--- title: "LLM Frameworks" type: "category" slug: "llm-frameworks" canonical_url: "https://www.graphcanon.com/categories/llm-frameworks" tool_count: 503 --- # LLM Frameworks *GraphCanon updated Aug 21, 2026* Frameworks and orchestration libraries for building LLM applications — prompting, chaining, RAG, and agent scaffolding (LangChain, LlamaIndex, Haystack). GraphCanon lists 503 published tools in LLM Frameworks. AutoGPT leads adoption at 186,623 GitHub stars. Pick on constraints, not hype: orchestration depth, RAG needs, agent loops, and team tolerance for framework surface area. GraphCanon ranks tools by typed graph relationships and live GitHub maintenance signals - not ad spend. 503 tools in this category (showing the top 60 by stars). ## Featured comparisons - [Yi vs Qwen](/compare/01-ai-yi-vs-qwenlm-qwen.md) - [Yi vs LLMs-from-scratch](/compare/01-ai-yi-vs-rasbt-llms-from-scratch.md) - [hexstrike-ai vs PentestGPT](/compare/0x4m4-hexstrike-ai-vs-greydgl-pentestgpt.md) - [hexstrike-ai vs AutoGPT](/compare/0x4m4-hexstrike-ai-vs-significant-gravitas-autogpt.md) - [rig vs LocalAI](/compare/0xplaygrounds-rig-vs-mudler-localai.md) - [1Panel vs open-webui](/compare/1panel-dev-1panel-vs-open-webui-open-webui.md) - [1Panel vs OpenHands](/compare/1panel-dev-1panel-vs-openhands-openhands.md) - [MaxKB vs WeKnora](/compare/1panel-dev-maxkb-vs-tencent-weknora.md) ## Stacks - [The RAG stack](/stacks/rag-pipeline.md) - [The AI agent stack](/stacks/autonomous-agent.md) ## Tools - [AutoGPT](/tools/significant-gravitas-autogpt.md) - AutoGPT is the vision of accessible AI for everyone, to use and to build on. (★ 186,623) [Very active] - [transformers](/tools/huggingface-transformers.md) - Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models (★ 164,121) [Very active] - [tensorflow](/tools/tensorflow-tensorflow.md) - An Open Source Machine Learning Framework for Everyone (★ 196,758) [Very active] - [prompts.chat](/tools/f-prompts-chat.md) - Share, discover, and collect prompts from the community (★ 167,212) [Very active] - [generative-ai-for-beginners](/tools/microsoft-generative-ai-for-beginners.md) - 21 Lessons for Getting Started with Generative AI (★ 113,577) [Very active] - [open-webui](/tools/open-webui-open-webui.md) - User-friendly AI Interface (Supports Ollama, OpenAI API, ...) (★ 148,875) [Very active] - [langchain](/tools/langchain-ai-langchain.md) - The agent engineering platform. (★ 143,615) [Very active] - [ollama](/tools/ollama-ollama.md) - Get up and running with various large language models using Ollama. (★ 177,524) [Very active] - [LLMs-from-scratch](/tools/rasbt-llms-from-scratch.md) - Implement a ChatGPT-like LLM in PyTorch from scratch, step by step (★ 102,733) [Very active] - [OpenHands](/tools/openhands-openhands.md) - AI-Driven Development (★ 84,154) [Very active] - [LlamaFactory](/tools/hiyouga-llamafactory.md) - Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (★ 74,132) [Very active] - [system_prompts_leaks](/tools/asgeirtj-system-prompts-leaks.md) - Extracted system prompts from various AI agents and LLMs (★ 62,977) [Very active] - [litellm](/tools/berriai-litellm.md) - Python SDK and Proxy Server for calling multiple LLM APIs (★ 55,221) [Very active] - [caveman](/tools/juliusbrussee-caveman.md) - Reduce token usage with concise 'caveman'-style prompts. (★ 98,423) [Very active] - [ai-engineering-from-scratch](/tools/rohitg00-ai-engineering-from-scratch.md) - Learn it. Build it. Ship it for others. (★ 46,862) [Very active] - [hello-agents](/tools/datawhalechina-hello-agents.md) - Course on building intelligent agents from scratch (★ 73,126) [Very active] - [LocalAI](/tools/mudler-localai.md) - Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required. (★ 48,500) [Very active] - [LightRAG](/tools/hkuds-lightrag.md) - [EMNLP2025] Simple and Fast Retrieval-Augmented Generation (★ 38,895) [Very active] - [ai-engineering-hub](/tools/patchy631-ai-engineering-hub.md) - Tutorials on LLMs, RAGs, and real-world AI agent applications (★ 37,020) [Active] - [FastGPT](/tools/labring-fastgpt.md) - A knowledge-based platform