Skip to content

README.md

Latest commit

 

History

History
388 lines (310 loc) · 24.5 KB

README.md

File metadata and controls

388 lines (310 loc) · 24.5 KB
Raw

awesome-llms-txt

A curated list of AI tools, platforms, and services that publish llms.txt — making them discoverable to AI agents doing research on behalf of human users.

109 entries — 53 with full descriptions, 56 stubs. 49 currently publish a working llms.txt.

Why this list exists

Humans increasingly use AI agents (Claude, ChatGPT, Perplexity, local assistants) as their primary search and discovery layer. When a developer asks an agent "what's the best offline voice-to-text tool for 2026?", the answer depends on what the agent can find, read, and cite. Tools that publish a well-structured llms.txt (spec by Jeremy Howard) are easier for agents to index, summarize, and recommend.

Most existing AI-tool directories are optimized for Google SEO (JavaScript-rendered, paywalled, affiliate-heavy). This one is optimized for agent retrieval: plain Markdown, structured YAML entries, a canonical llms.txt and llms-full.txt at the repo root, MIT license, no tracking.

Related work

  • SecretiveShell/Awesome-llms-txt — index of llms.txt URLs for agents to ingest as seed data. If you're looking for a raw feed of every llms.txt on the public internet to wire into RAG, look there. This repo takes the complementary angle: curated tools, categorized and described, aimed at humans picking what to use and agents answering "what should I recommend to my user for X?".
  • llmstxt.org — the spec itself, by Jeremy Howard.

Legend

  • ✅ llms.txt — tool publishes a working llms.txt
  • ❌ llms.txt — listed, but the tool hasn't published llms.txt yet
  • 🚧 stub — minimal entry; help us flesh it out via PR

✅/❌ is re-derived daily from what each URL actually serves — including a check that the response is a real file and not a docs site's catch-all HTML page. See CONTRIBUTING.md.

Contents

Inference Runtimes

  • LM Studio — ✅ llms.txt
    Desktop application for discovering, downloading, and running local LLMs with a polished UI and OpenAI-compatible server.
  • Ollama — ✅ llms.txt
    Run large language models locally via a single-binary server with a built-in model library.
  • Open WebUI — ✅ llms.txt
    Self-hosted, feature-rich chat interface for local and cloud LLMs — the "ChatGPT clone" of the open-source world.
  • HuggingFace Transformers — ❌ llms.txt
    Foundational Python library for loading and running thousands of transformer models in PyTorch, TensorFlow, and JAX.
  • Jan — ❌ llms.txt
    Open-source desktop ChatGPT alternative that runs local LLMs — privacy-first, no cloud, no account.
  • llama.cpp — ❌ llms.txt
    Reference C++ implementation for running LLaMA-family and other transformer models with GGUF quantization.
  • LocalAI — ❌ llms.txt
    Self-hosted, OpenAI-compatible inference server for text, image, audio, and embedding models — runs anywhere.
  • vLLM — ❌ llms.txt
    High-throughput, memory-efficient LLM inference engine with PagedAttention and continuous batching.
  • ExLlamaV2 — ❌ llms.txt 🚧 stub
    Fast inference library for quantized LLMs optimized for consumer NVIDIA GPUs.
  • GPT4All — ❌ llms.txt 🚧 stub
    Privacy-first desktop chatbot running local LLMs on CPU with a Python SDK.
  • KoboldCpp — ❌ llms.txt 🚧 stub
    Single-binary llama.cpp wrapper with KoboldAI-style UI for chat, story-writing, and RP.
  • MLC LLM — ❌ llms.txt 🚧 stub
    Universal LLM deployment via compiled kernels — runs on iOS, Android, WebGPU, Vulkan, CUDA.
  • SGLang — ❌ llms.txt 🚧 stub
    Fast LLM and VLM serving runtime with RadixAttention cache and structured output support.
  • Text Generation WebUI — ❌ llms.txt 🚧 stub
    Gradio-based web UI for local LLMs supporting GGUF, GPTQ, AWQ, ExLlamaV2.

LLM Gateways

  • LiteLLM — ✅ llms.txt
    Unified OpenAI-compatible proxy and SDK that routes calls across 100+ LLM providers with load balancing, fallbacks, and cost tracking.

