Open source alternatives to LLMSurvey
50 open source AI apps to use instead, best rated first.
Top picks
- O

Open WebUI
LaunchSelf-hosted AI platform that connects local and cloud models, extends with Python, and keeps your data under your control.
Self-hosted
- A

AutoGPT
LaunchAutoGPT is a platform for building, deploying and running AI agents that automate repeatable digital work such as research, outreach, content and support, without writing code. The product centres on Experts: AI specialists with a role, ins
- C

Crawl4AI
LaunchOpen-source web crawler and scraper that produces clean, structured output optimized for LLMs, RAG pipelines, and AI agents. Supports async crawling, CSS/XPath/LLM extraction, and stealth browser control.
- P

pi
LaunchTerminal-based coding agent with a minimal core, 15+ LLM providers, tree-structured session history, and a TypeScript extension system for building your own workflows.
- A

AFFiNE
LaunchAn open-source, local-first knowledge base that merges structured docs, infinite whiteboards, databases, and AI into a single workspace for teams and creators.
- A

aider
LaunchTerminal-based AI coding tool that lets you edit existing codebases or start new projects using LLMs like Claude, GPT, and DeepSeek.
More AI apps
About LLMSurvey
LLMSurvey
The official GitHub page for the survey paper "A Survey of Large Language…
LLMSurvey is the official GitHub page for the survey paper A Survey of Large Language Models, from the RUCAIBox group. It is a curated collection of papers and resources about large language models, and its organisation follows the structure of the survey. The page lists updates to the survey, including a Chinese book by the same authors, aimed at senior undergraduate and junior graduate students with a background in deep learning, which presents an overview and roadmap of LLMs. The most recent update adds material on long chain-of-thought reasoning, the paradigm used by recent reasoning models such as DeepSeek-R1 and OpenAI's o-series. That section discusses the reasoning patterns of long CoT, how long CoT data is built through distillation, search-based synthesis and multi-agent collaboration, the training methods of instruction tuning and scaled reinforcement learning, and test-time scaling. The page also tracks the number of arXiv papers that mention language models and large language models over time, with the milestones of the field marked, and it includes a timeline of the GPT series and an evolutionary graph of the LLaMA family. Corrections and suggestions are invited by email, and the authors ask people who use the survey to cite the paper.
- Price
- Free
- Made by
- RUCAIBox
- Category
- AI
- Website
- github.com/rucaibox/llmsurvey



