Open AI Stack
A curated directory of 100% free, open-source, and generous freemium AI tools alongside the cutting-edge silicon built to run them locally or on the cloud with affordability.
TL;DevTech // Open Source & Free AI Directory
- 1 What do you want to create or manage?
- 2 The tasks it takes — and the tools for each
Video
Short-form or long-form video: script it, generate it, edit it, dub it, ship it.
-
1
Script & storyboard
Turn a rough idea into a shot list and a script before you render a single frame.
-
LLM Models
A curated guide to the top large language models — comparing capabilities, context windows, and the best use cases for each.
-
ViMax
An open-source framework for agentic video generation, acting as a director, screenwriter, and producer.
-
reels-af
An open-source AI agent that automates creating short-form video content by generating scripts, sourcing clips, and editing Reels/Shorts/TikToks automatically.
-
NotebookLM
Google's AI research notebook that grounds answers in your sources and generates audio overviews — free to use.
-
LLM Models
-
2
Generate the footage
Text-to-video and image-to-video models, plus GPU studios you run yourself.
-
Wan2.1
Alibaba's open-source video generation model — produces high-quality short clips from text or image prompts and runs on consumer GPUs.
-
ViMax
An open-source framework for agentic video generation, acting as a director, screenwriter, and producer.
-
SceneWorks
A desktop-native AI image and video generation studio that runs on your own GPU — MLX on macOS, candle/CUDA on Windows. Features Image Studio, Video Studio, Character Studio, Document Studio, and Training Studio with 45+ image models and 9 video models.
-
ComfyUI
A highly powerful, modular, and node/graph-based GUI pipeline for Stable Diffusion, enabling custom AI image and video generation workflows.
-
Remotion
Create videos programmatically using React.
-
Wan2.1
-
3
Edit & assemble
Cut, stitch, and arrange raw clips into a finished timeline.
-
video-use
100% open-source video editing with an AI coding agent — drop raw footage in a folder, chat, and get final.mp4 back with filler cuts, color grading, subtitles, and animation overlays.
-
OpenMontage
An open-source tool for creating video montages and compilations automatically — stitch clips, add transitions, and generate highlight reels with AI assistance.
-
Vynaro
Desktop AI video narration editor: a 7-step pipeline turns film and drama clips into narrated, subtitled vertical videos with CapCut draft export.
-
Remotion
Create videos programmatically using React.
-
video-use
-
4
Voiceover & dubbing
Narration, voice cloning, and second-language audio tracks.
-
ElevenLabs
High-quality AI text-to-speech and voice cloning in many languages — free tier with monthly characters.
-
VoxCPM
An open-source text-to-speech and speech-to-text model that delivers high-quality speech synthesis and recognition in a unified framework.
-
pyVideoTrans
An open-source video translation and dubbing tool — automatically translates speech, subtitles, and audio from one language to another.
-
ElevenLabs
-
5
Subtitles & translation
Transcribe the audio, burn in subtitles, translate for other markets.
-
Whisper
OpenAI's open-source speech recognition model that transcribes and translates audio in 99 languages with high accuracy — runs locally on CPU or GPU.
-
pyVideoTrans
An open-source video translation and dubbing tool — automatically translates speech, subtitles, and audio from one language to another.
-
Vynaro
Desktop AI video narration editor: a 7-step pipeline turns film and drama clips into narrated, subtitled vertical videos with CapCut draft export.
-
Whisper
-
6
Automate & publish
Put the whole pipeline on rails so each new video is one trigger away.
-
reels-af
An open-source AI agent that automates creating short-form video content by generating scripts, sourcing clips, and editing Reels/Shorts/TikToks automatically.
-
n8n
A fair-code, self-hostable workflow automation platform with native AI nodes — build agentic workflows connecting 400+ apps and any LLM.
-
Activepieces
An open-source, self-hostable automation platform with AI agents and MCP support — a no-code alternative to Zapier you can run yourself.
-
OpenClaw
An open-source, autonomous AI agent that runs locally to automate tasks, manage files, and act as a proactive personal assistant.
-
reels-af
Image
Generate, refine, and batch-produce still images on your own hardware or a free API.
-
1
Check what your machine can run
Match models to your GPU and VRAM before downloading 20GB of weights.
-
CanIRun.ai
A browser-based tool that automatically detects your hardware and estimates which AI models can run locally on your system.
-
CanIRun.ai
-
2
Generate images
Diffusion front-ends and desktop studios for text-to-image and image-to-image.
-
ComfyUI
A highly powerful, modular, and node/graph-based GUI pipeline for Stable Diffusion, enabling custom AI image and video generation workflows.
-
AUTOMATIC1111
The most widely used open-source web UI for Stable Diffusion — supports hundreds of models, ControlNet, inpainting, upscaling, and a massive extension ecosystem.
-
SceneWorks
A desktop-native AI image and video generation studio that runs on your own GPU — MLX on macOS, candle/CUDA on Windows. Features Image Studio, Video Studio, Character Studio, Document Studio, and Training Studio with 45+ image models and 9 video models.
-
LocalAI
A free, open-source drop-in replacement for the OpenAI API that runs locally — supports text, image, audio, and embedding models with no cloud dependency.
-
ComfyUI
-
3
Build a repeatable pipeline
Node graphs and workflows so the same look is reproducible across a whole set.
-
ComfyUI
A highly powerful, modular, and node/graph-based GUI pipeline for Stable Diffusion, enabling custom AI image and video generation workflows.
-
AUTOMATIC1111
The most widely used open-source web UI for Stable Diffusion — supports hundreds of models, ControlNet, inpainting, upscaling, and a massive extension ecosystem.
-
ComfyUI
-
4
Write better prompts
Use an LLM to expand, vary, and critique prompts instead of guessing.
-
LLM Models
A curated guide to the top large language models — comparing capabilities, context windows, and the best use cases for each.
-
Open WebUI
A self-hosted, feature-rich ChatGPT-style interface for running LLMs locally via Ollama or OpenAI-compatible APIs — with RAG, tools, and user management built in.
-
Ollama
Run large language models locally with a single command. Supports Llama, Mistral, Gemma, and dozens more models on Mac, Windows, and Linux.
-
LLM Models
-
5
Batch & automate
Fire generations from a workflow, a webhook, or an agent on your desktop.
-
n8n
A fair-code, self-hostable workflow automation platform with native AI nodes — build agentic workflows connecting 400+ apps and any LLM.
-
Activepieces
An open-source, self-hostable automation platform with AI agents and MCP support — a no-code alternative to Zapier you can run yourself.
-
OpenClaw
An open-source, autonomous AI agent that runs locally to automate tasks, manage files, and act as a proactive personal assistant.
-
n8n
2D Graphics & Sprites
Game-ready 2D art: sprites, tilesets, layered maps, and UI assets.