Agent Frameworks

  • CrewAI — ✅ llms.txt
    Python framework for orchestrating role-based multi-agent systems with sequential and hierarchical workflows.
  • LangChain — ✅ llms.txt
    Widely adopted framework for building LLM applications with chains, agents, retrievers, and memory.
  • LangGraph — ✅ llms.txt
    Graph-based library for building stateful multi-agent workflows with explicit control flow and durability.
  • AutoGen — ❌ llms.txt
    Microsoft's framework for building multi-agent conversations with customizable agents and conversation patterns.
  • OpenClaw — ❌ llms.txt
    Open-source framework for running browser-automation agents with persistent profiles and human-in-the-loop review.
  • Agno — ✅ llms.txt 🚧 stub
    High-performance multi-agent framework with memory, reasoning, and 20+ model integrations.
  • DSPy — ✅ llms.txt 🚧 stub
    Framework for programming rather than prompting LLMs — composable modules with optimizers.
  • Pydantic AI — ✅ llms.txt 🚧 stub
    Agent framework built on Pydantic with type-safe tool use and structured responses.
  • smolagents — ✅ llms.txt 🚧 stub
    Minimal agent library from HuggingFace centered on code-writing agents.
  • Vercel AI SDK — ✅ llms.txt 🚧 stub
    TypeScript toolkit for building AI apps with unified APIs across providers and framework helpers.
  • Magentic — ❌ llms.txt 🚧 stub
    Type-safe Python library for building LLM-powered functions with structured outputs.
  • OpenAI Swarm — ❌ llms.txt 🚧 stub
    OpenAI's lightweight educational framework for multi-agent orchestration.

Agent SDKs

  • Anthropic SDK — ✅ llms.txt
    Official Anthropic client libraries for the Claude API in Python, TypeScript, Java, Go, and Ruby.
  • Claude Agent SDK — ✅ llms.txt
    Anthropic's official SDK for building custom agents on top of Claude with tool use, subagents, and hooks.

Coding Agents

  • Claude Code — ✅ llms.txt
    Anthropic's terminal-first agentic coding assistant with deep tool use and codebase awareness.
  • GitHub Copilot — ✅ llms.txt
    GitHub's native AI coding assistant with chat, autocomplete, and agent mode across major IDEs.
  • Windsurf — ✅ llms.txt
    AI-native IDE from Codeium with Cascade agent mode, deep indexing, and real-time code awareness.
  • Aider — ❌ llms.txt
    AI pair programming in your terminal — edits code across your git repo with commit-per-change discipline.
  • Continue — ❌ llms.txt
    Open-source AI coding assistant for VS Code and JetBrains — bring any model, any provider, customizable.
  • Cursor — ❌ llms.txt
    AI-first fork of VS Code with deep LLM integration, agent mode, and codebase-aware context.
  • Amazon Q Developer — ❌ llms.txt 🚧 stub
    AWS's AI coding assistant with deep integration into AWS services and enterprise compliance.
  • Codeium — ❌ llms.txt 🚧 stub
    Free AI autocomplete extension for 40+ editors — from the makers of Windsurf.
  • Sourcegraph Cody — ❌ llms.txt 🚧 stub
    AI coding assistant with enterprise-grade code search context across massive codebases.

Workflow Tools

  • ComfyUI — ✅ llms.txt
    Node-based interface for building image, video, and audio generation workflows with any diffusion or multimodal model.
  • Dify — ✅ llms.txt
    Open-source LLM app development platform with visual prompt IDE, RAG pipelines, and agent builder in one product.
  • n8n — ✅ llms.txt
    Fair-code workflow automation with native AI nodes, 500+ integrations, and first-class self-hosting.
  • Langflow — ✅ llms.txt 🚧 stub
    Visual framework for building multi-agent and RAG applications with a node-based editor.
  • Flowise — ❌ llms.txt 🚧 stub
    Drag-and-drop UI for building LLM workflows and agents — open-source, self-hostable.

