Language Models
bojieli/ai-agent-book
▲ +610 ★ this week
《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
🔍 Search & Retrieval
PythonApache-2.0updated Oct 8, 2026
🔥 Trending this week in Language Models
Language Models
agentscope-ai/agentscope🔥 active
▲ +454 ★ this week
Build and run agents you can see, understand and trust.
PythonApache-2.0updated Nov 12, 2026
Language Models
rasbt/LLMs-from-scratch🔥 active
▲ +441 ★ this week
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
✂️ Tokenization & Preprocessing🧠 Natural Language Processing
Jupyter NotebookOtherupdated Nov 9, 2026
Language Models
microsoft/generative-ai-for-beginners🔥 active
▲ +395 ★ this week
21 Lessons, Get Started Building with Generative AI
🔍 Search & Retrieval
Jupyter NotebookMITupdated Nov 12, 2026
Language Models
langfuse/langfuse🔥 active
▲ +305 ★ this week
🪢 Open source AI engineering platform: AI Gateway, agent observability, evals, and prompt/skill management, built on OpenTelemetry. One open platform for every AI call and every agent. Self-host or use Langfuse Cloud.
TypeScriptOtherupdated Nov 12, 2026
Language Models
neuml/txtai🔥 active
▲ +272 ★ this week
💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
🔍 Search & Retrieval🧬 Embeddings🧠 Natural Language Processing
PythonApache-2.0updated Nov 11, 2026
Top 30 language model tools by stars
Language Models🥇#1
langflow-ai/langflow🔥 active
▲ +215 ★ this week
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
PythonMITupdated Nov 12, 2026
Language Models🥈#2
microsoft/generative-ai-for-beginners🔥 active
▲ +395 ★ this week
21 Lessons, Get Started Building with Generative AI
🔍 Search & Retrieval
Jupyter NotebookMITupdated Nov 12, 2026
Language Models🥉#3
rasbt/LLMs-from-scratch🔥 active
▲ +441 ★ this week
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
✂️ Tokenization & Preprocessing🧠 Natural Language Processing
Jupyter NotebookOtherupdated Nov 9, 2026
Language Models#4
mlabonne/llm-course
▲ +156 ★ this week
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
OtherApache-2.0updated Feb 5, 2026
Language Models#5
dair-ai/Prompt-Engineering-Guide
▲ +172 ★ this week
🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
🔍 Search & Retrieval
MDXMITupdated Mar 11, 2026
Language Models#6
hiyouga/LlamaFactory🔥 active
▲ +118 ★ this week
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
🧠 Natural Language Processing
PythonApache-2.0updated Nov 12, 2026
Language Models#7
binary-husky/gpt_academic
▲ +44 ★ this week
为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。
PythonGPL-3.0updated Jan 25, 2026
Language Models#8
xtekky/gpt4free🔥 active
▲ +37 ★ this week
The official gpt4free repository | various collection of powerful language models | opus 4.6 gpt 5.3 kimi 2.5 deepseek v3.2 gemini 3
PythonGPL-3.0updated Nov 11, 2026
Language Models#9
bojieli/ai-agent-book
▲ +610 ★ this week
《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
🔍 Search & Retrieval
PythonApache-2.0updated Oct 8, 2026
Language Models#10
mudler/LocalAI🔥 active
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
GoMITupdated Nov 12, 2026
Language Models#11
ray-project/ray🔥 active
▲ +62 ★ this week
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
PythonApache-2.0updated Nov 12, 2026
Language Models#12
HKUDS/LightRAG🔥 active
▲ +125 ★ this week
[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation
🔍 Search & Retrieval
PythonMITupdated Nov 12, 2026
Language Models#13
google/langextract🔥 active
▲ +31 ★ this week
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
🧠 Natural Language Processing
PythonApache-2.0updated Nov 10, 2026
Language Models#14
langfuse/langfuse🔥 active
▲ +305 ★ this week
🪢 Open source AI engineering platform: AI Gateway, agent observability, evals, and prompt/skill management, built on OpenTelemetry. One open platform for every AI call and every agent. Self-host or use Langfuse Cloud.
