Troiana field guides01 / Library
Use AI tools
with intent.
Practical, source-backed guides for finding the official product, setting it up, learning its strongest workflows, and checking the work before it ships.
Published collections
Choose a platform.
Every published collection is written around the platform’s actual access points, capabilities, workflow, and risks—not a recycled template.
Creative AI
Adobe Firefly
Developing branded visual directions, generating and editing images, creating short video or audio assets, and moving creative experiments into Adobe workflows.
Enterprise language model platform
AI21 Studio
Building and operating language applications with AI21's Jamba models, including long-context chat, structured output, classification, summarization, extraction, and enterprise workflows.
Terminal and editor coding agent
Amp
Running focused coding tasks in durable threads, applying repository guidance, reviewing changes, and using different reasoning modes from the terminal or editor.
Scalable AI compute
Anyscale
Developing and operating distributed Python and AI workloads, including scalable Ray Serve endpoints for language and machine-learning models.
Speech AI platform
AssemblyAI
Transcribing recorded or live speech and extracting structured insights such as speakers, chapters, entities, topics, sentiment, and summaries.
Enterprise AI application platform
Microsoft Foundry
Building, evaluating, deploying, and governing enterprise generative AI applications and agents across models, tools, data, and Azure services.
Enterprise generative AI platform
Alibaba Cloud Model Studio
Building regional generative AI applications with Qwen and other models, governed knowledge bases and agents, or managed fine-tuning and inference inside Alibaba Cloud workspaces.
AI model deployment
Baseten
Turning open or custom models into versioned autoscaling APIs with development deployments, stable environments, observability, and controlled promotion.
Managed foundation models
Amazon Bedrock
Building governed generative AI applications across multiple foundation models with managed inference, evaluation, Knowledge Bases, Guardrails, and AWS integrations.
Licensed visual AI platform
Bria AI
Generating commercially oriented visuals with structured control, building reproducible masked edits, producing product and lifestyle imagery, and integrating asynchronous visual generation into governed applications.
Agentic browser automation
Browserless
Giving applications and AI agents managed browsers for stateful navigation, extraction, screenshots, PDFs, audits, and Puppeteer or Playwright automation.
High-speed AI inference
Cerebras Inference
Latency-sensitive language-model applications that need very fast token generation through a hosted API.
General assistant
ChatGPT
Broad everyday work: drafting, file analysis, research, image work, voice, and structured problem-solving.
Desktop AI productivity studio
Cherry Studio
Managing multiple model providers from one desktop app, comparing assistants, working with a local knowledge base, and extending personal workflows with carefully reviewed agents and MCP tools.
Community model platform
Civitai
Discovering exact versions of community models and related resources, inspecting samples and metadata, and publishing documented generative media resources.
Reasoning and writing
Claude
Careful long-form writing, reasoning through complex material, and disciplined coding or document work.
Agentic coding
Claude Code
Inspecting repositories, planning and implementing code changes, running development tools, debugging failures, and coordinating reviewable engineering work.
Agentic coding
Cline
Planning, implementing, testing, and reviewing multi-file software changes with visible tool use and configurable approvals.
AI image editing toolkit
Clipdrop
Rapidly removing backgrounds, objects, defects, and text; relighting or extending images; upscaling drafts; and creating controlled visual variants for product, property, portrait, and campaign work.
Sandbox-aware coding agent
CodeBuddy
Running complex coding tasks with visible artifacts and diffs while combining layered allow, ask, and deny rules with directory trust and OS-level shell sandboxing.
OpenAI coding agent
Codex
Planning, implementing, reviewing, and validating bounded software changes while using repository instructions, isolated worktrees, and human-controlled permissions.
Enterprise language AI
Cohere
Building enterprise text generation and retrieval systems with Chat, multilingual embeddings, semantic Rerank, tool use, and grounded generation.
Node-based generative AI
ComfyUI
Building reproducible node graphs for image, video, audio, and other generative workflows with precise control over models and parameters.
Microsoft AI assistant
Microsoft Copilot
Everyday drafting, summarization, image creation, voice, and Microsoft-oriented work where the relevant experience and account access are already in place.
Agent experience framework
CopilotKit
Building product-native agent interfaces with chat, custom components, shared application state, frontend tools, streaming, and deterministic human approval checkpoints.