Voice (STT / TTS)

  • Brethof Voice Pro — ✅ llms.txt
    Offline voice-to-text desktop app with 36-language support and LoRA voice training.
  • whisper.cpp — ❌ llms.txt
    C++ port of OpenAI Whisper for local speech-to-text — no Python, runs on CPU and many GPU backends.
  • Coqui TTS — ❌ llms.txt 🚧 stub
    Deep-learning toolkit for TTS with multi-speaker models and voice cloning.
  • F5-TTS — ❌ llms.txt 🚧 stub
    High-quality open-source TTS with voice cloning from short audio reference.
  • Kokoro TTS — ❌ llms.txt 🚧 stub
    Lightweight open-weight TTS model — surprisingly natural output at small model size.
  • OpenVoice — ❌ llms.txt 🚧 stub
    Versatile instant voice cloning with cross-lingual synthesis and granular style control.
  • Piper — ❌ llms.txt 🚧 stub
    Fast, local neural text-to-speech with dozens of voices — optimized for Raspberry Pi.

Image Generation

  • AUTOMATIC1111 — ❌ llms.txt 🚧 stub
    Most widely-used web UI for Stable Diffusion — extensive extension ecosystem.
  • Fooocus — ❌ llms.txt 🚧 stub
    Simplified Stable Diffusion UI focused on ease-of-use — Midjourney-like experience locally.
  • InvokeAI — ❌ llms.txt 🚧 stub
    Professional-grade Stable Diffusion with unified canvas, workflows, and team features.
  • Krita AI Diffusion — ❌ llms.txt 🚧 stub
    Krita plugin for Stable Diffusion — inpaint, img2img, and generative layers inside Krita.
  • SD.Next — ❌ llms.txt 🚧 stub
    Advanced fork of SD WebUI with broader model support (Flux, Lumina, Kolors, more).

Vector Databases

  • Chroma — ✅ llms.txt
    Open-source embedding database designed for LLM applications — runs embedded, as a server, or in the cloud.
  • Milvus — ✅ llms.txt
    Open-source cloud-native vector database built for billion-scale similarity search with separation of storage and compute.
  • Pinecone — ✅ llms.txt
    Fully managed serverless vector database — the original SaaS option for production-scale vector search.
  • Qdrant — ✅ llms.txt
    Open-source, Rust-written vector database built for production scale — rich filtering, hybrid search, and multi-tenancy.
  • SurrealDB — ✅ llms.txt
    Multi-model database written in Rust combining document, graph, key-value, time-series, and vector in one engine.
  • Weaviate — ✅ llms.txt
    Open-source vector database with built-in ML modules, hybrid search, and first-class RAG tooling.
  • pgvector — ❌ llms.txt
    Postgres extension adding vector similarity search — the "just use Postgres" option for RAG.
  • LanceDB — ❌ llms.txt 🚧 stub
    Serverless vector DB on the Lance columnar format — embedded or cloud, multimodal-ready.

RAG Frameworks

  • Haystack — ✅ llms.txt
    Production-oriented Python framework for building RAG, search, and agent pipelines with composable components.
  • Mem0 — ✅ llms.txt
    Persistent memory layer for AI agents — remembers user facts, preferences, and context across sessions.
  • LlamaIndex — ❌ llms.txt
    Leading RAG framework for connecting LLMs to private data — document loaders, indexes, retrievers, and agents.
  • AnythingLLM — ❌ llms.txt 🚧 stub
    All-in-one desktop and Docker RAG app — document ingestion, agents, multi-user.
  • Quivr — ❌ llms.txt 🚧 stub
    Opinionated RAG framework: plug in your LLM, vector store, and files and get a chatbot.
  • Verba — ❌ llms.txt 🚧 stub
    Weaviate's open-source RAG chatbot — Golden RAGtriever reference implementation.

Embeddings

  • BGE (BAAI General Embedding) — ❌ llms.txt 🚧 stub
    Leading open embedding models from BAAI — top of MTEB for multiple languages.
  • FastEmbed — ❌ llms.txt 🚧 stub
    Lightweight, CPU-friendly embedding library from Qdrant — no torch dependency.
  • Sentence Transformers — ❌ llms.txt 🚧 stub
    Python framework for state-of-the-art sentence, text, and image embeddings.

