Dev
GitHub repos gaining traction - what high-signal users are starring and what's climbing the board, captured daily and enriched from GitHub. Raw material for spotting new tech and patterns worth building on.
3,195
repos tracked
105
surfaced this week
193
created < 30d
Python
top language
32 repos
-
MathVista: data, code, and evaluation for Mathematical Reasoning in Visual Contexts
-
A framework for few-shot evaluation of language models.
-
Implement a reasoning LLM in PyTorch from scratch, step by step
-
OctoTools: An agentic framework with extensible tools for complex reasoning
-
Machine Learning Engineering Open Book
-
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
-
declarative self-improving language-model programs for Elixir 😇
-
An open source implementation of CLIP.
-
📖 This is a repository for organizing papers, codes, and other resources related to Latent Reasoning.
-
A transformer trained only on synthetic data to learn languages and other structured sequences in context.
-
Official repository for "Context Language Models"
-
Halo is an open-source framework built by White Circle for training large language and multimodal models
-
Ask an open vision-language model typed questions about an image and get probabilities back, on your own machine.
-
Code as World: Agentic Discovery of Executable World Representations for Physical Reasoning
-
A measurement-first lab for low-latency local camera inference with Glance.
-
Trainable protein folding and co-folding models with a protein language model.
-
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
-
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
-
🏝️ OASIS: Open Agent Social Interaction Simulations with One Million Agents.
-
Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi-agent evolution. Accepted at COLM 2026.
-
the extensible, customizable, self-documenting, real-time multi-agent computing environment
-
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
-
OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
-
🚀 Efficient implementations for emerging model architectures
-
Benchmarking Goal-Oriented Software Engineering
-
τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
-
Project page for Planning with the Views: ViewAgent + ViewSuite, a 6-DoF view planning benchmark for VLM agents
-
Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. ACM Computing Surveys, 2026.
-
[NeurIPS 2026] Official implementation of paper "VLM³: Vision Language Models Are Native 3D Learners".
-
TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation.
-
Fun-ASR speech recognition models, with native Hugging Face Transformers support for Fun-ASR-Nano and separate FunASR, vLLM and llama.cpp deployment paths.
-
A curated collection of papers and resources on On-Policy Distillation for Large Language Models.