dev101.io

AI & LLM Tools

Curated directory of LLM providers, agent frameworks, and self-hostable AI tools — with links straight to the source.

42 curated links across 9 sections

Everything we reach for when building AI-powered features. If you're wiring up an LLM, running inference locally, or stitching agents together into workflows, start here. Each link goes straight to the provider — no affiliate tracking, no wrapper sites.

Frontier LLM providers

Hosted APIs with state-of-the-art models.

  • OpenAI
    FeaturedPaid

    GPT-5, GPT-4.1, o-series reasoning models. Responses API is the stateful default; chat/completions still works.

    LLM providerAPI
  • Anthropic
    FeaturedPaid

    Claude Sonnet, Opus, Haiku. Strong at long context, tool use, and following complex instructions.

    LLM providerAPI
  • Google AI Studio
    Freemium

    Gemini Pro / Flash / Nano with huge context windows and native multimodal input. Free tier is generous.

    LLM providermultimodal
  • xAI
    Paid

    Grok models via Twitter-adjacent API. Competitive reasoning and real-time web grounding.

    LLM provider
  • Mistral
    Freemium

    Open-weight and hosted models out of Paris. Strong European option with EU data residency.

    LLM provideropen-weight
  • Cohere
    Paid

    Command R / R+ models optimized for RAG and enterprise workloads. Strong rerank + embed endpoints.

    LLM providerRAG

Fast inference & open models

Cheap, fast hosted inference for Llama, Mistral, DeepSeek, and friends.

  • Groq
    FeaturedFreemium

    LPU inference — hundreds of tokens/sec for Llama, Mixtral, Qwen. Ridiculous latency ceilings.

    inferencelow-latency
  • Together AI
    Paid

    Hosts 100+ open models with OpenAI-compatible APIs. Great for switching providers without rewriting code.

    inferenceopen models
  • Fireworks AI
    Paid

    Fast serverless inference for open-weight models with fine-tuning support.

    inferencefine-tuning
  • Replicate
    Paid

    Run any open-source model behind an HTTP API. Great for vision / audio / niche models.

    inferencemulti-modal
  • Hugging Face
    FeaturedFreemium

    The open-source model hub. Datasets, weights, Spaces, Inference Endpoints — the whole ecosystem.

    model hubdatasets
  • DeepInfra
    Paid

    Pay-per-token OpenAI-compatible API for open models. Aggressive pricing.

    inference

Router & gateway

One API key to try many models, or smart routing across providers.

  • OpenRouter
    FeaturedFreemium

    Unified API for 300+ models across every major provider. Budget caps, fallback routing, BYO keys.

    gatewaymulti-provider
  • Portkey
    Freemium

    Observability + guardrails + routing layer for production LLM apps. 50+ providers.

    gatewayobservability
  • Helicone
    Freemium

    Open-source LLM observability. Proxies requests and captures logs, cost, latency.

    observabilityopen-source

Run LLMs locally

Inference on your own laptop or server. No cloud, no data leaving the box.

  • Ollama
    FeaturedOpen-source

    One-command local LLM runtime. `ollama run llama3.2` and you're off. REST API baked in.

    localCLI
  • LM Studio
    Free

    Desktop app for chatting with local models. Great for non-technical users.

    localdesktop
  • llama.cpp
    Open-source

    The CPU/GPU inference engine that started the local-LLM revolution. Powers most of the stack.

    localinference engine
  • vLLM
    Open-source

    High-throughput batched inference for serving open-weight models in production.

    inference engineserving

Agent & orchestration frameworks

Libraries for building multi-step AI applications — chains, tools, memory, routers.

  • LangChain
    FeaturedOpen-source

    The most widely-used framework for chaining LLM calls, tools, and retrievers. TS + Python.

    frameworkagents
  • LangGraph
    Open-source

    State-machine-style agent framework from the LangChain team. Durable workflows + checkpointing.

    agentsworkflow
  • LlamaIndex
    Open-source

    Data framework optimized for RAG — indexing, retrieval, query engines. TS + Python.

    RAGframework
  • Vercel AI SDK
    FeaturedOpen-source

    TypeScript SDK for streaming chat UIs on Next.js / React / Svelte. Provider-agnostic.

    TypeScriptUI
  • Mastra
    Open-source

    TypeScript-first agent framework with memory, tools, workflows, and eval built in.

    TypeScriptagents
  • CrewAI
    Freemium

    Multi-agent framework organized around role-based crews. Popular in the no-code adjacent space.

    agentsmulti-agent

Workflow & automation builders

Visual canvases for stitching AI steps, APIs, and triggers into workflows.

  • n8n
    FeaturedFreemium

    Self-hostable workflow automation with 400+ integrations and native LLM nodes. The go-to Zapier alternative.

    workflowself-hosted
  • Flowise
    Open-source

    Drag-and-drop UI for LangChain flows. Self-hostable, open-source, great for prototyping agents.

    visualself-hosted
  • Langflow
    Open-source

    Visual authoring for LangChain pipelines. Big community, plays well with LangGraph.

    visualopen-source
  • Zapier
    Freemium

    The canonical no-code automation platform. AI actions across 7000+ apps.

    workflowno-code

Self-hostable chat UIs

Run your own ChatGPT. Point at any OpenAI-compatible endpoint and you're ready.

  • LibreChat
    FeaturedOpen-source

    Open-source chat UI supporting OpenAI, Anthropic, Gemini, Bedrock, and local providers. Active community.

    chat UIself-hosted
  • OpenWebUI
    Open-source

    Polished WebUI built for Ollama + any OpenAI-compatible API. One of the cleanest self-hosted options.

    chat UIself-hosted
  • AnythingLLM
    Open-source

    Desktop + Docker app that turns documents into a private RAG-powered workspace.

    RAGdesktop
  • Typingmind
    Paid

    Polished chat UI that lives in your browser, keys stay local. Supports every major provider.

    chat UIBYO key

Evals, observability, guardrails

Measure, monitor, and control your LLM apps in production.

  • Langfuse
    FeaturedFreemium

    Open-source LLM observability + evals + prompt management. Self-hostable and cloud.

    observabilityopen-source
  • LangSmith
    Freemium

    LangChain's commercial observability + eval platform. Tight LangChain / LangGraph integration.

    observabilityevals
  • Braintrust
    Paid

    Production-grade eval platform for shipping LLM features safely. Dataset + experiment tracking.

    evals
  • Promptfoo
    Open-source

    CLI + YAML for running prompt / red-team tests. Great in CI.

    evalsCLI

Vector databases & RAG stores

Where your embeddings live.

  • Pinecone
    Freemium

    Managed vector DB with the most mature enterprise feature set. Serverless tier is cheap.

    vector DB
  • Qdrant
    Open-source

    Open-source Rust vector DB. Self-hostable or managed cloud. Great filtering story.

    vector DBopen-source
  • Weaviate
    Open-source

    Open-source vector DB with hybrid search and module-based embedders. Good GraphQL API.

    vector DBopen-source
  • pgvector
    FeaturedOpen-source

    Vector similarity search for Postgres. If you already have Postgres, start here.

    Postgresextension
  • Turbopuffer
    Paid

    Serverless vector + full-text search built on object storage. Cheap at scale.

    vector DBserverless

Other resource directories

Links on this page point to third-party sites. We pick them on merit — no affiliate tracking, no paid placements. Spot something outdated or missing? Open an issue.