Visual agent and workflow platform
Coze
Composing and publishing AI agents and workflows with prompts, models, knowledge, variables, plugins, APIs, and channel integrations without building every orchestration surface from scratch.
Multi-agent orchestration
CrewAI
Building collaborative agent crews for autonomous tasks and structured, stateful Flows for reliable event-driven AI automation.
AI code editor
Cursor
Working with AI inside a real codebase: planning a change, editing files, reviewing diffs, and testing the result.
AI creation toolkit
DeepAI
Quickly exploring AI chat and visual concepts, generating or editing images, producing short visual drafts, and integrating straightforward media endpoints into prototypes.
AI inference cloud
DeepInfra
Serving language, embedding, reranking, vision, image, video, and speech models through a common API; testing model alternatives; and deploying private models at controlled scale.
Language AI platform
DeepL
Translating text and office documents, improving tone and phrasing, maintaining terminology with glossaries and style rules, and embedding reviewed multilingual workflows into products.
Reasoning assistant
DeepSeek
Reasoning through technical questions, exploring code or mathematics, working with uploaded text, and comparing a second model’s approach.
Autonomous software engineer
Devin
Investigating codebases, implementing scoped engineering tasks, producing pull requests, and standardizing repeatable work with Knowledge and Playbooks.
Low-code AI application platform
Dify
Building low-code AI workflows, chatflows, agents, RAG applications, model integrations, plugins, and deployable APIs with operational visibility.
Voice and audio
ElevenLabs
Producing voiceovers, designing or selecting voices, generating speech with controlled delivery, dubbing, sound creation, and audio localization.
AI web search
Exa
Finding web sources with semantic and filtered search, retrieving page contents, and supplying inspectable evidence to research or agent workflows.
Generative media infrastructure
fal
Calling production media-generation models asynchronously and deploying custom image, video, audio, and multimodal workloads on serverless GPUs.
Knowledge and workflow platform
FastGPT
Building grounded Q&A applications from documents, composing visual AI workflows and plugins, and publishing controlled agents through web channels or APIs.
Open-model serverless inference
Featherless.ai
Exploring many Hugging Face language models without provisioning GPUs, comparing creative, role-playing, coding, and general chat models, and prototyping OpenAI-compatible integrations.
Web data extraction
Firecrawl
Turning websites into markdown, structured records, URL maps, search results, screenshots, and asynchronous crawl datasets for AI applications.
Generative AI inference
Fireworks AI
Testing and serving generative models through shared serverless inference or private dedicated GPU deployments.
Expressive AI voice platform
Fish Audio
Creating expressive narration and dialogue, localizing approved scripts, prototyping realtime speech, and integrating controlled text-to-speech or authorized voice models into products.
Image generation and editing
FLUX
Creating and editing high-fidelity images with FLUX.2 variants, including multi-reference composition, typography, precise colors, and production image workflows.
Production AI inference platform
FriendliAI
Serving open models through instant APIs, deploying pinned Hugging Face models on dedicated GPUs, running private inference containers, and operating production inference with explicit scaling and observability.
Google AI assistant
Gemini
Working across large source material and Google-oriented workflows, especially when the relevant documents and context already live in your Google account.
Gemini-powered terminal agent
Gemini CLI
Completing bounded repository tasks from the terminal with explicit tool approvals, optional sandboxing, recoverable checkpoints, and scriptable output.
Coding agent
GitHub Copilot
Making scoped changes in a connected repository while reviewing the diff and carrying the work into a pull request.
Open-source local agent
goose
Running local coding and knowledge-work agents with selectable model providers, extensible MCP tools, reusable recipes, and configurable security controls.
Interactive AI application framework
Gradio
Rapidly turning Python functions, models, agents, media pipelines, and APIs into interactive demos, internal tools, evaluation interfaces, and production AI web applications.
Web and X assistant
Grok
Exploring current conversations, searching public web and X material, brainstorming, and pressure-testing a question from another angle.
Low-latency AI inference
Groq
Building latency-sensitive text, audio, tool-use, and structured-output applications on supported hosted models.
AI video and media platform
Hailuo AI
Creating short cinematic video concepts, animating owned images, testing camera movement, and producing subject-led social-video drafts from controlled references.
AI video generation and editing
Haiper
Creating short video concepts, animating owned images, restyling footage, extending a shot, and repairing selected regions without rebuilding an entire clip.