-
1
Sprites & character art
Generate consistent, engine-ready sprite sheets from a natural-language brief.
-
Agent Sprite Forge
Codex skills for game-ready 2D sprites, layered maps, and engine-ready prototypes — ask in natural language, Codex plans the asset pipeline, renders with built-in image generation, then local processors clean, split, validate, and export assets for Godot, Unity, or raw 2D game workflows.
-
ComfyUI
A highly powerful, modular, and node/graph-based GUI pipeline for Stable Diffusion, enabling custom AI image and video generation workflows.
-
AUTOMATIC1111
The most widely used open-source web UI for Stable Diffusion — supports hundreds of models, ControlNet, inpainting, upscaling, and a massive extension ecosystem.
-
Agent Sprite Forge
-
2
Tilesets, maps & backgrounds
Layered environment art you can drop straight into a scene.
-
Agent Sprite Forge
Codex skills for game-ready 2D sprites, layered maps, and engine-ready prototypes — ask in natural language, Codex plans the asset pipeline, renders with built-in image generation, then local processors clean, split, validate, and export assets for Godot, Unity, or raw 2D game workflows.
-
SceneWorks
A desktop-native AI image and video generation studio that runs on your own GPU — MLX on macOS, candle/CUDA on Windows. Features Image Studio, Video Studio, Character Studio, Document Studio, and Training Studio with 45+ image models and 9 video models.
-
ComfyUI
A highly powerful, modular, and node/graph-based GUI pipeline for Stable Diffusion, enabling custom AI image and video generation workflows.
-
Agent Sprite Forge
-
3
Animate the art
Motion graphics and frame animation for sprites, effects, and UI.
-
Remotion
Create videos programmatically using React.
-
ComfyUI
A highly powerful, modular, and node/graph-based GUI pipeline for Stable Diffusion, enabling custom AI image and video generation workflows.
-
Wan2.1
Alibaba's open-source video generation model — produces high-quality short clips from text or image prompts and runs on consumer GPUs.
-
Remotion
-
4
Wire assets into the engine
Let a coding agent generate the loader, atlas, and prototype scene.
-
Agent Sprite Forge
Codex skills for game-ready 2D sprites, layered maps, and engine-ready prototypes — ask in natural language, Codex plans the asset pipeline, renders with built-in image generation, then local processors clean, split, validate, and export assets for Godot, Unity, or raw 2D game workflows.
-
OpenCode
An open source agent that helps you write code in your terminal, IDE, or desktop.
-
Cline
An open-source autonomous coding agent for VS Code — plans tasks, edits files, and runs terminal commands with your approval, using any LLM you connect.
-
Roo Code
An open-source AI coding agent for VS Code — a whole dev team of AI agents that read, write, and run code in your editor using your own API keys.
-
Agent Sprite Forge
3D Model
Model, rig, animate, and render 3D assets — from CAD parts to mocap-driven characters.
-
1
Model the object
Describe a part in plain language and get parametric CAD geometry back.
-
CADAM
An open-source, AI-powered text-to-CAD application that runs entirely in the browser using WebAssembly to generate parametric 3D models from prompts and images.
-
CADAM
-
2
Capture motion
Turn ordinary video into full-body motion data without a mocap suit.
-
FreeMoCap
Research-grade, free open-source markerless motion capture — track full-body movement from regular video with no special hardware required.
-
FreeMoCap
-
3
Generate animation
Diffusion-based kinematic motion you can steer and retarget.
-
Kimodo
Kimodo is a kinematic motion diffusion model trained on large-scale optical mocap data. It is controlled through text and constraints to generate high-quality 3D human and robot motions.
-
Kimodo
-
4
Render & compose scenes
Local GPU studios for turning assets into finished frames and clips.
-
SceneWorks
A desktop-native AI image and video generation studio that runs on your own GPU — MLX on macOS, candle/CUDA on Windows. Features Image Studio, Video Studio, Character Studio, Document Studio, and Training Studio with 45+ image models and 9 video models.
-
ComfyUI
A highly powerful, modular, and node/graph-based GUI pipeline for Stable Diffusion, enabling custom AI image and video generation workflows.
-
Wan2.1
Alibaba's open-source video generation model — produces high-quality short clips from text or image prompts and runs on consumer GPUs.
-
SceneWorks
-
5
Script the pipeline
Automate exports, conversions, and engine imports with a coding agent.
-
OpenCode
An open source agent that helps you write code in your terminal, IDE, or desktop.
-
Cline
An open-source autonomous coding agent for VS Code — plans tasks, edits files, and runs terminal commands with your approval, using any LLM you connect.
-
Goose
An open-source, on-machine AI agent from Block — automates engineering tasks end to end and works with any LLM provider.
-
Pi Coding Agent
A minimalist open-source AI coding agent with just four tools (read, write, edit, bash), a sub-1000-token system prompt, and a self-modifying extension system.
-
OpenCode
Game
Everything a game needs: art, models, animation, code, audio, and smart NPCs.
-
1
Concept & design doc
Pin down the loop, systems, and scope before you build anything.
-
LLM Models
A curated guide to the top large language models — comparing capabilities, context windows, and the best use cases for each.
-
NotebookLM
Google's AI research notebook that grounds answers in your sources and generates audio overviews — free to use.
-
DeerFlow
An open-source SuperAgent framework by ByteDance designed to orchestrate sub-agents, memory, sandboxed code execution, and extensible skills for long-horizon tasks.
-
LLM Models
-
2
2D art & sprites
Characters, tilesets, and UI art generated to a consistent style.
-
Agent Sprite Forge
Codex skills for game-ready 2D sprites, layered maps, and engine-ready prototypes — ask in natural language, Codex plans the asset pipeline, renders with built-in image generation, then local processors clean, split, validate, and export assets for Godot, Unity, or raw 2D game workflows.
-
ComfyUI
A highly powerful, modular, and node/graph-based GUI pipeline for Stable Diffusion, enabling custom AI image and video generation workflows.
-
AUTOMATIC1111
The most widely used open-source web UI for Stable Diffusion — supports hundreds of models, ControlNet, inpainting, upscaling, and a massive extension ecosystem.
-
Agent Sprite Forge
-
3
3D models & environments
Geometry and scenes for anything that isn't flat.
-
CADAM
An open-source, AI-powered text-to-CAD application that runs entirely in the browser using WebAssembly to generate parametric 3D models from prompts and images.
-
SceneWorks
A desktop-native AI image and video generation studio that runs on your own GPU — MLX on macOS, candle/CUDA on Windows. Features Image Studio, Video Studio, Character Studio, Document Studio, and Training Studio with 45+ image models and 9 video models.
-
CADAM
-
4
Animation & motion capture
Give characters believable movement without a studio.
-
Kimodo
Kimodo is a kinematic motion diffusion model trained on large-scale optical mocap data. It is controlled through text and constraints to generate high-quality 3D human and robot motions.
