https://guides-ai.com/ Short, numbered, copy-paste AI guides — Claude Code, ChatGPT, MCP, local models, prompting, the API. New and revised plates, newest first. en Sun, 01 Nov 2026 00:00:00 GMT https://guides-ai.com/guides/connect-guides-ai-mcp-server/ https://guides-ai.com/guides/connect-guides-ai-mcp-server/ Sun, 01 Nov 2026 00:00:00 GMT MCP Add the guides-ai MCP server to Claude Code, Cursor, or any agent with one URL. No install, no token. Then search the whole guide library from chat. https://guides-ai.com/guides/fix-huggingface-download-incomplete/ https://guides-ai.com/guides/fix-huggingface-download-incomplete/ Wed, 21 Oct 2026 00:00:00 GMT Hugging Face Resume a stuck hf download, clear broken .incomplete partials with hf cache prune, and speed transfers with hf_xet when disk space allows. https://guides-ai.com/guides/openai-api-function-calling/ https://guides-ai.com/guides/openai-api-function-calling/ Wed, 21 Oct 2026 00:00:00 GMT Building with the API Give the model your own functions with the OpenAI Responses API: define a tool, run the call it returns, and send the result back in a loop. https://guides-ai.com/guides/gemini-api-structured-output/ https://guides-ai.com/guides/gemini-api-structured-output/ Wed, 21 Oct 2026 00:00:00 GMT Building with the API Make the Gemini API return JSON that matches a Pydantic schema with the google-genai SDK, then parse it into a typed object. https://guides-ai.com/guides/gemini-api-file-search/ https://guides-ai.com/guides/gemini-api-file-search/ Wed, 21 Oct 2026 00:00:00 GMT Building with the API Create a managed File Search store with the google-genai SDK, import a file, query it with the file_search tool, and read citations. https://guides-ai.com/guides/count-tokens-and-estimate-cost/ https://guides-ai.com/guides/count-tokens-and-estimate-cost/ Wed, 21 Oct 2026 00:00:00 GMT Building with the API Count tokens locally with tiktoken or Anthropic's count_tokens endpoint, then estimate cost from each provider's published per-token prices. https://guides-ai.com/guides/claude-api-files-api/ https://guides-ai.com/guides/claude-api-files-api/ Wed, 21 Oct 2026 00:00:00 GMT Building with the API Upload a PDF once with the Claude Files API, reference it by file_id across requests in Python, then list and delete it. https://guides-ai.com/guides/github-copilot-cli-authentication/ https://guides-ai.com/guides/github-copilot-cli-authentication/ Wed, 21 Oct 2026 00:00:00 GMT Other coding agents Log in to GitHub Copilot CLI with /login, check your Copilot subscription, and set GITHUB_TOKEN for CI with the Copilot Requests permission. https://guides-ai.com/guides/devin-desktop-first-steps/ https://guides-ai.com/guides/devin-desktop-first-steps/ Wed, 21 Oct 2026 00:00:00 GMT Other coding agents Access Devin by Cognition: the cloud web app, Devin Desktop IDE (formerly Windsurf), CLI and Slack, plus how it differs from terminal agents. https://guides-ai.com/guides/coding-agents-compared/ https://guides-ai.com/guides/coding-agents-compared/ Wed, 21 Oct 2026 00:00:00 GMT Other coding agents Compare Claude Code, Codex CLI, Copilot CLI, Cursor, OpenCode and Windsurf: terminal vs IDE, provider lock-in, MCP, open source and cost. https://guides-ai.com/guides/codex-cli-mcp/ https://guides-ai.com/guides/codex-cli-mcp/ Wed, 21 Oct 2026 00:00:00 GMT Other coding agents Enable MCP servers in OpenAI Codex CLI: config.toml location, the exact mcp_servers TOML shape, a worked example, and how to confirm it loaded. https://guides-ai.com/guides/which-local-model-should-i-run/ https://guides-ai.com/guides/which-local-model-should-i-run/ Wed, 21 Oct 2026 00:00:00 GMT Choosing tools Choose a local LLM by what fits your RAM and VRAM first, then by task, with starter picks for 8GB, 16GB, and 24GB machines. https://guides-ai.com/guides/local-model-in-cursor-or-claude-code/ https://guides-ai.com/guides/local-model-in-cursor-or-claude-code/ Wed, 21 Oct 2026 00:00:00 GMT Local LLMs Point Cursor's chat at a local OpenAI-compatible model, and see why Claude Code cannot use a non-Claude or local model as its backend. https://guides-ai.com/guides/fix-pip-install-torch-cuda/ https://guides-ai.com/guides/fix-pip-install-torch-cuda/ Wed, 21 Oct 2026 00:00:00 GMT Local LLMs Plain pip install torch gives a CPU-only build on Windows. Install from the PyTorch index URL that matches your CUDA, then verify the GPU. https://guides-ai.com/guides/fix-ollama-out-of-memory/ https://guides-ai.com/guides/fix-ollama-out-of-memory/ Wed, 21 Oct 2026 00:00:00 GMT Local LLMs Ollama ran out of memory or the model is too large. Check the split with ollama ps, then cut the model, the quant, or the context window. https://guides-ai.com/guides/fix-ollama-model-not-found/ https://guides-ai.com/guides/fix-ollama-model-not-found/ Wed, 21 Oct 2026 00:00:00 GMT Local LLMs ollama run says model not found? Pull the exact model:tag first, fix a wrong or case-sensitive tag, or run a GGUF straight from Hugging Face. https://guides-ai.com/guides/fix-cuda-out-of-memory/ https://guides-ai.com/guides/fix-cuda-out-of-memory/ Wed, 21 Oct 2026 00:00:00 GMT Local LLMs torch.OutOfMemoryError: CUDA out of memory means the GPU is full. Lower the batch size, use float16 or 4-bit, offload to CPU, or clear the cache. https://guides-ai.com/guides/call-a-local-model-openai-compatible/ https://guides-ai.com/guides/call-a-local-model-openai-compatible/ Wed, 21 Oct 2026 00:00:00 GMT Local LLMs Ollama, LM Studio, llama.cpp and vLLM all expose an OpenAI-compatible /v1 API. List models, run a chat completion, and stream from one SDK. https://guides-ai.com/guides/cursor-background-agents/ https://guides-ai.com/guides/cursor-background-agents/ Wed, 21 Oct 2026 