AI character and video studio
Hedra
Producing short speaking-character clips, audio-driven avatars, stylized character performances, and assembled multi-scene videos from controlled image and voice assets.
Open AI platform
Hugging Face
Discovering and evaluating open models and datasets, running hosted inference, collaborating through repositories, and publishing ML demos with Spaces.
AI inference and GPU cloud
Hyperbolic
Testing and serving open text, image, audio, and vision-language models through serverless APIs, or renting GPU capacity for controlled model and compute workloads.
Graphic generation
Ideogram
Creating graphic concepts, posters, social visuals, compositions containing text, style explorations, and editable image directions.
Multimodal search foundation
Jina AI
Building multilingual or multimodal semantic search, retrieval-augmented generation, relevance reranking, classification, and web-to-LLM ingestion workflows.
JetBrains coding agent
Junie
Exploring a codebase, producing an implementation plan, making supervised changes, and reviewing local or pull-request diffs with durable project guidance.
Configurable coding agent
Kilo Code
Planning and completing repository tasks with specialized agents, configurable providers, project rules, granular tool permissions, and optional terminal automation.
Multimodal AI agent
Kimi
Long-context and multimodal assistance, source-backed research, documents, spreadsheets, presentations, websites, and multi-step agent tasks.
Spec-driven agentic IDE
Kiro
Turning feature ideas into requirements, design, tasks, and implementation while preserving repository guidance and explicit review of agent changes.
Generative video
Kling AI
Creating text-to-video and image-to-video shots, controlling start and end frames, and maintaining subjects with reusable Elements.
Real-time AI creative suite
Krea
Rapid visual exploration, live art direction, image and video iteration, creative upscaling, style-guided generation, and assembling repeatable multi-model workflows.
Agent application framework
LangChain
Building agents with standardized model interfaces, typed tools, structured output, middleware, persistence, and human approval controls.
LLM engineering observability
Langfuse
Tracing complete LLM requests, debugging agents and retrieval, managing prompt versions, running experiments and evaluations, and monitoring quality, latency, tokens, and cost.
Durable agent orchestration
LangGraph
Designing stateful agent workflows that require explicit control flow, durable checkpoints, streaming, recovery, memory, and human-in-the-loop decisions.
LLM observability and evaluation
LangSmith
Tracing agent and LLM runs, investigating failures, comparing prompts and models on datasets, collecting feedback, monitoring production quality, and promoting tested versions.
AI application deployment cloud
DGX Cloud Lepton
Turning Python model code into a Photon service, deploying a Photon or container as a GPU endpoint, and operating bounded AI jobs and inference workloads in a managed workspace.
Realtime voice agent platform
LiveKit
Building low-latency voice assistants, multimodal room participants, phone agents, realtime translation, tool-using conversational workflows, and human handoffs.
Data framework for AI
LlamaIndex
Loading and indexing private data, building source-grounded retrieval applications, composing workflows and agents, and evaluating retrieval and response quality.
Local model runtime
LM Studio
Running supported open models locally, comparing model configurations, chatting with private local data, and providing local application APIs.
Open-source AI workspace
LobeHub
Using multiple AI providers in one workspace, building reusable assistants with files and knowledge, and operating a private multi-user LobeChat service with controlled extensions.
AI app builder
Lovable
Turning a product brief or interface reference into a working web application, iterating visually, connecting a backend, and synchronizing editable code to GitHub.
Generative video
Dream Machine
Developing images and short video shots, controlling transitions with keyframes, and transforming existing footage while preserving motion.
Visual AI automation
Make
Building visual automations and bounded AI agents that combine triggers, structured scenarios, knowledge, and tools across business applications.
Autonomous AI agent
Manus
Delegating multi-step research, analysis, file creation, browser work, and small application or website builds.
TypeScript agents and workflows
Mastra
Building TypeScript agents for open-ended tasks and typed, resumable workflows for controlled multistep processes, with shared memory, tracing, and evaluation.
Generative 3D platform
Meshy
Rapidly prototyping 3D props and characters, converting concept images into meshes, generating textures, and preparing draft assets for games, visualization, AR, or further artist refinement.
Personal AI assistant
Meta AI
Conversational research, recommendations, drafting, voice assistance, and image creation inside the Meta products people already use.