-
FreeMoCap
Research-grade, free open-source markerless motion capture — track full-body movement from regular video with no special hardware required.
-
Kimodo
-
5
Write the code
AI coding agents and editors that build systems, not just autocomplete lines.
-
OpenCode
An open source agent that helps you write code in your terminal, IDE, or desktop.
-
Cline
An open-source autonomous coding agent for VS Code — plans tasks, edits files, and runs terminal commands with your approval, using any LLM you connect.
-
Roo Code
An open-source AI coding agent for VS Code — a whole dev team of AI agents that read, write, and run code in your editor using your own API keys.
-
Cursor
An AI-first code editor (VS Code fork) with deep codebase awareness, multi-file edits, and agent mode — free hobby tier plus paid Pro.
-
Zed
An open-source, high-performance code editor written in Rust with built-in AI assistant and real-time multiplayer editing.
-
Forge Code
An open-source AI coding agent for the terminal — access 300+ models via OpenRouter with a free daily token tier.
-
Pi Coding Agent
A minimalist open-source AI coding agent with just four tools (read, write, edit, bash), a sub-1000-token system prompt, and a self-modifying extension system.
-
Free Claude Code
A free, open-source Claude Code-compatible agent runner that works without API keys or subscriptions — run Claude Code-style agents directly from your terminal with no costs or limits.
-
OpenCode
-
6
Sound & voice acting
Dialogue, barks, and narration — synthesized and cloned.
-
ElevenLabs
High-quality AI text-to-speech and voice cloning in many languages — free tier with monthly characters.
-
VoxCPM
An open-source text-to-speech and speech-to-text model that delivers high-quality speech synthesis and recognition in a unified framework.
-
Whisper
OpenAI's open-source speech recognition model that transcribes and translates audio in 99 languages with high accuracy — runs locally on CPU or GPU.
-
ElevenLabs
-
7
AI memory & agent skills
NPCs and copilots that remember, plus reusable skills for your dev agents.
-
MemoryPalace
An open-source long-term memory layer for LLMs — give your agents persistent recall across sessions for more coherent conversations.
-
Antigravity Awesome Skills
A massive library of 1,898+ reusable AI agent skills for Claude Code, Cursor, Codex CLI, and Gemini CLI — installable skill packs for coding, DevOps, data science, and more.
-
Ollama
Run large language models locally with a single command. Supports Llama, Mistral, Gemma, and dozens more models on Mac, Windows, and Linux.
-
llama.cpp
The foundational open-source inference engine for running quantized LLMs on CPU and GPU — the backbone powering Ollama, LM Studio, and most local runners.
-
MemoryPalace
-
8
Trailer & marketing clips
Turn gameplay footage into something you can post.
-
ViMax
An open-source framework for agentic video generation, acting as a director, screenwriter, and producer.
-
video-use
100% open-source video editing with an AI coding agent — drop raw footage in a folder, chat, and get final.mp4 back with filler cuts, color grading, subtitles, and animation overlays.
-
Wan2.1
Alibaba's open-source video generation model — produces high-quality short clips from text or image prompts and runs on consumer GPUs.
-
OpenMontage
An open-source tool for creating video montages and compilations automatically — stitch clips, add transitions, and generate highlight reels with AI assistance.
-
ViMax
App
Ship a real application: plan it, code it, give it AI features, memory, and tests.
-
1
Plan the build
Break the idea into architecture and a task list you can hand to an agent.
-
LLM Models
A curated guide to the top large language models — comparing capabilities, context windows, and the best use cases for each.
-
DeerFlow
An open-source SuperAgent framework by ByteDance designed to orchestrate sub-agents, memory, sandboxed code execution, and extensible skills for long-horizon tasks.
-
NotebookLM
Google's AI research notebook that grounds answers in your sources and generates audio overviews — free to use.
-
LLM Models
-
2
Write the code
Autonomous coding agents, AI-first editors, and terminal agents.
-
Cline
An open-source autonomous coding agent for VS Code — plans tasks, edits files, and runs terminal commands with your approval, using any LLM you connect.
-
Roo Code
An open-source AI coding agent for VS Code — a whole dev team of AI agents that read, write, and run code in your editor using your own API keys.
-
OpenCode
An open source agent that helps you write code in your terminal, IDE, or desktop.
-
Goose
An open-source, on-machine AI agent from Block — automates engineering tasks end to end and works with any LLM provider.
-
Cursor
An AI-first code editor (VS Code fork) with deep codebase awareness, multi-file edits, and agent mode — free hobby tier plus paid Pro.
-
Trae
An adaptive AI IDE with agent workflows and a token-based model — free tier plus a low-cost Lite plan.
-
Kilo Code
An open VS Code AI agent extension with pay-as-you-go model access — free signup credits to start building.
-
Zed
An open-source, high-performance code editor written in Rust with built-in AI assistant and real-time multiplayer editing.
-
Forge Code
An open-source AI coding agent for the terminal — access 300+ models via OpenRouter with a free daily token tier.
-
Pi Coding Agent
A minimalist open-source AI coding agent with just four tools (read, write, edit, bash), a sub-1000-token system prompt, and a self-modifying extension system.
-
Free Claude Code
A free, open-source Claude Code-compatible agent runner that works without API keys or subscriptions — run Claude Code-style agents directly from your terminal with no costs or limits.
-
Cline
-
3
Add AI features
Inference for the product itself — local, hosted, or both.
-
OpenRouter
A unified, OpenAI-compatible API that routes to dozens of models from one endpoint — includes a free tier with multiple free models.
-
Groq
An ultra-fast inference API serving open models (Llama, Mixtral, and more) on custom LPUs — free tier with thousands of requests per day.
-
NVIDIA NIM
NVIDIA's hosted API for hundreds of open models with an OpenAI-compatible endpoint — free credits to get started.
-
LocalAI
A free, open-source drop-in replacement for the OpenAI API that runs locally — supports text, image, audio, and embedding models with no cloud dependency.
-
Ollama
Run large language models locally with a single command. Supports Llama, Mistral, Gemma, and dozens more models on Mac, Windows, and Linux.
-
LLM Models
A curated guide to the top large language models — comparing capabilities, context windows, and the best use cases for each.
-
OpenRouter
-
4
Give it tools (MCP)
Expose your own APIs to models, then debug what the model actually sees.
-
FastMCP
A high-level Python framework for building MCP servers quickly — define tools, resources, and prompts with minimal boilerplate.
-
MCP Inspector
The official open-source debugging tool for MCP servers — inspect requests, responses, and tool schemas interactively in a browser UI.
-
Smithery
A community registry for discovering, installing, and sharing MCP servers — browse thousands of integrations for agents and AI tools.
-
FastMCP
-
5
Memory & document search
Persistent recall and RAG over your users' or your own documents.