built on LLMs for developing and deploying complex question-answering systems (★ 29,366) [Very active] - [graphrag](/tools/microsoft-graphrag.md) - A modular graph-based Retrieval-Augmented Generation (RAG) system (★ 35,519) [Very active] - [AstrBot](/tools/astrbotdevs-astrbot.md) - AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature (★ 39,240) [Very active] - [onyx](/tools/onyx-dot-app-onyx.md) - Open Source AI Platform - AI Chat with advanced features that works with every LLM (★ 31,617) [Very active] - [haystack](/tools/deepset-ai-haystack.md) - Open-source AI orchestration framework for building context-engineered LLM applications. (★ 26,073) [Very active] - [repomix](/tools/yamadashy-repomix.md) - Powerful repository packager for AI integration (★ 27,881) [Very active] - [promptfoo](/tools/promptfoo-promptfoo.md) - Tool for evaluating prompts and AI agents by comparing performance across various models and red teaming. (★ 23,838) [Very active] - [peft](/tools/huggingface-peft.md) - State-of-the-art Parameter-Efficient Fine-Tuning (★ 21,443) [Very active] - [WeKnora](/tools/tencent-weknora.md) - Open-source LLM knowledge platform for creating a queryable RAG, autonomous reasoning agent, and self-maintaining Wiki. (★ 19,992) [Very active] - [context7](/tools/upstash-context7.md) - Up-to-date code documentation for LLMs and AI code editors (★ 60,812) [Very active] - [DB-GPT](/tools/eosphoros-ai-db-gpt.md) - open-source agentic AI data assistant for the next generation of AI + Data products (★ 19,740) [Very active] - [happy-llm](/tools/datawhalechina-happy-llm.md) - 📚 From Zero to Building Large Models (★ 32,987) [Active] - [Vibe-Trading](/tools/hkuds-vibe-trading.md) - Vibe-Trading Your Personal Trading Agent (★ 27,621) [Very active] - [daily_stock_analysis](/tools/zhulinsen-daily-stock-analysis.md) - LLM-powered multi-market stock analysis system with multi-source market data, real-time news, decision dashboard, automated notifications, and cost-free scheduled runs. (★ 62,988) [Very active] - [ai](/tools/vercel-ai.md) - AI Toolkit for TypeScript (★ 26,035) [Very active] - [agentscope](/tools/agentscope-ai-agentscope.md) - Build and run agents you can see, understand and trust. (★ 28,973) [Very active] - [graphiti](/tools/getzep-graphiti.md) - Build Real-Time Knowledge Graphs for AI Agents (★ 30,018) [Very active] - [ai-guide](/tools/liyupi-ai-guide.md) - 免费开放的AI知识共享平台 (★ 18,766) [Active] - [mastra](/tools/mastra-ai-mastra.md) - Modern TypeScript framework for AI-powered applications and agents (★ 27,229) [Very active] - [jan](/tools/janhq-jan.md) - open source alternative to ChatGPT that runs offline locally (★ 44,020) [Very active] - [code-review-graph](/tools/tirth8205-code-review-graph.md) - Local-first code intelligence graph for MCP and CLI. (★ 26,442) [Very active] - [fastmcp](/tools/prefecthq-fastmcp.md) - The fast Pythonic way to build MCP servers and clients (★ 26,846) [Very active] - [DeepTutor](/tools/hkuds-deeptutor.md) - Lifelong Personalized Tutoring (★ 35,947) [Very active] - [TradingAgents](/tools/tauricresearch-tradingagents.md) - Multi-Agents LLM Financial Trading Framework (★ 98,335) [Active] - [FinGPT](/tools/ai4finance-foundation-fingpt.md) - FinGPT: Open-Source Financial Large Language Models (★ 21,100) [Active] - [langchain4j](/tools/langchain4j-langchain4j.md) - Java library for building LLM-powered applications on the JVM (★ 12,813) [Very active] - [awesome-ai-apps](/tools/arindam200-awesome-ai-apps.md) - A curated list of AI applications showcasing RAG, agents, and workflows. (★ 13,268) [Very active] - [chainlit](/tools/chainlit-chainlit.md) - Build Conversational AI in minutes ⚡️ (★ 12,373) [Very active] - [bisheng](/tools/dataelement-bisheng.md) - BISHENG is an open LLM devops platform for next generation Enterprise AI applications (★ 11,879) [Very active] - [llm-app](/tools/pathwaycom-llm-app.md) - Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data. (★ 59,037) [Steady] - [agenticSeek](/tools/fosowl-agenticseek.md) - Fully Local Manus AI. No APIs, No $200 monthly bills. (★ 26,870) [Very