Visual generation
Midjourney
Exploring visual directions, generating art direction references, and iterating on image or video concepts from a clear creative brief.
Mistral AI agent
Vibe by Mistral AI
Multilingual assistance, structured research, project-based knowledge work, custom agents, connected tools, and coding tasks.
Open model and dataset ecosystem
ModelScope
Discovering, evaluating, downloading, training, and publishing open models and datasets, or deploying controlled Studio and MCP projects through one AI asset hub.
Multi-model AI assistant
Monica
Summarizing webpages and documents, comparing model responses, drafting and rewriting text, researching with references, and accessing an assistant across devices.
Workflow automation
n8n
Connecting APIs and applications, building event-driven automations, orchestrating AI steps and tools, and retaining detailed control over workflow data and execution.
AI cloud and model platform
Nebius AI
Evaluating and serving open models through managed APIs or dedicated endpoints, and running controlled training and inference workloads on GPU VMs, containers, or Kubernetes.
Source-grounded research
NotebookLM
Building a focused knowledge space from PDFs, websites, videos, audio, and workspace files, then asking grounded questions or producing cited study and briefing materials.
Workspace AI
Notion AI
Working with AI in the same workspace as notes, pages, team documentation, and structured project information.
AI storytelling and illustration
NovelAI
Developing fiction with controlled context, memory and lorebooks; exploring story branches; generating anime-inspired concept art; and maintaining private, exportable creative projects.
Multimodal model and GPU APIs
Novita AI
Adding language, image, audio, or asynchronous video generation to applications, or deploying custom containers and models on dedicated or autoscaling GPU endpoints.
Local model runtime
Ollama
Running supported language and multimodal models locally, experimenting through a terminal, powering local applications through an API, and connecting compatible coding tools.
Multimodal developer API platform
OpenAI API Platform
Building production text, vision, audio, realtime, image, video, retrieval, and tool-using applications through managed models and platform APIs.
Provider-flexible coding agent
OpenCode
Using plan, build, exploration, and custom agents across repositories while controlling models, commands, edits, external directories, web access, skills, and subagents.
Autonomous software development
OpenHands
Delegating bounded repository tasks to an agent that can inspect code, edit files, run commands, and test changes inside a controlled execution environment.
Multi-model API router
OpenRouter
Comparing and calling many AI models through one interface, aggregating billing, and routing across providers for availability, cost, performance, or privacy.
Self-hosted AI interface
Open WebUI
Giving individuals or teams one controlled interface for multiple local or hosted models, reusable prompts, tools, and document knowledge bases.
Answer engine
Perplexity
Fast, source-oriented research, comparison work, and turning an open question into a brief you can check.
Agent platform and runtime
Agno
Building Python agents, specialist teams, and deterministic workflows, then serving and managing them through AgentOS with sessions, memory, knowledge, tracing, evaluation, RBAC, and approvals.
Personal conversational AI
Pi
Reflective conversation, brainstorming, goal clarification, rehearsal, and low-stakes personal organization in a warm conversational format.
Generative video
Pika
Creating short social videos from text, images, or footage; directing transitions with Pikaframes; and experimenting with Pika's visual effects and AI Selves.
AI video creation platform
PixVerse
Producing short stylized videos, character-consistent clips, image animation, effects-driven social concepts, and audio or lip-sync drafts through creator and API workflows.
Multi-model AI platform
Poe
Trying multiple AI models in one interface, comparing responses, and creating focused prompt bots, API bots, or Canvas apps.
Typed Python agent framework
Pydantic AI
Building Python agents with strongly typed inputs, dependencies, tools, and outputs, then evaluating and running them with explicit token, request, tool, concurrency, and durability controls.
Agentic coding workspace
Qoder
Delegating spec-driven development in isolated worktrees, reviewing autonomous changes, and using repository knowledge or expert agents for complex engineering tasks.
Multimodal assistant
Qwen
Multilingual assistance, web research, mixed-file analysis, coding, and experimenting with Qwen's open model family.
AI design platform
Recraft
Creating art-directed brand visuals, illustrations, icons, scalable vector assets, mockups, and controlled image variations inside a design-oriented workflow.
Hosted model APIs
Replicate
Testing public generative models, integrating versioned predictions, running asynchronous media jobs, and deploying custom model versions.