-
MemoryPalace
An open-source long-term memory layer for LLMs — give your agents persistent recall across sessions for more coherent conversations.
-
AnythingLLM
An open-source, all-in-one desktop app for chatting with your documents using any LLM — supports RAG, agents, and multi-user workspaces locally.
-
MemoryPalace
-
6
Test & automate the UI
Drive the browser and desktop with natural-language automation.
-
Stagehand
An open-source AI browser automation framework built on Playwright — control the web with natural-language actions.
-
UI-TARS-desktop
The open-source multimodal AI agent stack connecting cutting-edge AI models and agent infrastructure.
-
Stagehand
-
7
Reusable agent skills
Drop-in expertise so your coding agent writes idiomatic code the first time.
-
Antigravity Awesome Skills
A massive library of 1,898+ reusable AI agent skills for Claude Code, Cursor, Codex CLI, and Gemini CLI — installable skill packs for coding, DevOps, data science, and more.
-
Laravel Specialist
A curated AI agent skill for Laravel development — helps coding assistants generate idiomatic Laravel 13+ code with best practices, routing, Eloquent, and Blade patterns.
-
GenAI Agents to Production
A hands-on guide with runnable tutorials for every building block of a production GenAI agent stack — from basic chatbots to complex multi-agent systems.
-
Antigravity Awesome Skills
Website
Research, build, and run a site — including an AI agent that lives inside it.
-
1
Research & plan
Ground the plan in real sources instead of a blank page.
-
NotebookLM
Google's AI research notebook that grounds answers in your sources and generates audio overviews — free to use.
-
DeerFlow
An open-source SuperAgent framework by ByteDance designed to orchestrate sub-agents, memory, sandboxed code execution, and extensible skills for long-horizon tasks.
-
LLM Models
A curated guide to the top large language models — comparing capabilities, context windows, and the best use cases for each.
-
Humata
An AI assistant that answers questions and summarizes across your PDFs and documents — free tier with monthly pages.
-
NotebookLM
-
2
Build the site
Coding agents and editors that handle multi-file changes end to end.
-
Cursor
An AI-first code editor (VS Code fork) with deep codebase awareness, multi-file edits, and agent mode — free hobby tier plus paid Pro.
-
Cline
An open-source autonomous coding agent for VS Code — plans tasks, edits files, and runs terminal commands with your approval, using any LLM you connect.
-
OpenCode
An open source agent that helps you write code in your terminal, IDE, or desktop.
-
Zed
An open-source, high-performance code editor written in Rust with built-in AI assistant and real-time multiplayer editing.
-
Roo Code
An open-source AI coding agent for VS Code — a whole dev team of AI agents that read, write, and run code in your editor using your own API keys.
-
Trae
An adaptive AI IDE with agent workflows and a token-based model — free tier plus a low-cost Lite plan.
-
Kilo Code
An open VS Code AI agent extension with pay-as-you-go model access — free signup credits to start building.
-
Forge Code
An open-source AI coding agent for the terminal — access 300+ models via OpenRouter with a free daily token tier.
-
Cursor
-
3
Add an on-site AI agent
One script tag turns the page into something visitors can talk to.
-
Page Agent
An open-source AI operator that lives in your web page — add one script tag to turn any website into an AI-native app with natural language control, zero infrastructure, and privacy by default.
-
OpenRouter
A unified, OpenAI-compatible API that routes to dozens of models from one endpoint — includes a free tier with multiple free models.
-
LocalAI
A free, open-source drop-in replacement for the OpenAI API that runs locally — supports text, image, audio, and embedding models with no cloud dependency.
-
Page Agent
-
4
Test in a real browser
Natural-language browser automation for smoke tests and regressions.
-
Stagehand
An open-source AI browser automation framework built on Playwright — control the web with natural-language actions.
-
UI-TARS-desktop
The open-source multimodal AI agent stack connecting cutting-edge AI models and agent infrastructure.
-
Stagehand
-
5
Produce the content
Draft, source, and fact-check copy for the pages themselves.
-
LLM Models
A curated guide to the top large language models — comparing capabilities, context windows, and the best use cases for each.
-
NotebookLM
Google's AI research notebook that grounds answers in your sources and generates audio overviews — free to use.
-
InkOS
An open-source, autonomous AI agent system designed for writing, auditing, and revising long-form novels.
-
LLM Models
-
6
Automate the ops
Forms, notifications, publishing, and everything else that repeats.
-
n8n
A fair-code, self-hostable workflow automation platform with native AI nodes — build agentic workflows connecting 400+ apps and any LLM.
-
Activepieces
An open-source, self-hostable automation platform with AI agents and MCP support — a no-code alternative to Zapier you can run yourself.
-
OpenClaw
An open-source, autonomous AI agent that runs locally to automate tasks, manage files, and act as a proactive personal assistant.
-
n8n
Design
Concepts, visuals, product geometry, and motion for brand and UI work.
-
1
Explore concepts & moodboards
Get to a visual direction fast with local image generation.
-
ComfyUI
A highly powerful, modular, and node/graph-based GUI pipeline for Stable Diffusion, enabling custom AI image and video generation workflows.
-
AUTOMATIC1111
The most widely used open-source web UI for Stable Diffusion — supports hundreds of models, ControlNet, inpainting, upscaling, and a massive extension ecosystem.
-
SceneWorks
A desktop-native AI image and video generation studio that runs on your own GPU — MLX on macOS, candle/CUDA on Windows. Features Image Studio, Video Studio, Character Studio, Document Studio, and Training Studio with 45+ image models and 9 video models.
-
ComfyUI
-
2
Product & CAD geometry
Text-to-CAD for physical products and printable parts.
-
CADAM
An open-source, AI-powered text-to-CAD application that runs entirely in the browser using WebAssembly to generate parametric 3D models from prompts and images.
-
CADAM
-
3
Prototype the interface
Have an agent build the real component instead of a static mockup.
-
Cursor
An AI-first code editor (VS Code fork) with deep codebase awareness, multi-file edits, and agent mode — free hobby tier plus paid Pro.
-
Cline
An open-source autonomous coding agent for VS Code — plans tasks, edits files, and runs terminal commands with your approval, using any LLM you connect.
-
OpenCode
An open source agent that helps you write code in your terminal, IDE, or desktop.
-
Zed
An open-source, high-performance code editor written in Rust with built-in AI assistant and real-time multiplayer editing.
-
Cursor
-
4
Motion & presentation
Animated deliverables and video walkthroughs of the work.
-
Remotion
Create videos programmatically using React.
-
Wan2.1
Alibaba's open-source video generation model — produces high-quality short clips from text or image prompts and runs on consumer GPUs.
-
ViMax
An open-source framework for agentic video generation, acting as a director, screenwriter, and producer.
-
Remotion
-
5
Assets for games & apps
Sprites, icons, and layered art in an engine-ready format.
