Tools

Download and run open models such as Gemma locally with one command. Provides a REST API and Python/JS libraries, and ollama launch can point Claude Code, Codex and other agents at local models.

Open-source terminal coding agent that switches freely between model providers. Includes a build agent that edits code, a read-only plan agent for analysis, subagents, and a desktop app. Formerly sst/opencode.

Reference for the Claude API and Anthropic SDK: model selection and pricing, streaming, tool use, prompt caching, Managed Agents and more, plus workflows for model migration and prompt audits. Official Anthropic skill.

Scaffolds a Claude Agent SDK project in Python or TypeScript interactively with /new-sdk-app, then a verifier agent checks dependencies, config and code against official best practices. Maintained by Anthropic.

Local LLM inference engine in plain C/C++ with a command-line chat and an OpenAI-compatible HTTP server; pulls and runs GGUF models straight from Hugging Face. Supports Apple Silicon, CUDA, Vulkan and other hardware, plus low-bit quantization.

Google's official open-source terminal agent using Gemini models with a 1M-token context. Built-in Google Search, file and shell tools, plus MCP support. Personal Google accounts get a free quota.

High-throughput LLM inference and serving engine: vllm serve starts an OpenAI- and Anthropic-compatible server in one command. Supports 200+ model architectures from Hugging Face, quantization and distributed inference. Aimed mainly at NVIDIA, AMD and other GPUs.

Provides a sequential_thinking tool that guides the model to break complex problems into revisable, branching steps. Good for planning, analysis and tasks that need careful iteration. Official MCP reference server.

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.

AI pair programming in your terminal: builds a repo map of the whole codebase, auto-commits changes to git, works with Claude, DeepSeek, OpenAI and almost any other model including local ones, and can run lint and tests after edits.

Alibaba's open-source AI code review CLI (ocr): a deterministic pass filters and groups files and matches rules, then an agent reads the context and writes line-level comments; ocr scan reviews a whole directory. Needs an LLM endpoint, or delegate mode to hand off to your coding agent.

Turns common prompts such as summarizing, extracting insights and rewriting into reusable patterns you pipe text, web pages or YouTube transcripts through, using many model providers or local Ollama. Can also run as a REST API. Run fabric --setup first to configure models.

Detects your CPU, memory and GPU and scores open models on whether they run, speed, quality and context, then works with local runtimes like Ollama, llama.cpp and MLX to download and benchmark them. recommend --json gives agent-friendly output.

Local model gateway that routes requests from Claude Code, Codex and other coding agents to providers like DeepSeek, Kimi, Gemini and OpenRouter, with failover, rule-based routing and request logs. Bring your own API keys.

Packs a whole repository into a single AI-friendly file (XML, Markdown, JSON or plain text) with per-file token counts, automatically excludes files containing secrets, and can compress code with Tree-sitter or pack remote GitHub repos directly.

Open-source terminal coding agent from Alibaba's Qwen team with subagents, auto memory, skills and MCP. Works with Qwen, OpenAI, Anthropic, Gemini and other APIs or local models, with IDE plugins and a headless mode (qwen -p).

ModelScope's official training framework for LLMs and multimodal models: the swift command covers pretraining, fine-tuning, RL, inference, evaluation, quantization and deployment for 600+ text and 400+ multimodal models, with Megatron parallelism and a web UI. Usually needs a GPU.

Writes precise prompts for a specific AI tool: identifies the target tool, extracts your intent, asks at most three questions if details are missing, then outputs a lean, paste-ready prompt. Covers dozens of tools including ChatGPT, Claude Code, Cursor, Midjourney and Sora.

Nearly 100 skills spanning the AI research workflow: ideation and literature review, fine-tuning and post-training, distributed training, inference serving, evaluation, interpretability and paper writing, tied together by an autoresearch orchestration skill.

Plugin marketplace for AI research with nearly 100 skills in 23 categories, from ideation, fine-tuning and post-training to distributed training, inference serving, evaluation and paper writing, coordinated end to end by the autoresearch skill.

Simon Willison's LLM CLI and Python library: call OpenAI, Claude, Gemini and local models from the terminal, with conversations logged to SQLite automatically, plus embeddings, structured extraction, tool calling and a plugin system.

Lets Claude Code, Codex and other agents call Gemini, GPT, Ollama and other models to collaborate on code review, debugging, planning and multi-model consensus, and can bridge to other CLI agents. Configure at least one provider (API key or local Ollama). Formerly Zen MCP.

Teaches agents the Hugging Face Hub CLI hf: search and download models, manage datasets, Spaces, Buckets and repos, and run Jobs and inference endpoints. The skill content is generated from your local CLI, so install hf first. Maintained by Hugging Face.

Hugging Face's official skills: manage Hub models and datasets with the hf CLI, fine-tune language and vision models, run model evaluations, and build Gradio apps deployed to Spaces. Needs an HF account; cloud training on HF Jobs requires a paid plan.