00:00:00 GMT Cursor Cursor renamed Background Agents to Cloud Agents. Run async agents in a cloud VM on your repo, review their PRs, and learn the privacy limits. https://guides-ai.com/guides/claude-code-docker-devcontainer/ https://guides-ai.com/guides/claude-code-docker-devcontainer/ Wed, 21 Oct 2026 00:00:00 GMT Workflows Add Anthropic's official dev container feature to .devcontainer/devcontainer.json, rebuild, and run claude inside an isolated, reproducible container. https://guides-ai.com/guides/fix-claude-code-rate-limit/ https://guides-ai.com/guides/fix-claude-code-rate-limit/ Wed, 21 Oct 2026 00:00:00 GMT Claude Code commands Hit a usage or rate limit in Claude Code? What the session, weekly, and per-model limits mean, and the fastest ways to get working again. https://guides-ai.com/guides/claude-code-output-styles/ https://guides-ai.com/guides/claude-code-output-styles/ Wed, 21 Oct 2026 00:00:00 GMT Claude Code commands List, switch, and build output styles in Claude Code with /output-style, and see how a style differs from CLAUDE.md and the system prompt. https://guides-ai.com/guides/claude-code-memory-hierarchy/ https://guides-ai.com/guides/claude-code-memory-hierarchy/ Wed, 21 Oct 2026 00:00:00 GMT Claude Code commands Claude Code concatenates CLAUDE.md from managed policy, your home dir, the project, then CLAUDE.local.md. Inspect it with /memory and @path imports. https://guides-ai.com/guides/claude-code-choose-a-model/ https://guides-ai.com/guides/claude-code-choose-a-model/ Wed, 21 Oct 2026 00:00:00 GMT Claude Code commands Switch between Opus, Sonnet, and Haiku with /model, set a default, and match the model to the job without guessing at prices or benchmarks. https://guides-ai.com/guides/claude-code-jetbrains/ https://guides-ai.com/guides/claude-code-jetbrains/ Wed, 21 Oct 2026 00:00:00 GMT Install & set up Install the Claude Code [Beta] plugin from the JetBrains Marketplace, run claude in the IDE terminal, and connect external sessions with /ide. https://guides-ai.com/guides/opencode-first-steps/ https://guides-ai.com/guides/opencode-first-steps/ Mon, 19 Oct 2026 00:00:00 GMT Other coding agents Install the OpenCode CLI, connect a cloud or local Ollama model, open a project, give the agent a task, and compare it to Claude Code and Cursor. https://guides-ai.com/guides/agents-md-file/ https://guides-ai.com/guides/agents-md-file/ Mon, 19 Oct 2026 00:00:00 GMT Other coding agents AGENTS.md is the cross-agent conventions file. Where to put it, what to write, which tools read it, and how Claude Code loads it next to CLAUDE.md. https://guides-ai.com/guides/run-ocr-locally/ https://guides-ai.com/guides/run-ocr-locally/ Mon, 19 Oct 2026 00:00:00 GMT AI media Install indra-ocr, run a CPU-only OCR model on an image, pull Markdown from a multi-page PDF, batch files, and find where the weights cache. https://guides-ai.com/guides/generate-video-with-ltx-locally/ https://guides-ai.com/guides/generate-video-with-ltx-locally/ Mon, 19 Oct 2026 00:00:00 GMT AI media Run Lightricks LTX-Video on your own GPU with a short diffusers script: LTXPipeline, text-to-video, frames and steps, plus the ComfyUI route. https://guides-ai.com/guides/describe-images-with-a-vision-model/ https://guides-ai.com/guides/describe-images-with-a-vision-model/ Mon, 19 Oct 2026 00:00:00 GMT AI media Load Qwen3-VL-8B-Instruct with transformers, pass an image plus a question, and get captions, chart reads and answers on your own GPU. https://guides-ai.com/guides/clone-a-voice-locally/ https://guides-ai.com/guides/clone-a-voice-locally/ Mon, 19 Oct 2026 00:00:00 GMT AI media Use ResembleAI Chatterbox (MIT) to clone a voice from a short reference clip in a few lines of Python, with the consent caveat up front. https://guides-ai.com/guides/ollama-vs-lm-studio/ https://guides-ai.com/guides/ollama-vs-lm-studio/ Mon, 19 Oct 2026 00:00:00 GMT Choosing tools Ollama is a scriptable CLI and daemon; LM Studio is a desktop app with a model browser. Both run GGUF locally, so pick by workflow, not quality. https://guides-ai.com/guides/local-embeddings-embeddinggemma/ https://guides-ai.com/guides/local-embeddings-embeddinggemma/ Mon, 19 Oct 2026 00:00:00 GMT Prompting Install sentence-transformers, load EmbeddingGemma 2, encode queries and documents with its prefixes, score cosine similarity, and feed a vector DB. https://guides-ai.com/guides/ollama-gpu-not-detected/ https://guides-ai.com/guides/ollama-gpu-not-detected/ Mon, 19 Oct 2026 00:00:00 GMT Local LLMs Ollama ran on CPU instead of your GPU. Confirm it with ollama ps, then fix the driver, Docker and WSL passthrough, or a model too big for VRAM. https://guides-ai.com/guides/local-llm-apple-silicon-mlx/ https://guides-ai.com/guides/local-llm-apple-silicon-mlx/ Mon, 19 Oct 2026 00:00:00 GMT Local LLMs MLX is Apple's framework for M-series Macs. Install mlx-lm, generate from a Hugging Face model, and serve an OpenAI-style API with mlx_lm.server. https://guides-ai.com/guides/claude-code-usage-limits/ https://guides-ai.com/guides/claude-code-usage-limits/ Mon, 19 Oct 2026 00:00:00 GMT Claude Code commands What session, weekly, and per-model limits mean on Pro and Max, how /usage shows your plan usage, and what to do when you hit a limit. https://guides-ai.com/guides/claude-code-wsl-windows/ https://guides-ai.com/guides/claude-code-wsl-windows/ Mon, 19 Oct 2026 00:00:00 GMT Install & set up Enable WSL with wsl --install, run the Linux installer for Claude Code inside Ubuntu, fix the PATH, and keep projects on the Linux filesystem. https://guides-ai.com/guides/hugging-face-mcp-server-claude-code/ https://guides-ai.com/guides/hugging-face-mcp-server-claude-code/ Mon, 12 Oct 2026 00:00:00 GMT