OneDrive and Alibaba Cloud OSS, with encryption and mounting. Set up remotes with rclone config before use.

Creates a local CA with one command and issues development HTTPS certificates trusted by your system and browsers, for localhost, IPs and wildcard domains, with no extra configuration. Run mkcert -install once first to add the root certificate to the trust store.

MuseScore 4 command-line wrapper from CLI-Anything: lets agents transpose scores, extract parts, add or remove instruments, inspect score info and export PDF, MIDI, MusicXML, MP3 or braille. Handy for music teachers preparing scores in bulk. Needs MuseScore 4 and Python 3.10+.

From HKU's Data Intelligence Lab: plugins or skills for Claude Code, Codex and other agents generate agent-callable CLIs for apps like GIMP, Blender and LibreOffice, and the cli-hub package manager finds and installs ready-made community CLIs. Needs Python 3.10+.

Open-source crypto trading framework: download market data, backtest and optimize strategies, and paper trade from the CLI while agents iterate on strategies. Docker recommended; strategies need Python and live trading needs exchange API keys. Backtests don't guarantee returns.

General-purpose AI agent that runs on your machine, with a desktop app, CLI and API. Written in Rust, works with 15+ model providers and connects to 70+ extensions via MCP. Originally from Block, now part of the Linux Foundation's AAIF.

C/C++ port of OpenAI's Whisper speech recognition model that transcribes audio offline and outputs subtitles. Runs on CPU, with Apple Silicon and various GPU acceleration. Download a ggml-format model first.

Astral's extremely fast Python linter and formatter written in Rust, replacing Flake8, isort and Black, with 900+ built-in rules and auto-fix.

HashiCorp's infrastructure-as-code tool: manage multi-cloud and SaaS resources with declarative config, previewing changes with plan before running apply. Providers cover all major clouds. Licensed under BSL 1.1.

Package manager for macOS and Linux: agents can brew install CLI tools and desktop apps (casks), or use brew bundle to restore a dev environment from a Brewfile.