active] - [ludwig](/tools/ludwig-ai-ludwig.md) - Low-code framework for building custom LLMs and AI models (★ 11,746) [Very active] - [txtai](/tools/neuml-txtai.md) - All-in-one AI framework for semantic search, LLM orchestration and language model workflows (★ 12,890) [Very active] - [PocketFlow](/tools/the-pocket-pocketflow.md) - Minimalist 100-line LLM framework enabling Agent creation and workflow orchestration. (★ 11,108) [Active] - [MoneyPrinterTurbo](/tools/harry0703-moneyprinterturbo.md) - Generate short videos with one click using AI LLM (★ 102,619) [Very active] - [semantic-kernel](/tools/microsoft-semantic-kernel.md) - Integrate cutting-edge LLM technology quickly and easily into your apps (★ 28,427) [Very active] - [Prompt-Engineering-Guide](/tools/dair-ai-prompt-engineering-guide.md) - Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents (★ 77,531) [Slowing] - [heretic](/tools/p-e-w-heretic.md) - Fully automatic censorship removal for language models (★ 27,709) [Very active] - [Awesome-Multimodal-Large-Language-Models](/tools/bradyfu-awesome-multimodal-large-language-models.md) - Latest Advances on Multimodal Large Language Models (★ 17,978) [Very active] - [unity-mcp](/tools/coplaydev-unity-mcp.md) - Bridge between AI assistants and Unity Editor for asset management, scene control, script editing, task automation (★ 12,846) [Active] - [llamafile](/tools/mozilla-ai-llamafile.md) - Distribute and run LLMs with a single file. (★ 25,470) [Very active] ## Common questions ### What are the best llm frameworks tools? GraphCanon ranks LLM Frameworks tools by GitHub adoption and freshness. AutoGPT is the current leader (186,623 stars). See the full list on this page - sorted by stars, with [maintenance labels](/glossary/trust-and-signals/maintenance-label) and graph relationships. ### How does GraphCanon rank LLM Frameworks tools? We sort by GitHub stars and push recency on category pages, not paid placement. Alternatives and compare pages use [typed graph edges](/glossary/knowledge-graph/typed-edge) (alternative, successor, integrates_with) plus shared categories - constraint-first, not marketing votes. ### How many tools are in LLM Frameworks? 503 published tools are tagged with LLM Frameworks in the GraphCanon knowledge graph. ### What are popular LLM Frameworks comparisons? Head-to-head compare pages in this category include Yi vs Qwen, Yi vs LLMs-from-scratch, hexstrike-ai vs PentestGPT. Each comparison uses live GitHub stats and optional [trust signals](/glossary/trust-and-signals/trust-signal) - see the comparisons block on this page. ### Which stacks use LLM Frameworks? Curated workflow pages that include LLM Frameworks: [The RAG stack](/stacks/rag-pipeline); [The AI agent stack](/stacks/autonomous-agent). Each stack step includes when-not-to-use guidance. ### Where are graph-backed alternatives hubs for LLM Frameworks? High-intent OSS-vs-OSS alternatives pages include [LangChain alternatives](/tools/langchain-ai-langchain/alternatives), [LlamaIndex alternatives](/tools/run-llama-llama-index/alternatives), [Qdrant alternatives](/tools/qdrant-qdrant/alternatives), [FinRobot alternatives](/tools/ai4finance-foundation-finrobot/alternatives), [free-llm-api-resources alternatives](/tools/cheahjs-free-llm-api-resources/alternatives), [caveman alternatives](/tools/juliusbrussee-caveman/alternatives), [rtk alternatives](/tools/rtk-ai-rtk/alternatives), [unsloth alternatives](/tools/unslothai-unsloth/alternatives), [ollama alternatives](/tools/ollama-ollama/alternatives). Each hub ranks typed graph neighbors and constraint tags - not popularity votes. ### Is there a machine-readable LLM Frameworks list? Yes. Append `.md` to this URL or fetch [`/md/categories/llm-frameworks`](/md/categories/llm-frameworks) for a markdown twin. The JSON API exposes the same corpus at [`/api/graphcanon/categories/llm-frameworks`](/api/graphcanon/categories/llm-frameworks). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/categories/llm-frameworks`](/api/graphcanon/categories/llm-frameworks) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_