Hugging Face Add https://huggingface.co/mcp with a read token so your agent searches models, datasets, papers and docs from the chat, and uses MCP Spaces as tools. https://guides-ai.com/guides/deploy-gradio-app-hugging-face-spaces/ https://guides-ai.com/guides/deploy-gradio-app-hugging-face-spaces/ Mon, 12 Oct 2026 00:00:00 GMT Hugging Face Write a minimal Gradio app.py, add requirements.txt and a Space README, create the Space, push with the hf CLI, set secrets, and read the build logs. https://guides-ai.com/guides/hugging-face-upload-model-or-dataset/ https://guides-ai.com/guides/hugging-face-upload-model-or-dataset/ Mon, 12 Oct 2026 00:00:00 GMT Hugging Face Log in, create a repo with hf repos create, push files with hf upload and include/exclude, write a minimal README card, and do the same from Python. https://guides-ai.com/guides/hugging-face-datasets-load-stream-filter/ https://guides-ai.com/guides/hugging-face-datasets-load-stream-filter/ Mon, 12 Oct 2026 00:00:00 GMT Hugging Face Load a Hub dataset split, inspect its features, stream one too big to download, filter and batch-map it, then save it as Parquet or JSONL. https://guides-ai.com/guides/hugging-face-inference-providers-first-request/ https://guides-ai.com/guides/hugging-face-inference-providers-first-request/ Mon, 12 Oct 2026 00:00:00 GMT Hugging Face One HF token, one endpoint: call an open model with InferenceClient, the OpenAI SDK or curl, pick a provider, and see how billing works. https://guides-ai.com/guides/transformers-pipeline-quickstart/ https://guides-ai.com/guides/transformers-pipeline-quickstart/ Mon, 12 Oct 2026 00:00:00 GMT Hugging Face Install PyTorch and transformers, chat with a small instruct model via pipeline(), set device_map, dtype and max_new_tokens, then classify an image. https://guides-ai.com/guides/run-hugging-face-gguf-with-ollama-llama-cpp/ https://guides-ai.com/guides/run-hugging-face-gguf-with-ollama-llama-cpp/ Mon, 12 Oct 2026 00:00:00 GMT Hugging Face Pick a GGUF quant in the Files tab, then run it with ollama run hf.co/user/repo or llama-cli -hf user/repo:QUANT. https://guides-ai.com/guides/hugging-face-gated-models-access/ https://guides-ai.com/guides/hugging-face-gated-models-access/ Mon, 12 Oct 2026 00:00:00 GMT Hugging Face Accept the model licence, create a read or fine-grained token, log in with hf auth login, set HF_TOKEN for CI, and fix 401/403 errors. https://guides-ai.com/guides/hugging-face-cache-location/ https://guides-ai.com/guides/hugging-face-cache-location/ Mon, 12 Oct 2026 00:00:00 GMT Hugging Face Find the hf CLI cache path on Windows, macOS and Linux, inspect it with hf cache ls, move it with HF_HOME, and prune old models. https://guides-ai.com/guides/hugging-face-find-the-right-model/ https://guides-ai.com/guides/hugging-face-find-the-right-model/ Mon, 12 Oct 2026 00:00:00 GMT Hugging Face Filter the Models page by task, library, language, license and size, read the sort signals and the model card, pick a file, and search from the API. https://guides-ai.com/guides/hugging-face-cli-download-models/ https://guides-ai.com/guides/hugging-face-cli-download-models/ Sun, 06 Sep 2026 00:00:00 GMT Hugging Face Install the hf CLI, log in, download one GGUF instead of a whole repo with --include, put files where you want with --local-dir, and clean the cache. https://guides-ai.com/guides/rag-with-python-minimal/ https://guides-ai.com/guides/rag-with-python-minimal/ Sun, 06 Sep 2026 00:00:00 GMT Building with the API Chunk a folder of Markdown, embed it with Voyage, retrieve top-k with a numpy dot product, and answer with Claude citing the chunks it used. https://guides-ai.com/guides/openai-file-search-rag/ https://guides-ai.com/guides/openai-file-search-rag/ Sun, 06 Sep 2026 00:00:00 GMT Building with the API Upload files to an OpenAI vector store, attach the file_search tool to a Responses API call, and get cited answers. No embeddings code, no database. https://guides-ai.com/guides/openai-api-image-generation/ https://guides-ai.com/guides/openai-api-image-generation/ Sun, 06 Sep 2026 00:00:00 GMT Building with the API Two ways to make an image with the OpenAI API — the Images endpoint and the image_generation tool — save the PNG, set size, quality and format. https://guides-ai.com/guides/gemini-api-first-request/ https://guides-ai.com/guides/gemini-api-first-request/ Sun, 06 Sep 2026 00:00:00 GMT Building with the API Get a Gemini API key from AI Studio, set GEMINI_API_KEY, install the google-genai SDK, and make a working request with the Interactions API. https://guides-ai.com/guides/embeddings-explained-with-code/ https://guides-ai.com/guides/embeddings-explained-with-code/ Sun, 06 Sep 2026 00:00:00 GMT Building with the API What an embedding vector actually is, how to compute two and compare them in Python, and which model and dimension to pick. https://guides-ai.com/guides/claude-api-vision-images/ https://guides-ai.com/guides/claude-api-vision-images/ Sun, 06 Sep 2026 00:00:00 GMT Building with the API The image content block in Python and curl, the format and size limits from the docs, and a screenshot-to-CSV extraction that doesn't invent numbers. https://guides-ai.com/guides/claude-api-thinking-and-effort/ https://guides-ai.com/guides/claude-api-thinking-and-effort/ Sun, 06 Sep 2026 00:00:00 GMT Building with the API Turn on adaptive thinking, read thinking blocks, set depth with output_config.effort (low to max), stream deltas, and know what budget_tokens does. https://guides-ai.com/guides/claude-api-pdf-documents/ https://guides-ai.com/guides/claude-api-pdf-documents/ Sun, 06 Sep 2026 00:00:00 GMT Building with the API The document content block in Python, the page and size limits