-
Agent Sprite Forge
Codex skills for game-ready 2D sprites, layered maps, and engine-ready prototypes — ask in natural language, Codex plans the asset pipeline, renders with built-in image generation, then local processors clean, split, validate, and export assets for Godot, Unity, or raw 2D game workflows.
-
Agent Sprite Forge
Novel & Long-form Writing
Draft, revise, and audio-produce book-length work — privately if you want.
-
1
Draft & revise
Agents built for writing, auditing, and rewriting long manuscripts.
-
InkOS
An open-source, autonomous AI agent system designed for writing, auditing, and revising long-form novels.
-
LLM Models
A curated guide to the top large language models — comparing capabilities, context windows, and the best use cases for each.
-
InkOS
-
2
Keep it private & local
Run the model on your own machine so the manuscript never leaves it.
-
Ollama
Run large language models locally with a single command. Supports Llama, Mistral, Gemma, and dozens more models on Mac, Windows, and Linux.
-
LM Studio
A desktop app for discovering, downloading, and running local LLMs with a chat UI and an OpenAI-compatible local server.
-
Jan
An open-source, offline desktop app for running LLMs locally — clean chat UI with model management and an OpenAI-compatible API server.
-
GPT4All
Run powerful LLMs locally on CPU or GPU with no internet required — includes a desktop chat app and privacy-focused local AI inference.
-
llama.cpp
The foundational open-source inference engine for running quantized LLMs on CPU and GPU — the backbone powering Ollama, LM Studio, and most local runners.
-
Open WebUI
A self-hosted, feature-rich ChatGPT-style interface for running LLMs locally via Ollama or OpenAI-compatible APIs — with RAG, tools, and user management built in.
-
Ollama
-
3
Research & continuity
Source-grounded answers and long-term memory for characters and canon.
-
MemoryPalace
An open-source long-term memory layer for LLMs — give your agents persistent recall across sessions for more coherent conversations.
-
NotebookLM
Google's AI research notebook that grounds answers in your sources and generates audio overviews — free to use.
-
AnythingLLM
An open-source, all-in-one desktop app for chatting with your documents using any LLM — supports RAG, agents, and multi-user workspaces locally.
-
Humata
An AI assistant that answers questions and summarizes across your PDFs and documents — free tier with monthly pages.
-
MemoryPalace
-
4
Fit the whole book in context
Trim token overhead and run larger models on modest hardware.
-
Headroom
An open-source tool for reducing LLM token usage and context window overhead — helps you fit more into fewer tokens without losing relevant information.
-
AirLLM
An optimization tool that enables running massive Large Language Models (like Llama 3 70B/405B) on consumer-grade hardware with extremely low VRAM.
-
Headroom
-
5
Audiobook & narration
Synthesize or clone a narrating voice.
-
ElevenLabs
High-quality AI text-to-speech and voice cloning in many languages — free tier with monthly characters.
-
VoxCPM
An open-source text-to-speech and speech-to-text model that delivers high-quality speech synthesis and recognition in a unified framework.
-
ElevenLabs
-
6
Cover art
Generate and iterate on cover concepts locally.
-
ComfyUI
A highly powerful, modular, and node/graph-based GUI pipeline for Stable Diffusion, enabling custom AI image and video generation workflows.
-
AUTOMATIC1111
The most widely used open-source web UI for Stable Diffusion — supports hundreds of models, ControlNet, inpainting, upscaling, and a massive extension ecosystem.
-
SceneWorks
A desktop-native AI image and video generation studio that runs on your own GPU — MLX on macOS, candle/CUDA on Windows. Features Image Studio, Video Studio, Character Studio, Document Studio, and Training Studio with 45+ image models and 9 video models.
-
ComfyUI
Research
Ground answers in your sources, run deep multi-step investigations, and remember them.
-
1
Ground answers in your sources
Notebooks and RAG apps that cite the documents you gave them.
-
NotebookLM
Google's AI research notebook that grounds answers in your sources and generates audio overviews — free to use.
-
Open NotebookLM
An open-source alternative to Google NotebookLM — upload documents and generate podcast-style audio summaries using local or open-source TTS models.
-
Humata
An AI assistant that answers questions and summarizes across your PDFs and documents — free tier with monthly pages.
-
AnythingLLM
An open-source, all-in-one desktop app for chatting with your documents using any LLM — supports RAG, agents, and multi-user workspaces locally.
-
NotebookLM
-
2
Run deep, multi-step investigations
Agent frameworks that plan, search, and synthesize on their own.
-
DeerFlow
An open-source SuperAgent framework by ByteDance designed to orchestrate sub-agents, memory, sandboxed code execution, and extensible skills for long-horizon tasks.
-
OpenManus
An open-source recreation of the Manus general-purpose agent — runs autonomous multi-step tasks using any LLM without needing an invite.
-
Rowboat
An open-source, local-first AI coworker that builds a living knowledge graph from your work sources (Gmail, calendar, transcripts) and stores data locally as Markdown files.
-
DeerFlow
-
3
Capture meetings & interviews
Recording, transcription, and summaries you can search later.
-
4
Give it long-term memory
Persistent recall so the next session starts where the last one ended.
-
MemoryPalace
An open-source long-term memory layer for LLMs — give your agents persistent recall across sessions for more coherent conversations.
-
Rowboat
An open-source, local-first AI coworker that builds a living knowledge graph from your work sources (Gmail, calendar, transcripts) and stores data locally as Markdown files.
-
MemoryPalace
-
5
Keep sensitive material offline
Local models for material that can't go to a hosted API.
-
Ollama
Run large language models locally with a single command. Supports Llama, Mistral, Gemma, and dozens more models on Mac, Windows, and Linux.
-
LM Studio
A desktop app for discovering, downloading, and running local LLMs with a chat UI and an OpenAI-compatible local server.
-
Jan
An open-source, offline desktop app for running LLMs locally — clean chat UI with model management and an OpenAI-compatible API server.
-
GPT4All
Run powerful LLMs locally on CPU or GPU with no internet required — includes a desktop chat app and privacy-focused local AI inference.
-
Ollama
-
6
Turn findings into audio
Podcast-style overviews of a document set.
-
Open NotebookLM
An open-source alternative to Google NotebookLM — upload documents and generate podcast-style audio summaries using local or open-source TTS models.
-
NotebookLM
Google's AI research notebook that grounds answers in your sources and generates audio overviews — free to use.
-
Open NotebookLM
Data Analysis
Chat with your data, run models privately, and write the analysis code.
-
1
Chat with your data
Ask questions in plain language and get charts and tables back.
-
Julius
An AI data analyst that lets you chat with your data to analyze and visualize it — free tier.
-
AnythingLLM
An open-source, all-in-one desktop app for chatting with your documents using any LLM — supports RAG, agents, and multi-user workspaces locally.
