awesome-llms-txt

# awesome-llms-txt

> Curated list of AI tools discoverable to agents via llms.txt. MIT-licensed. Source: https://github.com/brethofai/awesome-llms-txt

## Inference Runtimes

- [LM Studio](https://lmstudio.ai): Desktop application for discovering, downloading, and running local LLMs with a polished UI and OpenAI-compatible server. ✓
  - llms.txt: https://lmstudio.ai/llms.txt
- [Ollama](https://ollama.com): Run large language models locally via a single-binary server with a built-in model library. ✓
  - llms.txt: https://ollama.com/llms.txt
- [Open WebUI](https://openwebui.com): Self-hosted, feature-rich chat interface for local and cloud LLMs — the "ChatGPT clone" of the open-source world. ✓
  - llms.txt: https://docs.openwebui.com/llms.txt
- [HuggingFace Transformers](https://huggingface.co/docs/transformers): Foundational Python library for loading and running thousands of transformer models in PyTorch, TensorFlow, and JAX. ✗
- [Jan](https://jan.ai): Open-source desktop ChatGPT alternative that runs local LLMs — privacy-first, no cloud, no account. ✗
- [llama.cpp](https://github.com/ggml-org/llama.cpp): Reference C++ implementation for running LLaMA-family and other transformer models with GGUF quantization. ✗
- [LocalAI](https://localai.io): Self-hosted, OpenAI-compatible inference server for text, image, audio, and embedding models — runs anywhere. ✗
- [vLLM](https://docs.vllm.ai): High-throughput, memory-efficient LLM inference engine with PagedAttention and continuous batching. ✗
- [ExLlamaV2](https://github.com/turboderp-org/exllamav2): Fast inference library for quantized LLMs optimized for consumer NVIDIA GPUs. ✗
- [GPT4All](https://www.nomic.ai/gpt4all): Privacy-first desktop chatbot running local LLMs on CPU with a Python SDK. ✗
- [KoboldCpp](https://github.com/LostRuins/koboldcpp): Single-binary llama.cpp wrapper with KoboldAI-style UI for chat, story-writing, and RP. ✗
- [MLC LLM](https://llm.mlc.ai): Universal LLM deployment via compiled kernels — runs on iOS, Android, WebGPU, Vulkan, CUDA. ✗
- [SGLang](https://sgl-project.github.io): Fast LLM and VLM serving runtime with RadixAttention cache and structured output support. ✗
- [Text Generation WebUI](https://github.com/oobabooga/text-generation-webui): Gradio-based web UI for local LLMs supporting GGUF, GPTQ, AWQ, ExLlamaV2. ✗

## LLM Gateways

- [LiteLLM](https://www.litellm.ai): Unified OpenAI-compatible proxy and SDK that routes calls across 100+ LLM providers with load balancing, fallbacks, and cost tracking. ✓
  - llms.txt: https://docs.litellm.ai/llms.txt

## Agent Frameworks

- [CrewAI](https://www.crewai.com): Python framework for orchestrating role-based multi-agent systems with sequential and hierarchical workflows. ✓
  - llms.txt: https://docs.crewai.com/llms.txt
- [LangChain](https://www.langchain.com): Widely adopted framework for building LLM applications with chains, agents, retrievers, and memory. ✓
  - llms.txt: https://python.langchain.com/llms.txt
- [LangGraph](https://langchain-ai.github.io/langgraph/): Graph-based library for building stateful multi-agent workflows with explicit control flow and durability. ✓
  - llms.txt: https://langchain-ai.github.io/langgraph/llms.txt
- [AutoGen](https://microsoft.github.io/autogen/): Microsoft's framework for building multi-agent conversations with customizable agents and conversation patterns. ✗
- [OpenClaw](https://github.com/openclaw/openclaw): Open-source framework for running browser-automation agents with persistent profiles and human-in-the-loop review. ✗
- [Agno](https://docs.agno.com): High-performance multi-agent framework with memory, reasoning, and 20+ model integrations. ✓
  - llms.txt: https://docs.agno.com/llms.txt
- [DSPy](https://dspy.ai): Framework for programming rather than prompting LLMs — composable modules with optimizers. ✓
  - llms.txt: https://dspy.ai/llms.txt
- [Pydantic AI](https://ai.pydantic.dev): Agent framework built on Pydantic with type-safe tool use and structured responses. ✓
  - llms.txt: https://ai.pydantic.dev/llms.txt
- [smolagents](https://huggingface.co/docs/smolagents): Minimal agent library from HuggingFace centered on code-writing agents. ✓
  - llms.txt: https://huggingface.co/docs/smolagents/llms.txt
- [Vercel AI SDK](https://ai-sdk.dev): TypeScript toolkit for building AI apps with unified APIs across providers and framework helpers. ✓
  - llms.txt: https://ai-sdk.dev/llms.txt
- [Magentic](https://magentic.dev): Type-safe Python library for building LLM-powered functions with structured outputs. ✗
- [OpenAI Swarm](https://github.com/openai/swarm): OpenAI's lightweight educational framework for multi-agent orchestration. ✗