from the docs, citations that point at a page — and when to pre-extract text instead. https://guides-ai.com/guides/claude-agent-sdk-typescript-quickstart/ https://guides-ai.com/guides/claude-agent-sdk-typescript-quickstart/ Sun, 06 Sep 2026 00:00:00 GMT Building with the API Install @anthropic-ai/claude-agent-sdk, stream an agent that edits real files, gate its tools, and read the final result message. https://guides-ai.com/guides/claude-agent-sdk-python-quickstart/ https://guides-ai.com/guides/claude-agent-sdk-python-quickstart/ Sun, 06 Sep 2026 00:00:00 GMT Building with the API Install claude-agent-sdk, run an agent that reads and edits real files, control which tools it may use, and read the final result. https://guides-ai.com/guides/stream-llm-responses/ https://guides-ai.com/guides/stream-llm-responses/ Sun, 06 Sep 2026 00:00:00 GMT Building with the API Print tokens as they arrive from the Claude and OpenAI APIs — Python and JavaScript, plus the raw SSE events and how to detect the end. https://guides-ai.com/guides/openai-api-structured-outputs/ https://guides-ai.com/guides/openai-api-structured-outputs/ Sun, 06 Sep 2026 00:00:00 GMT Building with the API Constrain Responses API output with text.format json_schema, parse it straight into Pydantic or Zod, and reuse strict schemas for function calling. https://guides-ai.com/guides/openai-api-first-request/ https://guides-ai.com/guides/openai-api-first-request/ Sun, 06 Sep 2026 00:00:00 GMT Building with the API Create a key, set OPENAI_API_KEY, and make a working Responses API call in curl, Python, and Node — the API OpenAI recommends for new projects. https://guides-ai.com/guides/claude-api-batch-requests/ https://guides-ai.com/guides/claude-api-batch-requests/ Sun, 06 Sep 2026 00:00:00 GMT Building with the API Create a batch of Messages requests, poll processing_status, stream results by custom_id — and pay 50% less than synchronous calls. https://guides-ai.com/guides/claude-api-prompt-caching/ https://guides-ai.com/guides/claude-api-prompt-caching/ Sun, 06 Sep 2026 00:00:00 GMT Building with the API Cache a long system prompt or document with cache_control, confirm hits in the usage fields, and know when the 1.25x write cost pays for itself. https://guides-ai.com/guides/claude-api-structured-output/ https://guides-ai.com/guides/claude-api-structured-output/ Sun, 06 Sep 2026 00:00:00 GMT Building with the API Constrain replies with output_config.format, or use messages.parse with Pydantic and Zod, so the Claude API returns JSON that always validates. https://guides-ai.com/guides/claude-api-tool-use/ https://guides-ai.com/guides/claude-api-tool-use/ Sun, 06 Sep 2026 00:00:00 GMT Building with the API Define a tool with a JSON schema, catch the tool_use block, run your function, and send back a tool_result — in a minimal Python loop. https://guides-ai.com/guides/claude-api-first-request/ https://guides-ai.com/guides/claude-api-first-request/ Sun, 06 Sep 2026 00:00:00 GMT Building with the API Get a key, set ANTHROPIC_API_KEY, and make a working Messages API call in curl, Python, and Node — then read the response properly. https://guides-ai.com/guides/gemini-cli-mcp-and-extensions/ https://guides-ai.com/guides/gemini-cli-mcp-and-extensions/ Sun, 06 Sep 2026 00:00:00 GMT Other coding agents Wire an MCP server into Gemini CLI's settings.json or add it with one command, check it with /mcp, and install a packaged extension. https://guides-ai.com/guides/windsurf-first-steps/ https://guides-ai.com/guides/windsurf-first-steps/ Sun, 06 Sep 2026 00:00:00 GMT Other coding agents Windsurf is now Devin Desktop. Install it, open a project, run a first agent task, and find where your rules live. Copy-paste. https://guides-ai.com/guides/github-copilot-cli-first-steps/ https://guides-ai.com/guides/github-copilot-cli-first-steps/ Sun, 06 Sep 2026 00:00:00 GMT Other coding agents Install GitHub Copilot CLI, log in, ask it for a command or a code change, and control what it's allowed to run. Copy-paste. https://guides-ai.com/guides/aider-first-steps/ https://guides-ai.com/guides/aider-first-steps/ Sun, 06 Sep 2026 00:00:00 GMT Other coding agents Install Aider, point it at Claude or GPT with an API key, make your first edit, and control its git auto-commits. Copy-paste. https://guides-ai.com/guides/codex-cli-first-steps/ https://guides-ai.com/guides/codex-cli-first-steps/ Sun, 06 Sep 2026 00:00:00 GMT Other coding agents Install Codex CLI with npm or Homebrew, sign in with ChatGPT, run your first task in a repo, and use /permissions to set what it can do. Copy-paste. https://guides-ai.com/guides/summarize-youtube-video-with-ai/ https://guides-ai.com/guides/summarize-youtube-video-with-ai/ Sun, 06 Sep 2026 00:00:00 GMT Everyday tasks Pull the transcript with yt-dlp --convert-subs srt, then hand the .srt file to Claude or ChatGPT with a prompt that gives you timestamps, not mush. https://guides-ai.com/guides/summarize-pdf-locally-with-ollama/ https://guides-ai.com/guides/summarize-pdf-locally-with-ollama/ Sun, 06 Sep 2026 00:00:00 GMT Everyday tasks Extract PDF text with pypdf, chunk it, summarize each chunk through the local Ollama API, and merge — about 30 lines, nothing uploaded. https://guides-ai.com/guides/chatgpt-analyze-csv-data/ https://guides-ai.com/guides/chatgpt-analyze-csv-data/ Sun, 06 Sep 2026 00:00:00 GMT Everyday tasks Upload a spreadsheet, get it cleaned, charted, and summarized — plus the limits worth knowing before you trust the numbers. https://guides-ai.com/guides/chatgpt-clean-spreadsheet-data/ https://guides-ai.com/guides/chatgpt-clean-spreadsheet-data/ Sun, 06 Sep 2026 00:00:00 GMT Everyday tasks Upload the CSV to ChatGPT data analysis, describe