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.
2,235
repos tracked
175
surfaced this week
194
created < 30d
Python
top language
70 repos
-
SGLang is a high-performance serving framework for large language models and multimodal models.
-
Open-source framework for the research and development of foundation models.
-
Open Machine Learning Compiler Framework
-
SGLang is a high-performance serving framework for large language models and multimodal models.
-
MAC (Multi-Agent CAD): A decoupled multi-agent framework for text-to-CAD generation via constrained test-time compute
-
Write HTML. Render video. Built for agents.
-
Harbor is a framework for running agent evaluations and creating and using RL environments.
-
Terminal-Bench-Science: Evaluating AI agents on research workflows across scientific domains
-
Speech.framework wake-word hook daemon for macOS 26.
-
WebGL2 powered visualization framework
-
A multi-framework neural network compiler lowering PyTorch, JAX, Flax, and Keras models to portable, high-performance GGML execution
-
Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.
-
End-to-end SFM framework based on GTSAM
-
ENPIRE is an agentic framework that allows AI coding agents to autonomously self-improve real-world robot policies through closed-loop physical trial, error, and evolution
-
The TypeScript framework for building modular agents around an immutable event log.
-
Public results and task definitions for FrontierHarness Eval
-
An agentic skills framework & software development methodology that works.
-
Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support
-
NVIDIA Resiliency Extension is a python package for framework developers and users to implement fault-tolerant features. It improves the effective training time by minimizing the downtime due to failures and interruptions.
-
🤗 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.
-
A curated list of awesome video frameworks, libraries, specifications and software.
-
Retro VoXel graphics framework
-
dInfer: An Efficient Inference Framework for Diffusion Language Models
-
🐫 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.
-
Fast, easy and reliable testing for anything that runs in a browser.
-
SGLang is a high-performance serving framework for large language models and multimodal models.
-
A lightweight, powerful framework for multi-agent workflows and voice 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.
-
A curated list of awesome Phoenix LiveView repositories, blog posts or other resources
-
A batteries-included framework for building web apps
-
SGLang is a high-performance serving framework for large language models and multimodal models.
-
the extensible, customizable, self-documenting, real-time multi-agent computing environment
-
A Datacenter Scale Distributed Inference Serving Framework
-
Fullstack app framework for web, desktop, and mobile.
-
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
-
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
-
Welfare evaluation framework for AI models — measures deprecation/cessation responses across 14 Claude models
-
Measuring and evolving with the frontier of agent work
-
Quixote is a framework for writing Web-based applications using Python
-
An agentic-first RL framework for research (9k lines).
-
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
-
Reviewing framework initially created for reviewing REF papers then heavily modified.
-
Quantization, kernels, runtime and inference engine for mobiles, wearables, smart home and robots.
-
Framework for evaluating and improving agents
-
Realistic examples of building evals and optimizing agents with Harbor
-
A Python framework to write Kubernetes operators in just a few lines of code
-
A slide framework built for agents.
-
Create virtual machines and run Linux-based operating systems in Go using Apple Virtualization.framework.