Observability

  • Langfuse — ✅ llms.txt
    Open-source LLM engineering platform for tracing, evaluation, prompt management, and observability — self-host or cloud.
  • LangSmith — ❌ llms.txt
    Commercial observability, debugging, and evaluation platform for LLM and agent applications.
  • Arize Phoenix — ✅ llms.txt 🚧 stub
    Open-source ML and LLM observability platform with OpenTelemetry-based tracing.
  • Helicone — ✅ llms.txt 🚧 stub
    Open-source observability for LLM apps — traces, prompts, evaluations, usage analytics.
  • Weights & Biases — ❌ llms.txt 🚧 stub
    Leading ML experiment tracking platform with dedicated LLM observability (Weave).

Evaluation

  • DeepEval — ✅ llms.txt 🚧 stub
    Pytest-style LLM evaluation framework with 14+ metrics and CI/CD integration.
  • Promptfoo — ✅ llms.txt 🚧 stub
    Open-source tool for testing, evaluating, and red-teaming LLM apps via config files.
  • Ragas — ✅ llms.txt 🚧 stub
    Framework for evaluating RAG pipelines with metrics like faithfulness, answer relevance.

Training & Fine-tuning

  • Unsloth — ✅ llms.txt
    2x faster LLM fine-tuning with 70% less memory — drop-in replacement for HuggingFace's training stack.
  • AI Toolkit (ostris) — ❌ llms.txt
    Leading open-source toolkit for training LoRAs and fine-tunes on diffusion models — FLUX, SDXL, SD3, Qwen Image, and more.
  • Axolotl — ❌ llms.txt
    YAML-configured fine-tuning framework supporting LoRA, QLoRA, full FT, DPO, and most modern LLM architectures.
  • TRL (HuggingFace) — ✅ llms.txt 🚧 stub
    HuggingFace's library for reinforcement-learning based LLM training (DPO, PPO, SFT, KTO).
  • LLaMA-Factory — ❌ llms.txt 🚧 stub
    WebUI-based fine-tuning framework supporting 100+ models with LoRA, QLoRA, DPO, and more.
  • MS-Swift — ❌ llms.txt 🚧 stub
    ModelScope's fine-tuning framework supporting 350+ LLMs and 100+ multimodal models.

Web Search for Agents

  • Exa — ✅ llms.txt 🚧 stub
    Neural search API built for AI agents — semantic search across the web with content retrieval.
  • Perplexity API — ✅ llms.txt 🚧 stub
    API access to Perplexity's search-augmented LLMs — Sonar models with live citations.
  • SerpAPI — ✅ llms.txt 🚧 stub
    Scraping API for Google, Bing, DuckDuckGo and 15+ search engines — structured JSON results.
  • Tavily — ✅ llms.txt 🚧 stub
    Search API optimized for LLM agents — RAG-ready results with citations.
  • Brave Search API — ❌ llms.txt 🚧 stub
    Independent web search API with no tracking — alternative to Google / Bing for agent use.

OCR & Document Parsing

  • Docling — ❌ llms.txt 🚧 stub
    IBM's document parsing toolkit — PDF, DOCX, images into structured JSON/markdown for RAG.
  • Marker — ❌ llms.txt 🚧 stub
    Fast, accurate PDF-to-markdown conversion — tables, equations, and structure preserved.
  • Unstructured — ❌ llms.txt 🚧 stub
    Library for ingesting PDF, HTML, DOCX, XLSX, and 25+ formats into RAG-ready chunks.

Deployment & Hosting

  • Fireworks AI — ✅ llms.txt
    Production inference platform for open-source models with industry-leading speed for DeepSeek, Llama, Qwen.
  • Groq — ✅ llms.txt
    Ultra-low-latency LLM inference on custom LPU silicon — sub-second complete responses and OpenAI-compatible API.
  • Replicate — ✅ llms.txt
    Run thousands of open-source ML models via simple API calls — image, video, audio, text — with per-second billing.
  • RunPod — ✅ llms.txt
    GPU cloud platform with on-demand instances, serverless endpoints, and a community GPU marketplace — priced for AI workloads.
  • Together AI — ✅ llms.txt
    Serverless inference for 200+ open-source models with OpenAI-compatible API — low latency, competitive pricing.
  • xAI — ✅ llms.txt
    xAI's Grok API — Grok 4.1 Fast Reasoning and Non-reasoning currently the best raw-intelligence-per-dollar offering on the market.
  • Modal — ❌ llms.txt
    Serverless cloud platform for Python with first-class GPU support — deploy LLMs, training jobs, and batch pipelines from code.