the mess once, and get back a cleaned file plus a repeatable formula or script. Limits and traps. https://guides-ai.com/guides/whisper-transcribe-audio-locally/ https://guides-ai.com/guides/whisper-transcribe-audio-locally/ Sun, 06 Sep 2026 00:00:00 GMT AI media Install OpenAI Whisper and ffmpeg, run whisper file.mp3 --model turbo, and get SRT and TXT subtitle files with timestamps out on your own machine. https://guides-ai.com/guides/upscale-images-locally/ https://guides-ai.com/guides/upscale-images-locally/ Sun, 06 Sep 2026 00:00:00 GMT AI media Enlarge photos and anime art 4x on your own machine with the standalone Real-ESRGAN binary — one command, no Python, and batch folders. https://guides-ai.com/guides/translate-subtitles-with-ai/ https://guides-ai.com/guides/translate-subtitles-with-ai/ Sun, 06 Sep 2026 00:00:00 GMT AI media Translate subtitles without breaking timestamps — a copy-paste Python script, the prompt that keeps line counts, and the checks that catch drift. https://guides-ai.com/guides/text-to-speech-locally/ https://guides-ai.com/guides/text-to-speech-locally/ Sun, 06 Sep 2026 00:00:00 GMT AI media Turn a text file into a WAV on your own machine — install Piper, download a voice, and choose between quality tiers and languages. https://guides-ai.com/guides/generate-short-ai-video-locally/ https://guides-ai.com/guides/generate-short-ai-video-locally/ Sun, 06 Sep 2026 00:00:00 GMT AI media The honest local text-to-video path: Wan 2.2 TI2V-5B in ComfyUI — three model files, real VRAM numbers, and a five-second clip. https://guides-ai.com/guides/generate-images-with-flux-locally/ https://guides-ai.com/guides/generate-images-with-flux-locally/ Sun, 06 Sep 2026 00:00:00 GMT AI media Run FLUX.1-schnell locally on your GPU with a short Python diffusers script — accept the Hugging Face license and offload for low VRAM. https://guides-ai.com/guides/comfyui-first-workflow/ https://guides-ai.com/guides/comfyui-first-workflow/ Sun, 06 Sep 2026 00:00:00 GMT AI media Install ComfyUI the reliable way, put a checkpoint in the right folder, load the default text-to-image graph, and generate an image. https://guides-ai.com/guides/ai-image-inpainting/ https://guides-ai.com/guides/ai-image-inpainting/ Sun, 06 Sep 2026 00:00:00 GMT AI media Inpainting masks a region and regenerates only that: Midjourney Vary (Region), Firefly Generative Fill, ChatGPT, or Stable Diffusion locally. https://guides-ai.com/guides/midjourney-prompts-that-work/ https://guides-ai.com/guides/midjourney-prompts-that-work/ Sun, 06 Sep 2026 00:00:00 GMT AI media Midjourney prompt structure: subject, style, details, then parameters last. --raw has replaced --style raw, and --ar still sets the aspect ratio. https://guides-ai.com/guides/remove-background-with-ai/ https://guides-ai.com/guides/remove-background-with-ai/ Sun, 06 Sep 2026 00:00:00 GMT AI media rembg cuts a subject to a transparent PNG from the command line — one file or a whole folder, offline, full resolution, no watermark and no upload. https://guides-ai.com/guides/fine-tuning-vs-rag-vs-prompting/ https://guides-ai.com/guides/fine-tuning-vs-rag-vs-prompting/ Sun, 06 Sep 2026 00:00:00 GMT Choosing tools A decision table plus rules of thumb — which one fixes your problem, and what each costs in money, latency and maintenance. https://guides-ai.com/guides/openai-vs-claude-api/ https://guides-ai.com/guides/openai-vs-claude-api/ Sun, 06 Sep 2026 00:00:00 GMT Choosing tools OpenAI and Claude API compared on price per million tokens, 1M-token context, tool use and long-context surcharges, plus how to decide with an eval. https://guides-ai.com/guides/claude-code-vs-cursor/ https://guides-ai.com/guides/claude-code-vs-cursor/ Sun, 06 Sep 2026 00:00:00 GMT Choosing tools Claude Code is a terminal agent; Cursor is an agent-first editor. Where each one wins, and why the Claude Code extension installs into Cursor too. https://guides-ai.com/guides/claude-vs-chatgpt-for-coding/ https://guides-ai.com/guides/claude-vs-chatgpt-for-coding/ Sun, 06 Sep 2026 00:00:00 GMT Choosing tools A practical split for real coding work, plus the deciding fact most comparisons skip: Claude Code needs a paid plan, ChatGPT answers on free. https://guides-ai.com/guides/pick-an-ai-model/ https://guides-ai.com/guides/pick-an-ai-model/ Sun, 06 Sep 2026 00:00:00 GMT Choosing tools Pick an AI model by job: coding, images, very long inputs, or private local inference. Current tiers, with the context-window myth corrected. https://guides-ai.com/guides/prompt-injection-defense/ https://guides-ai.com/guides/prompt-injection-defense/ Sun, 06 Sep 2026 00:00:00 GMT Prompting Six defenses that actually reduce blast radius — privilege separation, allowlists, fenced tool results, approval gates, output filtering, and tests. https://guides-ai.com/guides/llm-as-judge-evals/ https://guides-ai.com/guides/llm-as-judge-evals/ Sun, 06 Sep 2026 00:00:00 GMT Prompting Grade model outputs with a judge model: a copy-paste rubric prompt, a structured verdict, a Python scoring loop, and the biases that fake good scores. https://guides-ai.com/guides/evals-with-promptfoo/ https://guides-ai.com/guides/evals-with-promptfoo/ Sun, 06 Sep 2026 00:00:00 GMT Prompting Install promptfoo, write a config with two prompts, three test cases and real assertions, run it, and read the pass/fail grid. https://guides-ai.com/guides/rag-explained-simply/ https://guides-ai.com/guides/rag-explained-simply/ Sun, 06 Sep 2026 00:00:00 GMT Prompting RAG retrieves relevant chunks, then generates. With 1M-token context windows and hosted file_search tools, here is when it beats pasting the file. https://guides-ai.com/guides/prompt-chaining/ https://guides-ai.com/guides/prompt-chaining/ Sun, 06 Sep 2026 00:00:00 GMT Prompting Prompt chaining splits a task into separate API calls you can inspect (draft, review, refine), and when a modern model handles it in one call. https://guides-ai.com/guides/reduce-ai-hallucinations/ https://guides-ai.com/guides/reduce-ai-hallucinations/ Sun, 06 Sep 2026 00:00:00 GMT Prompting Ground answers in pasted source text, allow "not stated", demand a quote per claim, and lower temperature: the habits that cut invented facts. https://guides-ai.com/guides/write-a-system-prompt/ https://guides-ai.com/guides/write-a-system-prompt/ Sun, 06 Sep 2026 00:00:00 GMT Prompting System prompt structure: role, rules with reasons, exact output format, tagged examples. Set it in the API system parameter, then test by breaking it. https://guides-ai.com/guides/write-better-ai-prompts/ https://guides-ai.com/guides/write-better-ai-prompts/ Sun, 06 Sep 2026 00:00:00 GMT Prompting A prompt framework that still holds: role, task, context, format — plus the long-input ordering rule Anthropic measures at up to 30% better answers. https://guides-ai.com/guides/vllm-serve-openai-compatible/ https://guides-ai.com/guides/vllm-serve-openai-compatible/ Sun, 06 Sep 2026 00:00:00 GMT Local LLMs Install vLLM, start a server with vllm serve on localhost:8000, and call it with the OpenAI Python SDK. Needs a Linux box with an NVIDIA GPU. https://guides-ai.com/guides/run-local-llm-ollama-macos-linux/ https://guides-ai.com/guides/run-local-llm-ollama-macos-linux/ Sun, 06 Sep 2026 00:00:00 GMT Local LLMs Install Ollama with one command, pull gemma3:4b, chat offline in the terminal, and keep the daemon running as a background service on port 11434. https://guides-ai.com/guides/open-webui-with-ollama/ https://guides-ai.com/guides/open-webui-with-ollama/ Sun, 06 Sep 2026 00:00:00 GMT Local LLMs Give your local Ollama models a ChatGPT-style web interface with one Docker command — first login, model picker, and fixes. https://guides-ai.com/guides/ollama-in-docker-with-gpu/ https://guides-ai.com/guides/ollama-in-docker-with-gpu/ Sun, 06 Sep 2026 00:00:00 GMT Local LLMs NVIDIA Container Toolkit setup, the official docker run command, pulling a model, keeping models in a volume, and AMD or CPU fallbacks. https://guides-ai.com/guides/local-llm-ram-vram-requirements/ https://guides-ai.com/guides/local-llm-ram-vram-requirements/ Sun, 06 Sep 2026 00:00:00 GMT Local LLMs Real GGUF file sizes at Q4/Q8 for 1B to 70B models, the rule of thumb behind them, and what fits in 8, 16, 24 or 64 GB. Pick a model that runs. https://guides-ai.com/guides/llama-cpp-quickstart/ https://guides-ai.com/guides/llama-cpp-quickstart/ Sun, 06 Sep 2026 00:00:00 GMT Local LLMs Install llama.cpp, pull a GGUF from Hugging Face with llama cli -hf, chat in the terminal, then serve an OpenAI-compatible API on localhost:9931. https://guides-ai.com/guides/run-llm-lm-studio/ https://guides-ai.com/guides/run-llm-lm-studio/ Sun, 06 Sep 2026 00:00:00 GMT Local LLMs LM Studio downloads and runs GGUF models in a desktop app, then serves them at http://localhost:1234/v1 for any OpenAI-compatible client. No terminal. https://guides-ai.com/guides/choose-llm-quantization/ https://guides-ai.com/guides/choose-llm-quantization/ Sun, 06 Sep 2026 00:00:00 GMT Local LLMs Q4_K_M is the default pick for local LLMs. Real bits-per-weight for each GGUF level, why Q8_0 is a legacy format, and how to match one to your RAM. https://guides-ai.com/guides/call-ollama-api/ https://guides-ai.com/guides/call-ollama-api/ Sun, 06 Sep 2026 00:00:00 GMT Local LLMs Ollama serves a local API on port 11434. Call /api/chat with curl or Python, or point any OpenAI client at http://localhost:11434/v1/ instead. https://guides-ai.com/guides/ollama-custom-model-modelfile/ https://guides-ai.com/guides/ollama-custom-model-modelfile/ Sun, 06 Sep 2026 00:00:00 GMT Local LLMs An Ollama Modelfile bakes FROM, SYSTEM and PARAMETER into a named local model with ollama create, so behaviour travels with the model, not scripts. https://guides-ai.com/guides/run-local-llm-ollama-windows/ https://guides-ai.com/guides/run-local-llm-ollama-windows/ Sun, 06 Sep 2026 00:00:00 GMT Local LLMs Install Ollama on Windows 10 22H2+, run your first model with ollama run, check it landed on the GPU, and move the model store off your C: drive. https://guides-ai.com/guides/cursor-rules-file/ https://guides-ai.com/guides/cursor-rules-file/ Sun, 06 Sep 2026 00:00:00 GMT Cursor Cursor project rules are .mdc files with frontmatter. Learn the four rule types, which frontmatter produces each, and copy a working example. https://guides-ai.com/guides/cursor-mcp-servers/ https://guides-ai.com/guides/cursor-mcp-servers/ Sun, 06 Sep 2026 00:00:00 GMT Cursor Configure a local or remote MCP server in Cursor, global or per project, keep the API key out of git, and verify it with a real tool call. https://guides-ai.com/guides/cursor-first-steps/ https://guides-ai.com/guides/cursor-first-steps/ Sun, 06 Sep 2026 00:00:00 GMT Cursor Cursor in ten minutes: Tab completions, Cmd/Ctrl K inline edits, the Agent sidepane on Cmd/Ctrl I, and how to review or undo what Agent wrote. https://guides-ai.com/guides/excel-formulas-with-chatgpt/ https://guides-ai.com/guides/excel-formulas-with-chatgpt/ Sun, 06 Sep 2026 00:00:00 GMT ChatGPT Describe the sheet so ChatGPT can answer, ask for the formula plus a breakdown, verify it on real rows, and fix the four things that go wrong. https://guides-ai.com/guides/chatgpt-voice-mode/ https://guides-ai.com/guides/chatgpt-voice-mode/ Sun, 06 Sep 2026 00:00:00 GMT ChatGPT ChatGPT voice now runs inside the chat, not a separate blue-orb screen. Tap the Voice icon on web, hold the mic