THE DUDE’S FIELD GUIDE
Open-source AI & language models
AI and language-model repositories include inference engines, training tools and model interfaces. Choose the layer you actually need before comparing individual projects.
How to choose
Check model compatibility, memory needs, deployment options and model licenses separately from the application license.
Repositories to explore
Ordered by observed stars. This is a directory sample, not a best-to-worst verdict. Individual briefs show observation dates and source links.
| Project and purpose | Code license | Setup | Observed stars |
|---|---|---|---|
| affaan-m/ECC The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond. | MIT | See setup guide | 305,3112026-11-17 |
| NousResearch/hermes-agent The agent that grows with you | MIT | See setup guide | 264,1702026-11-17 |
| firecrawl/firecrawl Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥 | AGPL-3.0 | Developer library | 202,5892026-11-17 |
| DietrichGebert/ponytail Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. | MIT | See setup guide | 192,8822026-11-17 |
| ollama/ollama Get a local language model running quickly. | MIT | Command line | 187,4122026-11-17 |
| huggingface/transformers 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. | Apache-2.0 | Developer library | 169,3292026-11-17 |
| langchain-ai/langchain The agent engineering platform. | MIT | See setup guide | 149,8512026-11-18 |
| Graphify-Labs/graphify Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every… | Apache-2.0 | Command line | 149,5572026-11-17 |
| harry0703/MoneyPrinterTurbo Generate short videos from a topic or keyword using an automated AI workflow. | MIT | See setup guide | 144,4122026-11-18 |
| ggml-org/llama.cpp A flexible engine for running language models. | MIT | Developer tool | 135,6762026-11-17 |
| TauricResearch/TradingAgents TradingAgents: Multi-Agents LLM Financial Trading Framework | Apache-2.0 | Developer library | 122,9512026-11-17 |
| browser-use/browser-use Connect an AI agent to a web browser. | MIT | Developer tool | 121,3092026-11-17 |
| JuliusBrussee/caveman 🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman. | Apache-2.0 | See setup guide | 121,0182026-11-17 |
| paperclipai/paperclip The open-source app everyone uses to manage agents at work | MIT | See setup guide | 114,7502026-11-18 |
| tt-a1i/archify Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more. | Apache-2.0 | See setup guide | 97,4342026-11-17 |
| vllm-project/vllm A high-throughput and memory-efficient inference and serving engine for LLMs | Apache-2.0 | See setup guide | 97,1102026-11-17 |
| OpenHands/OpenHands 🙌 OpenHands: AI-Driven Development | MIT | See setup guide | 93,6582026-11-17 |
| unclecode/crawl4ai Official Crawl4AI Cloud: a hosted web scraping, extraction, and search API for AI agents. Free API key, 1,000 credits a month, no card. Fully open source: this repo is the Apache-2.0 crawler that powers… | Apache-2.0 | Self-hosted service | 87,4802026-11-17 |
| rtk-ai/rtk CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies | Apache-2.0 | Command line | 86,9182026-11-17 |
| bytedance/deer-flow An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks… | MIT | See setup guide | 85,4452026-11-17 |
| headroomlabs-ai/headroom Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server. | Apache-2.0 | Developer library | 79,9082026-11-17 |
| unslothai/unsloth Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more. | Apache-2.0 | See setup guide | 79,7352026-11-18 |
| Ebony-Vinyl/dsh-our-free-model 在 dsh 里装上这个插件即可,无需登录、注册或填 API Key,就能使用包括 DeepSeek V4.1 Flash、Kimi K3 在内的前沿模型——完全免费,不限量。 All you do is install this plugin in dsh: no login, no sign-up, no API key — the frontier models are just there,… | MIT | See setup guide | 78,4732026-11-17 |
| hiyouga/LlamaFactory Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024) | Apache-2.0 | See setup guide | 76,0892026-11-17 |
| ZhuLinsen/daily_stock_analysis LLM 驱动的多市场股票智能分析系统:多源行情、实时新闻、决策看板与自动推送,支持零成本定时运行。 LLM-powered multi-market stock analysis system with multi-source market data, real-time news, decision dashboard, automated notifications, and cost-free… | MIT | See setup guide | 73,0552026-11-17 |
| FoundationAgents/MetaGPT 🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming | MIT | Developer library | 71,3292026-11-17 |
| blader/humanizer Agent skill that removes signs of AI-generated writing from text | MIT | Agent skill | 70,2902026-11-17 |
| mem0ai/mem0 The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production. | Apache-2.0 | See setup guide | 69,1242026-11-17 |
| upstash/context7 Context7 Platform -- Up-to-date docs for AI agents | MIT | See setup guide | 65,0092026-11-17 |
| sansan0/TrendRadar Aggregate news and RSS feeds, filter topics, and generate AI-assisted trend briefings and alerts. | GPL-3.0 | See setup guide | 63,6972026-11-17 |
| MemPalace/mempalace The best-benchmarked open-source AI memory system. And it's free. | MIT | See setup guide | 60,5972026-11-17 |
| pathwaycom/serviette A no-code RAG server that keeps answers in sync with your documents. Works with 8 vector databases. Built on Pathway. | MIT | Self-hosted service | 58,7072026-11-17 |
| run-llama/llama_index LlamaIndex is the document processing platform for AI | MIT | See setup guide | 52,9292026-11-17 |
| mudler/LocalAI LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required. | MIT | See setup guide | 50,4332026-11-18 |
| jeecgboot/JeecgBoot An AI-assisted low-code platform for business applications, workflows, reports and knowledge bases. | Apache-2.0 | See setup guide | 48,5012026-11-17 |
| paperless-ngx/paperless-ngx A community-supported supercharged document management system: scan, index and archive all your documents | GPL-3.0 | See setup guide | 48,2152026-11-17 |
| AstrBotDevs/AstrBot AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨ | AGPL-3.0 | Developer library | 47,1212026-11-17 |
| milvus-io/milvus Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search | Apache-2.0 | See setup guide | 46,6792026-11-17 |
| ray-project/ray Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads. | Apache-2.0 | See setup guide | 44,3122026-11-17 |
| codewhale-hq/Codewhale An open-source coding agent for your terminal, written in Rust. It works with any model, can split one task across several agents, and every line of it is yours to read. | MIT | Command line | 41,1872026-11-17 |
| datalab-to/marker Convert PDF to markdown + JSON quickly with high accuracy | Apache-2.0 | See setup guide | 40,9582026-11-17 |
| 2noise/ChatTTS A generative speech model for daily dialogue. | AGPL-3.0 | See setup guide | 40,0172026-11-17 |
| The-Vibe-Company/quivr An open-source engine that turns continuous content streams into search and monitoring. Durable ingestion, hybrid search, alerts, and plugins for formats, models and business rules. | MIT | See setup guide | 39,6572026-11-17 |
| khoj-ai/khoj Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI… | AGPL-3.0 | Self-hosted service | 38,1612026-11-17 |
| DayuanJiang/next-ai-draw-io Draw and edit draw.io diagrams by chatting with an AI. Web app, desktop app, and an MCP server for Claude Code, Cursor, Codex and VS Code. | Apache-2.0 | MCP server | 37,0242026-11-17 |
| tirth8205/code-review-graph Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo… | MIT | Command line | 32,8252026-11-17 |
| QwenLM/qwen-code An open-source AI coding agent that lives in your terminal. | Apache-2.0 | Command line | 30,7522026-11-18 |
Is open source the same as free to run?
No. The code license and operating costs are separate. Check model terms, hardware, hosting and paid services in each project’s documentation.
Read our sourcing and ranking methodology →