Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Released model weights, reference implementations and architecture research.
Signals: large-language-models, llm, foundation-models, transformer, gpt, llama, mistral, qwen
1,455 results
This repository contains examples of fine-tuning Harmonized Landsat and Sentinel-2 (HLS) Prithvi foundation model.
FireAct: Toward Language Agent Fine-tuning
Repo for fine-tuning Casual LLMs
[EMNLP'25] s3 - ⚡ Efficient & Effective Search Agent Training via RL for RAG (RLVR for Search with Minimal Data)
[NeurIPS' 2025] JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent
Deploy any AI model, agent, database, RAG, and pipeline locally or remotely in minutes
CLI, SDK, and IDE plugins for Duel Agents
Agents Capable of Self-Editing Their Prompts / Python Code
[CVPR 2024] "LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning"; an interactive Large Language 3D Assistant.
[ICLR'24] Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning
Code and data for "MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning" [ICLR 2024]
An Instruction-tuned Large Language Model for E-commerce
This repository contains code for extending the Stanford Alpaca synthetic instruction tuning to existing instruction-tuned models such as Flan-T5.
Retrieval-Augmented Theorem Provers for Lean
🔍 The hardest search benchmark in the wild — vague, multi-turn, proactive. 200 long-horizon tasks with persona-driven progressive disclosure, scored by verifiable schema-free knowledge-graph evaluation. No vibes, just triplet F1.
Official Implementation of ICML 2025 Paper: "Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models".
Fast, lossless LLM inference via dual-view diffusion decoding.
Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).
BaseAI — The Web AI Framework. The easiest way to build serverless autonomous AI agents with memory. Start building local-first, agentic pipes, tools, and memory. Deploy serverless with one command.
An open-source framework for collaborative AI agents, enabling diverse, distributed agents to team up and tackle complex tasks through internet-like connectivity.
The all-in-one RWKV runtime box with embed, RAG, AI agents, and more.
A local sandbox for your AI agents
Jupyter code notebooks of "ChatGPT Prompt Engineering for Developers" by DeepLearning.AI and OpenAI.
Enforce structured output from LLMs 100% of the time
24,540 repositories in the index in total.