on mobile, and when to skip it. https://guides-ai.com/guides/chatgpt-projects/ https://guides-ai.com/guides/chatgpt-projects/ Sun, 06 Sep 2026 00:00:00 GMT ChatGPT ChatGPT Projects group chats around shared files and instructions. Free plans get 5 files per project, Plus 25, Pro and Business 40; sharing is free. https://guides-ai.com/guides/build-a-custom-gpt/ https://guides-ai.com/guides/build-a-custom-gpt/ Sun, 06 Sep 2026 00:00:00 GMT ChatGPT Custom GPT creation now needs a Business, Enterprise or Edu workspace. Use the Configure tab for instructions, up to 20 knowledge files, and actions. https://guides-ai.com/guides/chatgpt-custom-instructions/ https://guides-ai.com/guides/chatgpt-custom-instructions/ Sun, 06 Sep 2026 00:00:00 GMT ChatGPT Custom instructions moved to Settings then Personalization and are now one field, not two boxes. They apply immediately to all chats, on every plan. https://guides-ai.com/guides/chatgpt-summarize-pdf/ https://guides-ai.com/guides/chatgpt-summarize-pdf/ Sun, 06 Sep 2026 00:00:00 GMT ChatGPT Attach the PDF in ChatGPT, ask for a shape instead of a summary, then drill in. The 512 MB and 2M-token caps, and what to do with a scanned file. https://guides-ai.com/guides/claude-artifacts/ https://guides-ai.com/guides/claude-artifacts/ Sun, 06 Sep 2026 00:00:00 GMT Claude Artifacts open code, docs and diagrams in a side panel. Turn on Code execution and file creation in Settings, iterate in place, then publish a link. https://guides-ai.com/guides/claude-projects-getting-started/ https://guides-ai.com/guides/claude-projects-getting-started/ Sun, 06 Sep 2026 00:00:00 GMT Claude Claude Projects keep files and instructions across chats. Free accounts get up to 5 projects; paid plans add RAG that expands knowledge up to 10x. https://guides-ai.com/guides/claude-code-remote-mcp-servers/ https://guides-ai.com/guides/claude-code-remote-mcp-servers/ Sun, 06 Sep 2026 00:00:00 GMT MCP Add a hosted MCP server with claude mcp add --transport http, authenticate with OAuth or a header, and pick the right scope for your team. https://guides-ai.com/guides/claude-code-mcp-troubleshooting/ https://guides-ai.com/guides/claude-code-mcp-troubleshooting/ Sun, 06 Sep 2026 00:00:00 GMT MCP claude mcp list says Failed to connect or Pending approval? Five checks find the cause: scope, approval, the -- separator, env vars and timeouts. https://guides-ai.com/guides/build-mcp-server-typescript/ https://guides-ai.com/guides/build-mcp-server-typescript/ Sun, 06 Sep 2026 00:00:00 GMT MCP Write a one-tool MCP server with the official TypeScript SDK, serve it over stdio, and call it from Claude Code. Copy-paste. https://guides-ai.com/guides/build-mcp-server-python/ https://guides-ai.com/guides/build-mcp-server-python/ Sun, 06 Sep 2026 00:00:00 GMT MCP Write a one-tool MCP server named word_count with the official Python SDK, run it over stdio, and call it from Claude Code with claude mcp add. https://guides-ai.com/guides/mcp-claude-code-vs-desktop/ https://guides-ai.com/guides/mcp-claude-code-vs-desktop/ Sun, 06 Sep 2026 00:00:00 GMT MCP claude mcp add registers a server from the terminal; Claude Desktop edits a JSON config from Settings. Same protocol, two setup flows, a scope trick. https://guides-ai.com/guides/best-mcp-servers-to-start/ https://guides-ai.com/guides/best-mcp-servers-to-start/ Sun, 06 Sep 2026 00:00:00 GMT MCP Seven MCP reference servers are still maintained — filesystem, fetch, git, memory, time. GitHub, Postgres, Slack and Puppeteer were archived. https://guides-ai.com/guides/connect-claude-code-to-github/ https://guides-ai.com/guides/connect-claude-code-to-github/ Sun, 06 Sep 2026 00:00:00 GMT MCP Add GitHub's hosted MCP server at api.githubcopilot.com with a bearer token — the old @modelcontextprotocol/server-github package has been archived. https://guides-ai.com/guides/install-mcp-server-claude-code/ https://guides-ai.com/guides/install-mcp-server-claude-code/ Sun, 06 Sep 2026 00:00:00 GMT MCP Add an MCP server with claude mcp add: -- for local commands, --transport http for hosted ones, --scope to choose who gets it, then /mcp to confirm. https://guides-ai.com/guides/claude-code-parallel-sessions-worktrees/ https://guides-ai.com/guides/claude-code-parallel-sessions-worktrees/ Sun, 06 Sep 2026 00:00:00 GMT Workflows Start a second Claude Code session in its own git worktree with `claude --worktree`, keep .env files in it, and clean up when you're done. Copy-paste. https://guides-ai.com/guides/claude-code-headless-ci/ https://guides-ai.com/guides/claude-code-headless-ci/ Sun, 06 Sep 2026 00:00:00 GMT Workflows Run Claude Code non-interactively with claude -p, get JSON back, pre-approve tools, and wire it into a CI job. Copy-paste. https://guides-ai.com/guides/claude-code-github-actions/ https://guides-ai.com/guides/claude-code-github-actions/ Sun, 06 Sep 2026 00:00:00 GMT Workflows Install the Claude GitHub App, add one secret, and drop in a workflow so @claude answers in your issues and PRs. Copy-paste. https://guides-ai.com/guides/claude-code-review-a-pr/ https://guides-ai.com/guides/claude-code-review-a-pr/ Sun, 06 Sep 2026 00:00:00 GMT Workflows Run /code-review (alias /review) on a diff, or check out a PR with gh. Ask for correctness over style, then have Claude apply only fixes you accept. https://guides-ai.com/guides/ai-coding-agent-context/ https://guides-ai.com/guides/ai-coding-agent-context/ Sun, 06 Sep 2026 00:00:00 GMT Workflows CLAUDE.md, AGENTS.md and .cursor/rules: four habits that fix most bad AI code — a rules file, @file references, one example, a clean context. https://guides-ai.com/guides/claude-code-whole-codebase-safely/ https://guides-ai.com/guides/claude-code-whole-codebase-safely/ Sun, 06 Sep 2026 00:00:00 GMT Workflows Branch, plan, deny the destructive commands, review in small chunks. Auto mode now starts on by default, so don't assume Claude will stop and ask. https://guides-ai.com/guides/claude-code-skills-and-plugins/ https://guides-ai.com/guides/claude-code-skills-and-plugins/ Sun, 06 Sep 2026 00:00:00 GMT Claude Code commands Skills are folders with a SKILL.md. Plugins bundle skills, agents and hooks for sharing. Install one from a marketplace, then write your own. https://guides-ai.com/guides/claude-code-settings-json/ https://guides-ai.com/guides/claude-code-settings-json/ Sun, 06 Sep 2026 00:00:00 GMT Claude Code commands The four settings files Claude Code reads, which one wins when they disagree, and the handful of keys worth setting on day one. https://guides-ai.com/guides/claude-code-permissions/ https://guides-ai.com/guides/claude-code-permissions/ Sun, 06 Sep 2026 00:00:00 GMT Claude Code commands Claude Code now starts in auto mode on Pro, Max and Team plans. Shift+Tab to switch, and write allow/deny rules that actually match the command. https://guides-ai.com/guides/claude-code-track-costs/ https://guides-ai.com/guides/claude-code-track-costs/ Sun, 06 Sep 2026 00:00:00 GMT Claude Code commands Run /usage to see session tokens, cost and plan limits — /cost is now just an alias. Then cut waste with /clear, subagents and the right model. https://guides-ai.com/guides/claude-code-manage-context/ https://guides-ai.com/guides/claude-code-manage-context/ Sun, 06 Sep 2026 00:00:00 GMT Claude Code commands Use /clear between tasks, /compact within one, /context to see what fills the window, and claude -c to resume. Keeps long sessions fast and cheap. https://guides-ai.com/guides/claude-code-subagents/ https://guides-ai.com/guides/claude-code-subagents/ Sun, 06 Sep 2026 00:00:00 GMT Claude Code commands A subagent is a separate Claude with its own context window. Write one as a Markdown file in .claude/agents/ — note /agents is no longer a wizard. https://guides-ai.com/guides/claude-code-hooks/ https://guides-ai.com/guides/claude-code-hooks/ Sun, 06 Sep 2026 00:00:00 GMT Claude Code commands Hooks run a shell command on Claude Code events. Note $CLAUDE_FILE_PATHS no longer exists — read the file path from the JSON on stdin instead. https://guides-ai.com/guides/create-claude-code-slash-command/ https://guides-ai.com/guides/create-claude-code-slash-command/ Sun, 06 Sep 2026 00:00:00 GMT Claude Code commands Drop a Markdown file in .claude/commands/ and the filename becomes the command. $0 is the first positional argument, and skills are now preferred. https://guides-ai.com/guides/create-claude-md-project-memory/ https://guides-ai.com/guides/create-claude-md-project-memory/ Sun, 06 Sep 2026 00:00:00 GMT Claude Code commands Run /init, keep CLAUDE.md under 200 lines, and confirm it loaded with /context. Plus .claude/rules for path-scoped instructions and @path imports. https://guides-ai.com/guides/gemini-cli-first-steps/ https://guides-ai.com/guides/gemini-cli-first-steps/ Sun, 06 Sep 2026 00:00:00 GMT First steps Install Gemini CLI with npm, npx or Homebrew, sign in with Google for 60 requests a minute free, and run your first prompt inside a project. https://guides-ai.com/guides/claude-code-terminal-shortcuts/ https://guides-ai.com/guides/claude-code-terminal-shortcuts/ Sun, 06 Sep 2026 00:00:00 GMT First steps The keys that make Claude Code fast: @ for files, ! for shell, Esc to interrupt, Esc Esc to rewind, Shift+Tab for modes, Ctrl+B to background. https://guides-ai.com/guides/claude-code-plan-mode/ https://guides-ai.com/guides/claude-code-plan-mode/ Sun, 06 Sep 2026 00:00:00 GMT First steps Plan mode makes Claude Code research and propose before editing. Enter it with Shift+Tab or /plan, review the plan, then approve — or keep planning. https://guides-ai.com/guides/first-claude-code-session/ https://guides-ai.com/guides/first-claude-code-session/ Sun, 06 Sep 2026 00:00:00 GMT First steps Run claude inside your project, give it one clear task, and check the permission mode first — auto mode may edit files without asking on paid plans. https://guides-ai.com/guides/update-claude-code/ https://guides-ai.com/guides/update-claude-code/ Sun, 06 Sep 2026 00:00:00 GMT Install & set up claude update applies the newest Claude Code now, claude doctor says why one stalled, and package-manager installs need upgrading by hand. Copy-paste. https://guides-ai.com/guides/claude-code-vscode-extension/ https://guides-ai.com/guides/claude-code-vscode-extension/ Sun, 06 Sep 2026 00:00:00 GMT Install & set up Install the Claude Code extension from the VS Code Marketplace for a native panel with inline diffs and rewind — it no longer auto-installs itself. https://guides-ai.com/guides/fix-claude-command-not-found/ https://guides-ai.com/guides/fix-claude-command-not-found/ Sun, 06 Sep 2026 00:00:00 GMT Install & set up claude: command not found means the install directory is not on your PATH. Four fixes: new terminal, PATH entry, duplicate install, npm repair. https://guides-ai.com/guides/install-claude-code-macos-linux/ https://guides-ai.com/guides/install-claude-code-macos-linux/ Sun, 06 Sep 2026 00:00:00 GMT Install & set up Install Claude Code with the curl script or Homebrew in under a minute. The npm route now needs Node.js 22+, and a paid Claude plan is required. https://guides-ai.com/guides/install-claude-code-windows/ https://guides-ai.com/guides/install-claude-code-windows/ Sun, 06 Sep 2026 00:00:00 GMT Install & set up irm https://claude.ai/install.ps1 | iex installs Claude Code on Windows 10 1809+. WinGet and npm alternatives, Git Bash setup, and the first login.