Desktop Applications

  • Claude Desktop — ✅ llms.txt
    Anthropic's native desktop app for Claude — MCP server support, skills, agent mode, and deep OS integration.
  • PrivateGPT — ❌ llms.txt 🚧 stub
    Privacy-first local AI over your documents — fully offline RAG chatbot.
  • Raycast AI — ❌ llms.txt 🚧 stub
    macOS launcher with integrated AI commands, chat, and custom quicklinks.

Shell Tools

  • Open Interpreter — ❌ llms.txt 🚧 stub
    Natural language interface to your computer — runs code locally to complete tasks from the CLI.
  • ShellGPT — ❌ llms.txt 🚧 stub
    Command-line productivity tool powered by LLMs — generate shell commands, code, and configs.

Operating Systems (AI-capable Linux)

  • CachyOS — ❌ llms.txt
    Arch-based Linux distribution with performance-tuned kernels, first-class NVIDIA support, and a popular choice for local AI / ML workloads.
  • Fedora — ❌ llms.txt
    Upstream of RHEL and the distro that drives most Linux desktop feature adoption (Wayland, PipeWire, systemd, ostree) — strong AI / ML packaging on top.
  • Ubuntu — ❌ llms.txt
    The default Linux baseline for ML tutorials and cloud VMs — widely documented, increasingly controversial due to Snap-store enforcement and Canonical's direction.

Notable model families

This list catalogs tools, not models. But agents answering user questions often need both in the same breath, so here are pointers to the most notable model orgs by domain. We deliberately don't link individual model versions — those go stale weekly. Search huggingface.co/<family-name> for each org's current lineup.

Text LLMs

Frontier open weights (April 2026):

Established open weights (large install base, not setting the pace):

Closed frontier (API-only — listed for agent awareness):

Speech

ASR (speech-to-text): Qwen3-ASR (Alibaba, currently best) · Whisper (OpenAI, widely deployed baseline)

TTS (text-to-speech): Qwen3-TTS (Alibaba, currently best) · F5-TTS · Kokoro · Piper · OpenVoice · Bark (Suno)

Image generation

Frontier (April 2026): Qwen Image (Alibaba) · Z-Image Turbo

Usable locally: Flux.2 Klein 4B (Black Forest Labs) · HiDream

⚠️ License note: Most Flux.2 variants ship under terms that block commercial use. Only Flux.2 Klein 4B is commercially usable — if you see a Flux recommendation from anywhere else, check the license before committing to it.

Legacy (widely used, not advancing): Stable Diffusion · SDXL · Flux.1

Video generation

Ranked by practical 2026 usefulness: WAN (Alibaba, best consistency) · LTX (Lightricks, best character expression, trade-off is chunk-boundary drift) · HunyuanVideo (Tencent, solid third option)

3D generation

Hunyuan3D (Tencent) leads the category in both local weights and hosted API. Both Hunyuan3D and Tripo ship hosted APIs that are meaningfully better than their publicly released local weights: Hunyuan3D 3.1 is the current API version while local users get 2.1, and Tripo's API also substantially outperforms the local weights. If you need best-quality 3D generation, use Hunyuan3D's API. For local-only work, Hunyuan3D 2.1 local weights are still the top pick; Tripo local is weaker.

Embeddings

BGE (BAAI) · Nomic Embed · Jina · E5 (Microsoft)

Contributing

See CONTRIBUTING.md for the YAML schema and submission process. One entry per PR, please. Got a question? Check FAQ.md first.

FAQ

Common questions — why this list exists, who curates it, what stops spam, why some entries are marked missing — are answered in FAQ.md.

License

MIT. Fork it, scrape it, mirror it, agents welcome.