AI use cases

2925 ways people actually use AI, compiled from the videos in this library. Each names the job and why it is worth doing, and links to the moment in the source video.

Agent browser automation — Moli provides a headless browser engine that builds DOM layout on demand for geometry or screenshots.

Github Awesome
AI-generated game-art workflow — Sprite-maker combines prompting, references, AI-planned rigs and key poses, deterministic rendering, and optional region repair.

Github Awesome
Agent communication — Pi-peer lets coding-agent sessions on one machine exchange constrained plain-text messages.

Github Awesome
Design assistance — Airship lets an existing coding agent edit real project source from described visual changes.

Github Awesome
AI interface feedback — Generative-loaders supplies animated waiting states for streaming text, activity indicators, and image generation.

Github Awesome
Benchmark generation — Arc-task-gen creates fresh ARC-style puzzles matched to the distribution of a public evaluation.

Github Awesome
Coding-agent orchestration — Waku places multiple local coding agents behind one interface and maintains their sessions and project tasks.

Github Awesome
Coding assistance — Ante runs a terminal coding-agent loop offline using its embedded inference engine.

Github Awesome
Research software architectures — Make a coding agent consult arXiv papers and converge on a recommendation with documented prior failure modes.

Github Awesome
Execute large implementation plans — Coordinate persistent worker loops for implementation, review, repair, and independent rechecking across context resets.

Github Awesome
Evolve coding agents — Preserve, mutate, or replace agents' prompts, code, tools, and dependencies based on benchmark evidence.

Github Awesome
Translate speech locally — Perform two-way voice translation on a Raspberry Pi 5 without internet access after setup.

Github Awesome
Generate video and audio — Create up to 15 seconds of video with native stereo audio from mixed text, image, video, and audio references.

Github Awesome
Run persistent coding workflows — Preserve sessions, memory, schedules, checkpoints, and reusable lessons while delegating work to isolated sub-agents.

Github Awesome
Modify sandboxed applications — Allow agents to work on private per-user copies while queuing simulated permission outcomes for bulk approval.

Github Awesome
Compress coding-agent context — Reduce upstream tool-output and history context while retaining expandable references.

Github Awesome
PDF retrieval — Token-Saver uses local BM25 and embedding search to send only relevant passages with page citations to Claude Desktop.

Github Awesome
Video-generation acceleration — ComfyUI-Spectrum-MiniMax-H3 forecasts intermediate hidden features to avoid running the transformer on every step.

Github Awesome
AI-agent workflow evaluation — RealReplicaBench tests whether agents can complete 107 long business workflows in reproducible service replicas.

Github Awesome
Video generation — MAGI-2-preview generates 10-second videos with synchronized audio from prompts or prompts plus still images.

Github Awesome
Document visual understanding — Doc7 renders document pages and sends them to a vision model to preserve charts, diagrams, relationships, and visible UI state in Markdown.

Github Awesome
Video captioning and transcription — Captivo generates captions on-device through whisper.cpp, while Open Edit transcribes video and designs stylized subtitles.

Github Awesome
Large-model inference on Apple devices — Swiftlet runs 35B and 80B Qwen mixture-of-experts models by streaming routed experts from SSD.

Github Awesome
Local LLM fine-tuning — Soup fine-tunes LLMs locally with QLoRA and includes reward-hack mitigation for GRPO runs.

Github Awesome
Model-driven office editing — Gen Office embeds model-driven editing into document, spreadsheet, presentation, and PDF workspaces.

Github Awesome
Video-to-video generation — Finger Frame AI regenerates a video while preserving the subject's movement and facial alignment.

Github Awesome
3D scene reconstruction — QuerySplat predicts 3D Gaussian splats, cameras, depth point clouds, and appearance from a handful of photos.

Github Awesome
Personal assistant memory retrieval — Waku-agent demonstrates an agent harness, loop, memory, and evaluation structure while deciding whether each turn needs memory.

Github Awesome
Agent file-system execution — Cloudflare Computer gives an agent a durable SQLite-backed file system projected into containers, shells, or ECMAScript workers.

Github Awesome
Business-context retrieval — AWS's context ontology accelerator converts databases and files into validated ontology and knowledge-graph context for agents.

Github Awesome
Coding assistance — Soul advisor, DSCode, Scopey, and related projects coordinate coding agents, isolate work, checkpoint changes, or detect scope drift.