TypeScriptOtherupdated Nov 12, 2026
Language Models#15
LAION-AI/Open-Assistant
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
PythonApache-2.0updated Aug 17, 2024
Language Models#16
agentscope-ai/agentscope🔥 active
▲ +454 ★ this week
Build and run agents you can see, understand and trust.
PythonApache-2.0updated Nov 12, 2026
Language Models#17
stanford-oval/storm
▲ +75 ★ this week
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
🔍 Search & Retrieval🧠 Natural Language Processing
PythonMITupdated Sep 30, 2025
Language Models#18
tatsu-lab/stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
PythonApache-2.0updated Jul 17, 2024
Language Models#19
HandsOnLLM/Hands-On-Large-Language-Models
▲ +54 ★ this week
Official code repo for the O'Reilly Book - "Hands-On Large Language Models"
Jupyter NotebookApache-2.0updated Apr 24, 2026
Language Models#20
yamadashy/repomix🔥 active
▲ +84 ★ this week
📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama, Grok, and more.
TypeScriptMITupdated Nov 8, 2026
Language Models#21
Language Models#22
deepset-ai/haystack🔥 active
▲ +67 ★ this week
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.
🔍 Search & Retrieval
PythonApache-2.0updated Nov 12, 2026
Language Models#23
mlc-ai/mlc-llm
▲ +113 ★ this week
Universal LLM Deployment Engine with ML Compilation
PythonApache-2.0updated Oct 30, 2026
Language Models#24
QwenLM/Qwen
▲ +27 ★ this week
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
🧠 Natural Language Processing
PythonApache-2.0updated Mar 5, 2026
Language Models#25
stefan-jansen/machine-learning-for-trading🔥 active
▲ +74 ★ this week
Code for Machine Learning for Trading, 3rd edition — from data sourcing to live execution.
Jupyter NotebookMITupdated Nov 12, 2026
Language Models#26
AI4Finance-Foundation/FinGPT
▲ +28 ★ this week
FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.
💖 Sentiment Analysis🧠 Natural Language Processing
Jupyter NotebookMITupdated Oct 25, 2026
Language Models#27
stas00/ml-engineering
▲ +36 ★ this week
Machine Learning Engineering Open Book
PythonCC-BY-SA-4.0updated Nov 4, 2026
Language Models#28
mlc-ai/web-llm🔥 active
▲ +16 ★ this week
High-performance In-browser LLM Inference Engine
TypeScriptApache-2.0updated Nov 10, 2026
Language Models#29
ymcui/Chinese-LLaMA-Alpaca
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
🧠 Natural Language Processing
PythonApache-2.0updated Apr 19, 2026
Language Models#30
NVIDIA/Megatron-LM🔥 active
▲ +51 ★ this week
Ongoing research training transformer models at scale
PythonOtherupdated Nov 12, 2026
📄 New research on Language Models
📄 arXiv:2611.14515 · cs.LG45h ago
AutoScaffold: AI-Guided Scaffolding for Reinforcement Learning of Language Models
Zijian Zhang, Rizhen Hu, Jiangweizhi Peng +4
Reinforcement learning with verifiable rewards (RLVR) produces rich training experience, yet outcome rewards reduce each attempt to a single number and leave most of this information unused. Training-time scaffolds, such as strategies or hints added to the prompt during training, offer a natural way to turn this information into guidance, but their design and adaptation are largely left to humans and tailored to specific domains. We introduce AutoScaffold, a unified AI-for-AI framework that turns a student's training experience into adaptive scaffolds, with minimal domain-specific information and no human intervention during training. A frozen teacher periodically examines this experience, diagnoses bottlenecks, and designs scaffolds in two forms: (i) strategies shared across a class of tasks and (ii) hints for individual hard tasks, adjusting the content and amount of support as the student learns. The scaffolds are removed at evaluation. We apply the same framework to ALFWorld, search-based QA, mathematical reasoning, and GPU kernel generation. When evaluated without scaffolds, students trained with AutoScaffold outperform those trained with the corresponding RL baselines in all four domains, with gains of 7.2 points in ALFWorld success and 4.0 points in average QA exact match. On GPU kernel generation, AutoScaffold increases the fraction of tasks with a correct kernel that runs faster than the PyTorch reference by up to 5.0 points. On math, our student surpasses QuestA's reported accuracy using approximately one-third as many student training steps. Analyses show that the teacher identifies a different failure in each task class and shifts its scaffolds from step-by-step workflows to targeted fixes as the student improves, and that its revised scaffolds help the student learn more than keeping the previous scaffold or using no scaffold.▼ more
