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.
1,506
repos tracked
261
surfaced this week
214
created < 30d
Python
top language
131 repos
-
Read, search, and edit AI dialogs stored as Jupyter notebooks, and convert them to and from LLM chat histories
-
🛰 A loupe for your agents — a real-time Mission-Control dashboard and workspace for AI coding agents, across every provider and every project on your machine
-
Data model and surgery toolkit for dialogs and notebooks
-
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
-
Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
-
SGLang is a high-performance serving framework for large language models and multimodal models.
-
Unsloth is a local UI for training and running Gemma 4, Qwen3.6, DeepSeek, Kimi, GLM and other models.
-
The agent that grows with you
-
Reproducible, flexible LLM evaluations
-
A lightweight execution guard for running LLM-generated Python in a normal Python process
-
the extensible, customizable, self-documenting, real-time multi-agent computing environment
-
A Datacenter Scale Distributed Inference Serving Framework
-
Custom AI agent platform to speed up your work.
-
Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.
-
Never stop coding. Free MIT AI gateway: one endpoint, 268+ providers (50+ free), 500+ models — Kimi, Claude, GPT, OpenAI, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 500+ contributors
-
LLM inference in C/C++
-
LLM inference in C/C++
-
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
-
🤗 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.
-
Automatic evals for LLMs
-
Language model tokenization at GB/s
-
Scored tooling katas, habit rules, and pre-baked warm-start sessions for LLM coding agents
-
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.
-
AIDE: AI-Driven Exploration in the Space of Code. The machine Learning engineering agent that automates AI R&D.
-
Same model, different wrapper: a from-scratch benchmark comparing coding-agent harnesses (codex, pi, opencode, cursor, devin) and open models on correctness, speed, and token cost
-
vLLM 0.25.1 serving stack for poolside/Laguna-S-2.1-NVFP4 with DFlash speculative decoding — DGX Spark & RTX 6000 PRO
-
LLM plugin to access Google's Gemini family of models
-
Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
-
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
-
A high-throughput and memory-efficient inference and serving engine for LLMs
-
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
-
Control Gmail, Google Calendar, Docs, Sheets, Slides, Chat, Forms, Tasks, Search & Drive with AI - Comprehensive Google Workspace / G Suite MCP Server & CLI Tool
-
Starter Kit for Auto-Judge developers
-
nnScaler: Compiling DNN models for Parallel Training
-
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
-
Apple's on-device Foundation Models from the command line — tiny, fast, no API key, in the spirit of Simon Willison's llm
-
the LLM vulnerability scanner
-
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.
-
LLM Architecture Gallery source data
-
Open-source test harness for AI agents. Stress-test production agents with adversarial multi-turn scenarios in CI
-
A cosy home for your LLMs.
-
Machine Learning Engineering Open Book
-
Assorted useful tools, almost entirely generated using LLMs
-
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
-
Ongoing research project for code&math LLMs
-
VibePrompter is a desktop app for visually designing process flows with typed inputs/outputs, validating connections, and exporting diagrams as JSON or LLM-ready prompts. Built with Python and pywebview, it provides a native, lightweight interface for turning workflows into implementation-ready specifications.
-
Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
-
MLT & AI Communities