Github Awesome
Research and CRM maintenance — CRM uses a durable research agent to process queued database rows while preventing unsupported personal inferences.

Github Awesome
Large-model inference — WASTE and Kimi K3 in C stream model components from storage and use caches to run models without conventional GPU requirements.

Github Awesome
Code-change review — Ratchet checks agent-produced edits for unnecessary dependencies, duplicate helpers, thin wrappers, and other patterns.

Github Awesome
Writing analysis — Humanizer CLI identifies mechanical signs of machine-written prose and provides editing guidance.

Github Awesome
Procedure recording — Skill recorder reconstructs the intent and ordered steps of a real work session for reuse as an agent skill or scheduled automation.

Github Awesome
Workplace coordination and campaign production — QM and the marketing team Eve template isolate agents, route work among specialists, and preserve shared context.

Github Awesome
Generating interactive video worlds — Lingbot World V2 generates long interactive video with causal frame generation, KV caching, and planning agents.

Github Awesome
Building a personal model from application-use context — Persome exposes receipts-backed memory over MCP so trusted clients can access work context outside the chat window.

Github Awesome
Reviewing and improving user interfaces — The skills collection gives coding agents structured checks for visual design, accessibility, layout, details, and product writing.

Github Awesome
Rebuilding 3D objects from reference images using procedural code — IMG3JS and the Three.js Object Sculptor Codex Plugin create animation-ready models with pivots, sockets, and colliders.

Github Awesome
Searching papers, querying scientific databases, running code, and preserving research artifacts with provenance — Open science supports literature review, experiments, and write-ups in one browser workspace.

Github Awesome
Producing files, updating applications, working across documents and the terminal, and scheduling recurring jobs — Open Worker acts as a desktop co-worker rather than stopping at a chat response.

Github Awesome
Evaluate multimodal perception — PerceptionBench tests visual skills such as counting, depth, localization, OCR, and hallucination resistance before reasoning.

Github Awesome
Generate multilingual speech and clone voices — Audio8_TTS provides multilingual speech generation and zero-shot voice cloning in a 0.6 billion parameter model.

Github Awesome
Optimize generative-engine visibility — GeoLook samples brand visibility across AI engines, audits citation gaps, and produces implementation tickets and deployable assets.

Github Awesome
Control robots from vision and instructions — TurboVLA encodes vision and instructions separately and predicts continuous action chunks with a compact decoder.

Github Awesome
Coordinate software delivery — CodeJury divides delivery into six terminal-driven stages and uses multiple configurable review roles before execution.

Github Awesome
Monitor and control coding agents — Numbat applies local CEL rules to agent events for live alerts, forensic timelines, and supported pre-action blocking.

Github Awesome
Reduce coding-agent tool context — Ratel searches tool schemas and skill metadata and injects only the capabilities relevant to the current turn.

Github Awesome
Route requests among models — World model optimizer scores registered models on held-out tasks and serves an endpoint that chooses a model per request.

Github Awesome
Large-model local inference — DeltaFin streams routed experts from a CDN into a growing cache so a 2.8 trillion-parameter mixture-of-experts model can run on a 64 GB MacBook.

Github Awesome
Robot task planning and control — Tau Zero VLA splits long-horizon robot work into subtasks and uses a world model to search alternative actions when plans become uncertain.

Github Awesome
Agent framework execution — labs-OO-Agents hands methods with ellipsis bodies to a model while retaining deterministic Python implementations for methods with real bodies.

Github Awesome
Agent-session accounting — agentacct joins Claude Code and Codex logs with tasks and test evidence to estimate tokens and cost and distinguish verified from agent-reported work.

Github Awesome
Writing and marketing-copy generation — AI copywriter interviews the user, writes marketing copy, and removes listed AI-writing patterns without inventing product facts.

Github Awesome
Agentic reinforcement-learning environments — AgentENV provides sandboxed, forkable environments for Kimi K3's agentic RL training.

Github Awesome
Coding-agent game generation — Claude-of-Duty uses a fleet of coding agents to generate a browser FPS and evaluates the result with screenshot tests and profiling.

Github Awesome
Scientific research assistance — Open Science can read files, run Python or R, search the web, query permissioned life-science connectors, and preview generated scientific artifacts.

Github Awesome
Home automation and personal information assistance — Renfield's agent works across Home Assistant, calendars, email, media, and documents using local context from a RAG knowledge base and long-term memory.

Github Awesome