## Agent SDKs

- [Anthropic SDK](https://docs.claude.com/en/api/overview): Official Anthropic client libraries for the Claude API in Python, TypeScript, Java, Go, and Ruby. ✓
  - llms.txt: https://docs.claude.com/llms.txt
- [Claude Agent SDK](https://docs.claude.com/en/api/agent-sdk/overview): Anthropic's official SDK for building custom agents on top of Claude with tool use, subagents, and hooks. ✓
  - llms.txt: https://docs.claude.com/llms.txt

## Coding Agents

- [Claude Code](https://claude.com/claude-code): Anthropic's terminal-first agentic coding assistant with deep tool use and codebase awareness. ✓
  - llms.txt: https://docs.claude.com/llms.txt
- [GitHub Copilot](https://github.com/features/copilot): GitHub's native AI coding assistant with chat, autocomplete, and agent mode across major IDEs. ✓
  - llms.txt: https://docs.github.com/llms.txt
- [Windsurf](https://windsurf.com): AI-native IDE from Codeium with Cascade agent mode, deep indexing, and real-time code awareness. ✓
  - llms.txt: https://docs.windsurf.com/llms.txt
- [Aider](https://aider.chat): AI pair programming in your terminal — edits code across your git repo with commit-per-change discipline. ✗
- [Continue](https://www.continue.dev): Open-source AI coding assistant for VS Code and JetBrains — bring any model, any provider, customizable. ✗
- [Cursor](https://cursor.com): AI-first fork of VS Code with deep LLM integration, agent mode, and codebase-aware context. ✗
- [Amazon Q Developer](https://aws.amazon.com/q/developer/): AWS's AI coding assistant with deep integration into AWS services and enterprise compliance. ✗
- [Codeium](https://codeium.com): Free AI autocomplete extension for 40+ editors — from the makers of Windsurf. ✗
- [Sourcegraph Cody](https://sourcegraph.com/cody): AI coding assistant with enterprise-grade code search context across massive codebases. ✗

## Workflow Tools

- [ComfyUI](https://www.comfy.org): Node-based interface for building image, video, and audio generation workflows with any diffusion or multimodal model. ✓
  - llms.txt: https://docs.comfy.org/llms.txt
- [Dify](https://dify.ai): Open-source LLM app development platform with visual prompt IDE, RAG pipelines, and agent builder in one product. ✓
  - llms.txt: https://docs.dify.ai/llms.txt
- [n8n](https://n8n.io): Fair-code workflow automation with native AI nodes, 500+ integrations, and first-class self-hosting. ✓
  - llms.txt: https://docs.n8n.io/llms.txt
- [Langflow](https://www.langflow.org): Visual framework for building multi-agent and RAG applications with a node-based editor. ✓
  - llms.txt: https://www.langflow.org/llms.txt
- [Flowise](https://flowiseai.com): Drag-and-drop UI for building LLM workflows and agents — open-source, self-hostable. ✗

## Voice (STT / TTS)

- [Brethof Voice Pro](https://brethof.ai/voice/): Offline voice-to-text desktop app with 36-language support and LoRA voice training. ✓
  - llms.txt: https://brethof.ai/voice/llms.txt
- [whisper.cpp](https://github.com/ggml-org/whisper.cpp): C++ port of OpenAI Whisper for local speech-to-text — no Python, runs on CPU and many GPU backends. ✗
- [Coqui TTS](https://github.com/coqui-ai/TTS): Deep-learning toolkit for TTS with multi-speaker models and voice cloning. ✗
- [F5-TTS](https://github.com/SWivid/F5-TTS): High-quality open-source TTS with voice cloning from short audio reference. ✗
- [Kokoro TTS](https://github.com/hexgrad/kokoro): Lightweight open-weight TTS model — surprisingly natural output at small model size. ✗
- [OpenVoice](https://github.com/myshell-ai/OpenVoice): Versatile instant voice cloning with cross-lingual synthesis and granular style control. ✗
- [Piper](https://github.com/rhasspy/piper): Fast, local neural text-to-speech with dozens of voices — optimized for Raspberry Pi. ✗