-
Julius
-
2
Run models locally & privately
Keep proprietary datasets on your own hardware.
-
Ollama
Run large language models locally with a single command. Supports Llama, Mistral, Gemma, and dozens more models on Mac, Windows, and Linux.
-
LM Studio
A desktop app for discovering, downloading, and running local LLMs with a chat UI and an OpenAI-compatible local server.
-
Jan
An open-source, offline desktop app for running LLMs locally — clean chat UI with model management and an OpenAI-compatible API server.
-
llama.cpp
The foundational open-source inference engine for running quantized LLMs on CPU and GPU — the backbone powering Ollama, LM Studio, and most local runners.
-
GPT4All
Run powerful LLMs locally on CPU or GPU with no internet required — includes a desktop chat app and privacy-focused local AI inference.
-
LocalAI
A free, open-source drop-in replacement for the OpenAI API that runs locally — supports text, image, audio, and embedding models with no cloud dependency.
-
Ollama
-
3
Write the analysis code
Agents that write, run, and fix the notebook or script for you.
-
OpenCode
An open source agent that helps you write code in your terminal, IDE, or desktop.
-
Cline
An open-source autonomous coding agent for VS Code — plans tasks, edits files, and runs terminal commands with your approval, using any LLM you connect.
-
Roo Code
An open-source AI coding agent for VS Code — a whole dev team of AI agents that read, write, and run code in your editor using your own API keys.
-
Cursor
An AI-first code editor (VS Code fork) with deep codebase awareness, multi-file edits, and agent mode — free hobby tier plus paid Pro.
-
Pi Coding Agent
A minimalist open-source AI coding agent with just four tools (read, write, edit, bash), a sub-1000-token system prompt, and a self-modifying extension system.
-
OpenCode
-
4
Extract from documents & PDFs
Pull structured answers out of unstructured files.
-
Humata
An AI assistant that answers questions and summarizes across your PDFs and documents — free tier with monthly pages.
-
AnythingLLM
An open-source, all-in-one desktop app for chatting with your documents using any LLM — supports RAG, agents, and multi-user workspaces locally.
-
Humata
-
5
Burst to hosted inference
Fast free-tier endpoints when a job is too big for your laptop.
-
OpenRouter
A unified, OpenAI-compatible API that routes to dozens of models from one endpoint — includes a free tier with multiple free models.
-
Groq
An ultra-fast inference API serving open models (Llama, Mixtral, and more) on custom LPUs — free tier with thousands of requests per day.
-
NVIDIA NIM
NVIDIA's hosted API for hundreds of open models with an OpenAI-compatible endpoint — free credits to get started.
-
OpenRouter
-
6
Automate the recurring report
Schedule the pipeline instead of rerunning it by hand.
-
n8n
A fair-code, self-hostable workflow automation platform with native AI nodes — build agentic workflows connecting 400+ apps and any LLM.
-
Activepieces
An open-source, self-hostable automation platform with AI agents and MCP support — a no-code alternative to Zapier you can run yourself.
-
n8n
Daily Routines & Automation
Hand the repeating parts of your day to an agent that actually runs them.
-
1
Get a personal assistant
Local, autonomous agents that manage files and act on your behalf.
-
OpenClaw
An open-source, autonomous AI agent that runs locally to automate tasks, manage files, and act as a proactive personal assistant.
-
OpenHuman
Your personal AI super intelligence. Private, simple and extremely powerful.
-
Hermes Agent
An open-source, self-improving autonomous AI agent designed for persistence and memory, capable of learning and creating its own skills over time.
-
Rowboat
An open-source, local-first AI coworker that builds a living knowledge graph from your work sources (Gmail, calendar, transcripts) and stores data locally as Markdown files.
-
OpenClaw
-
2
Automate workflows
Self-hosted, node-based automation with AI steps built in.
-
n8n
A fair-code, self-hostable workflow automation platform with native AI nodes — build agentic workflows connecting 400+ apps and any LLM.
-
Activepieces
An open-source, self-hostable automation platform with AI agents and MCP support — a no-code alternative to Zapier you can run yourself.
-
n8n
-
3
Let it use your computer
Multimodal agents that click, type, and run commands.
-
UI-TARS-desktop
The open-source multimodal AI agent stack connecting cutting-edge AI models and agent infrastructure.
-
Goose
An open-source, on-machine AI agent from Block — automates engineering tasks end to end and works with any LLM provider.
-
OpenManus
An open-source recreation of the Manus general-purpose agent — runs autonomous multi-step tasks using any LLM without needing an invite.
-
UI-TARS-desktop
-
4
Let it use the browser
Natural-language control of web pages and logged-in sessions.
-
Stagehand
An open-source AI browser automation framework built on Playwright — control the web with natural-language actions.
-
Page Agent
An open-source AI operator that lives in your web page — add one script tag to turn any website into an AI-native app with natural language control, zero infrastructure, and privacy by default.
-
Stagehand
-
5
Handle meetings & documents
Notes, summaries, and answers without attending everything.
-
6
Give it memory
So your assistant stops asking the same questions every morning.
-
MemoryPalace
An open-source long-term memory layer for LLMs — give your agents persistent recall across sessions for more coherent conversations.
-
MemoryPalace
Audio, Voice & Music
Transcribe, synthesize, clone, and dub audio in any language.
-
1
Transcribe speech
Speech-to-text across dozens of languages, locally or hosted.
-
Whisper
OpenAI's open-source speech recognition model that transcribes and translates audio in 99 languages with high accuracy — runs locally on CPU or GPU.
-
Fathom
An AI meeting assistant that records, transcribes, and summarizes calls — forever-free plan.
-
VoxCPM
An open-source text-to-speech and speech-to-text model that delivers high-quality speech synthesis and recognition in a unified framework.
-
Whisper
-
2
Synthesize & clone voices
Text-to-speech good enough for narration and characters.
-
ElevenLabs
High-quality AI text-to-speech and voice cloning in many languages — free tier with monthly characters.
-
VoxCPM
An open-source text-to-speech and speech-to-text model that delivers high-quality speech synthesis and recognition in a unified framework.
-
ElevenLabs
-
3
Dub & translate
Rebuild the audio track in another language, lip-timed to the video.
-
pyVideoTrans
An open-source video translation and dubbing tool — automatically translates speech, subtitles, and audio from one language to another.
-
ElevenLabs
High-quality AI text-to-speech and voice cloning in many languages — free tier with monthly characters.
-
pyVideoTrans
-
4
Run audio models locally
Self-hosted endpoints for transcription and synthesis.
-
LocalAI
A free, open-source drop-in replacement for the OpenAI API that runs locally — supports text, image, audio, and embedding models with no cloud dependency.
-
llama.cpp
The foundational open-source inference engine for running quantized LLMs on CPU and GPU — the backbone powering Ollama, LM Studio, and most local runners.
