DFlash: Block Diffusion for Flash Speculative Decoding

The open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills.

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

Android real-time face capture framework for Live2D avatar animation, based on MediaPipe landmarks , MNN engine and custom tracking logic. 安卓端皮套人面捕系统，基于阿里 MNN。

Task-oriented AI Agent productivity platform

🎥 Make videos programmatically with React

利用AI大模型，一键解说并剪辑视频； Using AI models to automatically provide commentary and edit videos with a single click.

利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.

Open-source & free — Battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in fine-tuned ruleset (NPE, thre…

Official repository for SaaS-Bench: realistic, locally deployable SaaS workflows for GUI agent evaluation.

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

Evaluating Long-Horizon Agentic Software Development Across Version Upgrades — 115 tasks, 17 repos, 5 languages

Sleek, Fast and Token Efficient AI Coding Agent

Skills for Real Engineers. Straight from my .claude directory.

AI enabled pair programmer for Claude, GPT, O Series, Grok, Deepseek, Gemini and 300+ models

Lossless Claw — LCM (Lossless Context Management) plugin for OpenClaw

The offical repo for "LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling"

开源的 AI 时代软件研发方法论 | Open-source software development methodology for the AI era

Can Language Models Rebuild Programs From Scratch?

Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.

Spec-driven development (SDD) for AI coding assistants.

一个 LLM 驱动的 Galgame

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Awesome List for Agentic RL

A self-hosted ML coding practice platform. 68 problems from ReLU to flow matching — attention, training, RLHF, diffusion, and more. Instant feedback in the browser.

CodeCircuit: Toward Inferring LLM-Generated Code Correctness via Attribution Graphs

A curated collection of 900+ resources for evaluating AI coding agents — benchmarks, scoring methods, toolchain, leaderboards & pitfalls. Agent-queryable.