## Image Generation

- [AUTOMATIC1111](https://github.com/AUTOMATIC1111/stable-diffusion-webui): Most widely-used web UI for Stable Diffusion — extensive extension ecosystem. ✗
- [Fooocus](https://github.com/lllyasviel/Fooocus): Simplified Stable Diffusion UI focused on ease-of-use — Midjourney-like experience locally. ✗
- [InvokeAI](https://invoke.com): Professional-grade Stable Diffusion with unified canvas, workflows, and team features. ✗
- [Krita AI Diffusion](https://github.com/Acly/krita-ai-diffusion): Krita plugin for Stable Diffusion — inpaint, img2img, and generative layers inside Krita. ✗
- [SD.Next](https://github.com/vladmandic/sdnext): Advanced fork of SD WebUI with broader model support (Flux, Lumina, Kolors, more). ✗

## Vector Databases

- [Chroma](https://www.trychroma.com): Open-source embedding database designed for LLM applications — runs embedded, as a server, or in the cloud. ✓
  - llms.txt: https://docs.trychroma.com/llms.txt
- [Milvus](https://milvus.io): Open-source cloud-native vector database built for billion-scale similarity search with separation of storage and compute. ✓
  - llms.txt: https://milvus.io/llms.txt
- [Pinecone](https://www.pinecone.io): Fully managed serverless vector database — the original SaaS option for production-scale vector search. ✓
  - llms.txt: https://docs.pinecone.io/llms.txt
- [Qdrant](https://qdrant.tech): Open-source, Rust-written vector database built for production scale — rich filtering, hybrid search, and multi-tenancy. ✓
  - llms.txt: https://qdrant.tech/llms.txt
- [SurrealDB](https://surrealdb.com): Multi-model database written in Rust combining document, graph, key-value, time-series, and vector in one engine. ✓
  - llms.txt: https://surrealdb.com/llms.txt
- [Weaviate](https://weaviate.io): Open-source vector database with built-in ML modules, hybrid search, and first-class RAG tooling. ✓
  - llms.txt: https://weaviate.io/llms.txt
- [pgvector](https://github.com/pgvector/pgvector): Postgres extension adding vector similarity search — the "just use Postgres" option for RAG. ✗
- [LanceDB](https://lancedb.com): Serverless vector DB on the Lance columnar format — embedded or cloud, multimodal-ready. ✗

## RAG Frameworks

- [Haystack](https://haystack.deepset.ai): Production-oriented Python framework for building RAG, search, and agent pipelines with composable components. ✓
  - llms.txt: https://docs.haystack.deepset.ai/llms.txt
- [Mem0](https://mem0.ai): Persistent memory layer for AI agents — remembers user facts, preferences, and context across sessions. ✓
  - llms.txt: https://docs.mem0.ai/llms.txt
- [LlamaIndex](https://www.llamaindex.ai): Leading RAG framework for connecting LLMs to private data — document loaders, indexes, retrievers, and agents. ✗
- [AnythingLLM](https://anythingllm.com): All-in-one desktop and Docker RAG app — document ingestion, agents, multi-user. ✗
- [Quivr](https://www.quivr.com): Opinionated RAG framework: plug in your LLM, vector store, and files and get a chatbot. ✗
- [Verba](https://github.com/weaviate/verba): Weaviate's open-source RAG chatbot — Golden RAGtriever reference implementation. ✗

## Embeddings

- [BGE (BAAI General Embedding)](https://huggingface.co/BAAI): Leading open embedding models from BAAI — top of MTEB for multiple languages. ✗
- [FastEmbed](https://github.com/qdrant/fastembed): Lightweight, CPU-friendly embedding library from Qdrant — no torch dependency. ✗
- [Sentence Transformers](https://sbert.net): Python framework for state-of-the-art sentence, text, and image embeddings. ✗

## Observability

- [Langfuse](https://langfuse.com): Open-source LLM engineering platform for tracing, evaluation, prompt management, and observability — self-host or cloud. ✓
  - llms.txt: https://langfuse.com/llms.txt
- [LangSmith](https://www.langchain.com/langsmith): Commercial observability, debugging, and evaluation platform for LLM and agent applications. ✗
- [Arize Phoenix](https://phoenix.arize.com): Open-source ML and LLM observability platform with OpenTelemetry-based tracing. ✓
  - llms.txt: https://arize.com/docs/phoenix/llms.txt
- [Helicone](https://helicone.ai): Open-source observability for LLM apps — traces, prompts, evaluations, usage analytics. ✓
  - llms.txt: https://helicone.ai/llms.txt
- [Weights & Biases](https://wandb.ai): Leading ML experiment tracking platform with dedicated LLM observability (Weave). ✗