-
LocalAI
-
5
Produce podcasts & overviews
Turn documents into conversational audio.
-
Open NotebookLM
An open-source alternative to Google NotebookLM — upload documents and generate podcast-style audio summaries using local or open-source TTS models.
-
NotebookLM
Google's AI research notebook that grounds answers in your sources and generates audio overviews — free to use.
-
Open NotebookLM
AI Agent or Assistant
Build your own agent: framework, tools, memory, model, and the ability to act.
-
1
Learn the stack
Runnable tutorials and a model-by-model comparison before you commit.
-
GenAI Agents to Production
A hands-on guide with runnable tutorials for every building block of a production GenAI agent stack — from basic chatbots to complex multi-agent systems.
-
LLM Models
A curated guide to the top large language models — comparing capabilities, context windows, and the best use cases for each.
-
GenAI Agents to Production
-
2
Pick a framework
Orchestration for sub-agents, planning, and sandboxed execution.
-
Google ADK
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
-
AgentScope
Build and run agents you can see, understand and trust.
-
DeerFlow
An open-source SuperAgent framework by ByteDance designed to orchestrate sub-agents, memory, sandboxed code execution, and extensible skills for long-horizon tasks.
-
OpenManus
An open-source recreation of the Manus general-purpose agent — runs autonomous multi-step tasks using any LLM without needing an invite.
-
Hermes Agent
An open-source, self-improving autonomous AI agent designed for persistence and memory, capable of learning and creating its own skills over time.
-
Google ADK
-
3
Give it tools (MCP)
Build servers, browse the registry, and debug the protocol traffic.
-
FastMCP
A high-level Python framework for building MCP servers quickly — define tools, resources, and prompts with minimal boilerplate.
-
Smithery
A community registry for discovering, installing, and sharing MCP servers — browse thousands of integrations for agents and AI tools.
-
MCP Inspector
The official open-source debugging tool for MCP servers — inspect requests, responses, and tool schemas interactively in a browser UI.
-
FastMCP
-
4
Give it memory
Persistent recall and a knowledge graph over your own work.
-
MemoryPalace
An open-source long-term memory layer for LLMs — give your agents persistent recall across sessions for more coherent conversations.
-
AnythingLLM
An open-source, all-in-one desktop app for chatting with your documents using any LLM — supports RAG, agents, and multi-user workspaces locally.
-
Rowboat
An open-source, local-first AI coworker that builds a living knowledge graph from your work sources (Gmail, calendar, transcripts) and stores data locally as Markdown files.
-
MemoryPalace
-
5
Run the model
Local engines and free hosted endpoints to serve the agent's brain.
-
Ollama
Run large language models locally with a single command. Supports Llama, Mistral, Gemma, and dozens more models on Mac, Windows, and Linux.
-
llama.cpp
The foundational open-source inference engine for running quantized LLMs on CPU and GPU — the backbone powering Ollama, LM Studio, and most local runners.
-
LM Studio
A desktop app for discovering, downloading, and running local LLMs with a chat UI and an OpenAI-compatible local server.
-
LocalAI
A free, open-source drop-in replacement for the OpenAI API that runs locally — supports text, image, audio, and embedding models with no cloud dependency.
-
OpenRouter
A unified, OpenAI-compatible API that routes to dozens of models from one endpoint — includes a free tier with multiple free models.
-
Groq
An ultra-fast inference API serving open models (Llama, Mixtral, and more) on custom LPUs — free tier with thousands of requests per day.
-
NVIDIA NIM
NVIDIA's hosted API for hundreds of open models with an OpenAI-compatible endpoint — free credits to get started.
-
Ollama
-
6
Let it act on the world
Desktop and browser control, plus an agent embedded in your site.
-
UI-TARS-desktop
The open-source multimodal AI agent stack connecting cutting-edge AI models and agent infrastructure.
-
Stagehand
An open-source AI browser automation framework built on Playwright — control the web with natural-language actions.
-
Page Agent
An open-source AI operator that lives in your web page — add one script tag to turn any website into an AI-native app with natural language control, zero infrastructure, and privacy by default.
-
OpenClaw
An open-source, autonomous AI agent that runs locally to automate tasks, manage files, and act as a proactive personal assistant.
-
UI-TARS-desktop
-
7
Add reusable skills
Pre-built expertise you can drop into a coding agent.
-
Antigravity Awesome Skills
A massive library of 1,898+ reusable AI agent skills for Claude Code, Cursor, Codex CLI, and Gemini CLI — installable skill packs for coding, DevOps, data science, and more.
-
Laravel Specialist
A curated AI agent skill for Laravel development — helps coding assistants generate idiomatic Laravel 13+ code with best practices, routing, Eloquent, and Blade patterns.
-
Free Claude Code
A free, open-source Claude Code-compatible agent runner that works without API keys or subscriptions — run Claude Code-style agents directly from your terminal with no costs or limits.
-
Antigravity Awesome Skills
-
8
Cut token cost
Fit more into context and run big models on small machines.
-
Headroom
An open-source tool for reducing LLM token usage and context window overhead — helps you fit more into fewer tokens without losing relevant information.
-
AirLLM
An optimization tool that enables running massive Large Language Models (like Llama 3 70B/405B) on consumer-grade hardware with extremely low VRAM.
-
Headroom
Run AI on Your Own Machine
A private stack: your hardware, your models, an OpenAI-compatible API.
-
1
Check your hardware
Find out which models your GPU and RAM can actually handle.
-
CanIRun.ai
A browser-based tool that automatically detects your hardware and estimates which AI models can run locally on your system.
-
CanIRun.ai
-
2
Pick a model
Compare capabilities, context windows, and licences.
-
LLM Models
A curated guide to the top large language models — comparing capabilities, context windows, and the best use cases for each.
-
LLM Models
-
3
Run it
Inference engines and one-command model runners.
-
Ollama
Run large language models locally with a single command. Supports Llama, Mistral, Gemma, and dozens more models on Mac, Windows, and Linux.
-
llama.cpp
The foundational open-source inference engine for running quantized LLMs on CPU and GPU — the backbone powering Ollama, LM Studio, and most local runners.
-
LM Studio
A desktop app for discovering, downloading, and running local LLMs with a chat UI and an OpenAI-compatible local server.
-
Jan
An open-source, offline desktop app for running LLMs locally — clean chat UI with model management and an OpenAI-compatible API server.
-
GPT4All
Run powerful LLMs locally on CPU or GPU with no internet required — includes a desktop chat app and privacy-focused local AI inference.
-
AirLLM
An optimization tool that enables running massive Large Language Models (like Llama 3 70B/405B) on consumer-grade hardware with extremely low VRAM.
-
Ollama
-
4
Get a chat interface
Self-hosted UIs with model management and document chat.
-
Open WebUI
A self-hosted, feature-rich ChatGPT-style interface for running LLMs locally via Ollama or OpenAI-compatible APIs — with RAG, tools, and user management built in.