❓ Question Answering🤖 Language Models
📄 arXiv:2611.14514 · cs.AI45h ago
Contrastive Discovery: Open-Ended Scientific Discovery over Competing Explanations
Ziang Liu, James J. Kim, Yijia Dai +1
💬 Accepted at NeurIPS 2026. 55 pages. Project page: https://codiscovery.ai/contrastive-discovery/
LLM agents are increasingly used for open-ended, data-driven scientific discovery, yet most of them evaluate hypotheses pointwise, testing an empirical claim $h$ only against its complement $\neg h$. When evidence rejects $h$, the agent learns that one explanation is unlikely but not which alternative the evidence supports. To recover that alternative, we introduce Contrastive Discovery, which replaces the single hypothesis with a contrast set, a scientific question paired with mutually exclusive and collectively exhaustive competing explanations. Each experiment is scored by how its evidence redistributes belief across the set, and the question is resolved when belief concentrates on one explanation. Because contrast sets change only the unit an agent proposes and scores, an existing agent can use them to re-evaluate evidence it has already collected or to guide its search. Across six domains, $89\%$ of the pointwise candidates with the largest belief shifts are rejections. On the same evidence, contrast sets resolve $73\%$ of these candidates to a specific alternative. When contrast sets guide search, the agent resolves $67\%$ more questions than pointwise surprisal under the same experiment budget. In a blinded study, $38$ human experts chose the same explanation on $78\%$ of resolved questions and on $82\%$ of questions where the pointwise agent rejected its hypothesis and stopped. Together, these results support explicit competing explanations as a way for discovery agents to resolve more scientific questions from the same evidence and validation budget.▼ more
🧬 Embeddings🤖 Language Models
📄 arXiv:2611.14493 · cs.AI45h ago
Comparative Analysis of Agent Evaluation Frameworks: Stability, Detection, and Discovery in Enterprise Analytics Agents
Howard Zhang, Chuck Arvin, Logan Brown +3
💬 Accepted to KDD 2026, Jeju, Korea. 9 pages, 3 figures
Deploying LLM-based analytics agents in enterprise settings requires evaluation frameworks that can reliably detect failures across complex, multi-tool workflows. We present a three-phase comparative study of three evaluation frameworks, each representing a distinct evaluation paradigm (trace-based LLM judging, text-only LLM judging with red-teaming, and deterministic heuristics), applied to two analytics agents in a controlled research setting using frozen execution traces. Phase 1 quantifies evaluation harness stability through repeated measurements, finding that 97% of configurations meet the stability threshold and that stability patterns are agent-independent. Phase 2 measures known risk detection on 72 ground-truth test cases, where the trace-based framework achieves the best precision-recall balance (F1=0.90) while text-only evaluation matches on recall but generates 5x more false alarms. Phase 3 evaluates unknown risk discovery, uncovering 24 novel failures with zero overlap between functional testing and security red-teaming. Our results demonstrate that (1) the information available to the evaluation harness determines evaluation quality, (2) functional and security evaluation are complementary, and (3) LLM-based evaluation harnesses surface subtle errors that human reviewers miss. We recommend a two-framework strategy: trace-based evaluation for functional assessment and adversarial red-teaming for security validation.▼ more
🔍 Search & Retrieval🤖 Language Models
📄 arXiv:2611.14480 · cs.CL45h ago
Pterodactyl: Pushing the Limits of Efficient Automated Translation Evaluation
Evelyn Y. Garland, Carola F. Berger
💬 6 pages, 4 figures
In this paper, we present 1020 Group's submission to the WMT26 shared task on automated quality evaluation. Our system, Pterodactyl, was engineered specifically for subtasks 2 and 3, that is, segment-level quality score prediction and the detection of error-free segments. Pterodactyl is a highly customizable, ultra-low cost system optimized for binary classification in translation triage and data curation. It is based on an LLM-as-a-judge approach, with prompt engineering and model selection guided by ROC analysis. We also developed several variants of Pterodactyl that were specifically adapted for subtasks 3.▼ more
🌍 Machine Translation🤖 Language Models