Cloud app builder
Replit
Planning, building, previewing, and publishing web or mobile applications from a brief while retaining access to the generated project and development environment.
Mode-based coding agent
Roo Code
Planning, implementing, debugging, and explaining repository changes with specialized modes and visible approval of file, command, browser, and MCP actions.
Generative video
Runway
Developing image-to-video and text-to-video shots, iterating motion and camera direction, and organizing generative video work into creative sessions.
Enterprise AI inference
SambaNova Cloud
Testing and integrating high-throughput hosted language models through a familiar API surface, with enterprise deployment options through SambaStack.
Hosted multimodal model APIs
SiliconCloud
Testing and integrating hosted open models for chat, embeddings, reranking, image, audio, and video workloads through a common API surface.
Generative media platform
Stability AI
Building applications that generate, edit, upscale, control, and transform images through Stable Image services and related Stability AI models.
Music generation
Suno
Exploring song concepts, generating musical directions from a brief, developing lyrics and arrangements, and producing draft tracks for creative review.
Search and web retrieval
Tavily
Giving AI applications current web search, clean page extraction, selective site crawling, URL mapping, and asynchronous research capabilities.
Open-model AI cloud
Together AI
Comparing and serving open models through serverless inference, dedicated endpoints, evaluations, fine-tuning, and managed GPU infrastructure.
AI media enhancement suite
Topaz Labs
Restoring and enhancing existing photos and footage, reducing noise, recovering detail, increasing resolution, stabilizing motion, interpolating frames, and preparing media for delivery.
AI-native development environment
TRAE
Building and modifying applications through an AI-native editor while keeping project context, generated plans, agent actions, and visual previews in one workspace.
Music generation
Udio
Exploring song ideas, extending arrangements, remixing owned material, and directing new music with authorized style references.
Language and document AI platform
Upstage
Building language and document automation with Solar models, structured generation, document digitization, information extraction, classification, semantic retrieval, and agent APIs.
AI web app builder
v0
Turning product ideas, screenshots, and requirements into responsive web interfaces and incremental full-stack applications.
AI raster-to-vector service
Vectorizer.AI
Converting logos, illustrations, scans, icons, artwork, and other bitmap assets into editable or scalable vector paths through a browser or repeatable production pipeline.
Cloud generative AI platform
Vertex AI
Building and operating production generative AI and ML systems with Gemini and Model Garden models, grounding, RAG, evaluation, tuning, agents, and Google Cloud controls.
Reference-driven AI video
Vidu
Creating short videos with reusable characters, products, props, scenes, or styles and maintaining visual continuity across reference-driven shots.
AI character motion platform
Viggle
Animating a still character from reference motion, replacing characters in existing movement, creating short dance or performance clips, and prototyping real-time character overlays.
High-throughput model serving
vLLM
Serving open and custom language, embedding, reranking, transcription, and related models at high throughput through familiar APIs on controlled GPU infrastructure.
Retrieval embeddings and reranking
Voyage AI
Creating high-quality text or multimodal embeddings and reranking candidate results for semantic search, RAG, code search, and domain-specific retrieval.
Agentic code editor
Windsurf
Understanding codebases, planning and implementing repository changes with Cascade, and preserving team conventions through project rules.
Serverless AI inference
Cloudflare Workers AI
Running open-source text, embedding, image, speech, and classification models in serverless Workers and combining them with AI Gateway and Vectorize.
Multimodal model API platform
xAI API
Building Grok-powered text, coding, reasoning, multimodal, media, realtime voice, retrieval, and tool-using applications through production APIs.
Local and distributed model serving
Xinference
Running and managing multiple open or custom model types behind local or cluster APIs with model lifecycle, resource, authentication, permission, audit, and monitoring controls.
AI automation
Zapier
Automating trigger-and-action workflows, connecting AI to business applications, creating agents, transforming data, and reducing repetitive operational work.
AI-powered cloud deployment
Zeabur
Using plain language to configure application deployments and accessing multiple model providers through a single OpenAI-compatible API and usage ledger.
Codebase-aware coding agents
Zencoder
Completing multi-file coding tasks with repository context, validation tools, specialized agents, and controlled search across approved codebases.
No published collection matches that search.
Research index
Every tool on our radar.
Colored, linked entries are published. The remaining marks are the research queue; they will become clickable only when their guides are genuinely useful.