-
AnythingLLM
An open-source, all-in-one desktop app for chatting with your documents using any LLM — supports RAG, agents, and multi-user workspaces locally.
-
Jan
An open-source, offline desktop app for running LLMs locally — clean chat UI with model management and an OpenAI-compatible API server.
-
Open WebUI
-
5
Expose an OpenAI-compatible API
Point existing code at localhost instead of a vendor.
-
LocalAI
A free, open-source drop-in replacement for the OpenAI API that runs locally — supports text, image, audio, and embedding models with no cloud dependency.
-
Ollama
Run large language models locally with a single command. Supports Llama, Mistral, Gemma, and dozens more models on Mac, Windows, and Linux.
-
llama.cpp
The foundational open-source inference engine for running quantized LLMs on CPU and GPU — the backbone powering Ollama, LM Studio, and most local runners.
-
LocalAI
-
6
Fall back to the cloud
Free tiers for the jobs your machine can't finish.
-
OpenRouter
A unified, OpenAI-compatible API that routes to dozens of models from one endpoint — includes a free tier with multiple free models.
-
Groq
An ultra-fast inference API serving open models (Llama, Mixtral, and more) on custom LPUs — free tier with thousands of requests per day.
-
NVIDIA NIM
NVIDIA's hosted API for hundreds of open models with an OpenAI-compatible endpoint — free credits to get started.
-
OpenRouter
-
7
Stretch the context window
Reduce token overhead and squeeze in bigger models.
-
Headroom
An open-source tool for reducing LLM token usage and context window overhead — helps you fit more into fewer tokens without losing relevant information.
-
AirLLM
An optimization tool that enables running massive Large Language Models (like Llama 3 70B/405B) on consumer-grade hardware with extremely low VRAM.
-
Headroom
Marketing & Social Content
Research the angle, produce the assets, and automate the campaign.
-
1
Research & positioning
Source-grounded competitive and audience research.
-
NotebookLM
Google's AI research notebook that grounds answers in your sources and generates audio overviews — free to use.
-
DeerFlow
An open-source SuperAgent framework by ByteDance designed to orchestrate sub-agents, memory, sandboxed code execution, and extensible skills for long-horizon tasks.
-
Humata
An AI assistant that answers questions and summarizes across your PDFs and documents — free tier with monthly pages.
-
LLM Models
A curated guide to the top large language models — comparing capabilities, context windows, and the best use cases for each.
-
NotebookLM
-
2
Short-form video
Scripted, generated, and edited clips for social.
-
reels-af
An open-source AI agent that automates creating short-form video content by generating scripts, sourcing clips, and editing Reels/Shorts/TikToks automatically.
-
ViMax
An open-source framework for agentic video generation, acting as a director, screenwriter, and producer.
-
Wan2.1
Alibaba's open-source video generation model — produces high-quality short clips from text or image prompts and runs on consumer GPUs.
-
video-use
100% open-source video editing with an AI coding agent — drop raw footage in a folder, chat, and get final.mp4 back with filler cuts, color grading, subtitles, and animation overlays.
-
Vynaro
Desktop AI video narration editor: a 7-step pipeline turns film and drama clips into narrated, subtitled vertical videos with CapCut draft export.
-
OpenMontage
An open-source tool for creating video montages and compilations automatically — stitch clips, add transitions, and generate highlight reels with AI assistance.
-
reels-af
-
3
Visuals & creative
Ad creative and social images generated locally.
-
ComfyUI
A highly powerful, modular, and node/graph-based GUI pipeline for Stable Diffusion, enabling custom AI image and video generation workflows.
-
AUTOMATIC1111
The most widely used open-source web UI for Stable Diffusion — supports hundreds of models, ControlNet, inpainting, upscaling, and a massive extension ecosystem.
-
SceneWorks
A desktop-native AI image and video generation studio that runs on your own GPU — MLX on macOS, candle/CUDA on Windows. Features Image Studio, Video Studio, Character Studio, Document Studio, and Training Studio with 45+ image models and 9 video models.
-
ComfyUI
-
4
Voice & localisation
Narration and dubbed versions for other markets.
-
ElevenLabs
High-quality AI text-to-speech and voice cloning in many languages — free tier with monthly characters.
-
VoxCPM
An open-source text-to-speech and speech-to-text model that delivers high-quality speech synthesis and recognition in a unified framework.
-
pyVideoTrans
An open-source video translation and dubbing tool — automatically translates speech, subtitles, and audio from one language to another.
-
ElevenLabs
-
5
Automate campaigns
Scheduling, publishing, and multi-step follow-up.
-
n8n
A fair-code, self-hostable workflow automation platform with native AI nodes — build agentic workflows connecting 400+ apps and any LLM.
-
Activepieces
An open-source, self-hostable automation platform with AI agents and MCP support — a no-code alternative to Zapier you can run yourself.
-
OpenClaw
An open-source, autonomous AI agent that runs locally to automate tasks, manage files, and act as a proactive personal assistant.
-
n8n
-
6
Follow up on calls
Recorded, transcribed, summarized sales and partner calls.
-
Fathom
An AI meeting assistant that records, transcribes, and summarizes calls — forever-free plan.
-
Fathom
TL;DevTech // Recent Posts
- Meta's Muse Code Is 10x Cheaper. There's a Catch. Aug 8, 2026
- Nvidia Confirms RTX Spark Successors N2X and N3X Aug 7, 2026
- China's AI Companion Rules: A Developer's Guide Aug 7, 2026
- The Empty Shelf and the Quiet Push: MacBook Air Shortage Aug 7, 2026
- H100 in Orbit: StarCloud's 88,000-Satellite Flex Aug 7, 2026
TL;DevTech // Edge & Local AI Hardware
-
Nvidia RTX 3090 Available
24GB GDDR6X VRAM. A proven workhorse for local AI inference — runs 13B–70B quantized models at solid speeds. Great value on the used market for developers entering local AI.
-
Nvidia RTX 5070 Ti Available
16GB GDDR7 VRAM with next-gen Blackwell architecture. Exceptional FP8/FP4 throughput for local inference — rivals last-gen flagships at a lower price point.
-
Nvidia RTX 5090 Available
32GB GDDR7 VRAM. The flagship Blackwell GPU for local AI workloads — runs large quantized models with bandwidth and compute headroom to spare.
-
Nvidia RTX Spark Superchip Coming Soon
Co-developed MediaTek ARM CPU + Blackwell GPU in a compact form. 128GB unified memory and 1 Petaflop FP4 performance lets developers natively run 120B parameter models on Windows with zero cloud latency.
-
Apple M6 Family Coming Soon
Potential 2nm process with WMCM multi-chip packaging for memory bandwidth scaling. Designed to accelerate local open-source models using Apple's native MLX framework — no discrete GPU needed.