## Evaluation

- [DeepEval](https://www.deepeval.com): Pytest-style LLM evaluation framework with 14+ metrics and CI/CD integration. ✓
  - llms.txt: https://www.deepeval.com/llms.txt
- [Promptfoo](https://www.promptfoo.dev): Open-source tool for testing, evaluating, and red-teaming LLM apps via config files. ✓
  - llms.txt: https://www.promptfoo.dev/llms.txt
- [Ragas](https://docs.ragas.io): Framework for evaluating RAG pipelines with metrics like faithfulness, answer relevance. ✓
  - llms.txt: https://docs.ragas.io/llms.txt

## Training & Fine-tuning

- [Unsloth](https://unsloth.ai): 2x faster LLM fine-tuning with 70% less memory — drop-in replacement for HuggingFace's training stack. ✓
  - llms.txt: https://docs.unsloth.ai/llms.txt
- [AI Toolkit (ostris)](https://github.com/ostris/ai-toolkit): Leading open-source toolkit for training LoRAs and fine-tunes on diffusion models — FLUX, SDXL, SD3, Qwen Image, and more. ✗
- [Axolotl](https://axolotl.ai): YAML-configured fine-tuning framework supporting LoRA, QLoRA, full FT, DPO, and most modern LLM architectures. ✗
- [TRL (HuggingFace)](https://huggingface.co/docs/trl): HuggingFace's library for reinforcement-learning based LLM training (DPO, PPO, SFT, KTO). ✓
  - llms.txt: https://huggingface.co/docs/trl/llms.txt
- [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory): WebUI-based fine-tuning framework supporting 100+ models with LoRA, QLoRA, DPO, and more. ✗
- [MS-Swift](https://github.com/modelscope/ms-swift): ModelScope's fine-tuning framework supporting 350+ LLMs and 100+ multimodal models. ✗

## Web Search for Agents

- [Exa](https://exa.ai): Neural search API built for AI agents — semantic search across the web with content retrieval. ✓
  - llms.txt: https://exa.ai/llms.txt
- [Perplexity API](https://docs.perplexity.ai): API access to Perplexity's search-augmented LLMs — Sonar models with live citations. ✓
  - llms.txt: https://docs.perplexity.ai/llms.txt
- [SerpAPI](https://serpapi.com): Scraping API for Google, Bing, DuckDuckGo and 15+ search engines — structured JSON results. ✓
  - llms.txt: https://serpapi.com/llms.txt
- [Tavily](https://tavily.com): Search API optimized for LLM agents — RAG-ready results with citations. ✓
  - llms.txt: https://tavily.com/llms.txt
- [Brave Search API](https://brave.com/search/api/): Independent web search API with no tracking — alternative to Google / Bing for agent use. ✗

## OCR & Document Parsing

- [Docling](https://docling-project.github.io/docling/): IBM's document parsing toolkit — PDF, DOCX, images into structured JSON/markdown for RAG. ✗
- [Marker](https://github.com/VikParuchuri/marker): Fast, accurate PDF-to-markdown conversion — tables, equations, and structure preserved. ✗
- [Unstructured](https://unstructured.io): Library for ingesting PDF, HTML, DOCX, XLSX, and 25+ formats into RAG-ready chunks. ✗

## Deployment & Hosting

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

## Desktop Applications

- [Claude Desktop](https://claude.com/download): Anthropic's native desktop app for Claude — MCP server support, skills, agent mode, and deep OS integration. ✓
  - llms.txt: https://docs.claude.com/llms.txt
- [PrivateGPT](https://github.com/zylon-ai/private-gpt): Privacy-first local AI over your documents — fully offline RAG chatbot. ✗
- [Raycast AI](https://www.raycast.com/ai): macOS launcher with integrated AI commands, chat, and custom quicklinks. ✗

## Shell Tools

- [Open Interpreter](https://www.openinterpreter.com): Natural language interface to your computer — runs code locally to complete tasks from the CLI. ✗
- [ShellGPT](https://github.com/TheR1D/shell_gpt): Command-line productivity tool powered by LLMs — generate shell commands, code, and configs. ✗

## Operating Systems (AI-capable Linux)

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