Stars
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
⚙️ A curated list of static analysis (SAST) tools and linters for all programming languages, config files, build tools, and more. The focus is on tools which improve code quality.
[Survey] A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"
Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!
Extremely fast Query Engine for DataFrames, written in Rust
SWE-Swiss: A Multi-Task Fine-Tuning and RL Recipe for High-Performance Issue Resolution
[NeurIPS 2025 Spotlight] Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning
codes for R-Zero: Self-Evolving Reasoning LLM from Zero Data (https://www.arxiv.org/pdf/2508.05004)
Open Source DeepWiki: AI-Powered Wiki Generator for GitHub/Gitlab/Bitbucket Repositories. Join the discord: https://discord.gg/gMwThUMeme
An open-source AI agent that lives in your terminal.
An open-source AI agent that brings the power of Gemini directly into your terminal.
How can we build a true AI agent? Like Claude Code.
Kode CLI — Design for post-human workflows. One unit agent for every human & computer task.
DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation
A set of coding style guidelines for Vibe Coding or SWE-Agents that maximize efficiency and improve human readability.
Trae Agent is an LLM-based agent for general purpose software engineering tasks.
KernelBench: Can LLMs Write GPU Kernels? - Benchmark + Toolkit with Torch -> CUDA (+ more DSLs)
Model Context Protocol Servers
[NeurIPS'25] Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"
Paper List of Inference/Test Time Scaling/Computing
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3, Qwen3-MoE, DeepSeek-R1, GLM4.5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, …