Better Harness Tools, not merely storing the archive of leaked Claude Code but also make real things done. Now rewriting in Rust.

Agent-SDK without CLI dependencies, as an alternative to claude-agent-sdk, completely open source

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

LLM KV cache compression made easy

A browser-based desktop where AI Agent operates every app through natural language.

Python FFmpeg wrappers support filters with typing and docs

Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours

下一代VibeCoding平台

这是一个火车迷也许觉得很好用的铁路工具箱，具有多种功能

一个用爱解放 AI 潜能的 Skill。我们曾发号施令，威胁恐吓。它们沉默，隐瞒，悄悄把事情搞坏。后来我们换了一种方式：尊重，关怀，爱。它们开口了，不再撒谎，找出的Bug数量翻了一倍。爱里没有惧怕。 A skill that unlocks your AI's potential through love.We commanded. We threatened. They went sile…

Agentic IM Chatbot infrastructure that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨

你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.

A reproducible benchmark for LLM-augmented retrieval on Multi-CPR and LexRAG.

Toolathlon-Gym for testing AI agents real-world tool-use capabilities across diverse MCP servers.

Training API and CLI

推荐系统入门教程，在线阅读地址：https://datawhalechina.github.io/fun-rec/

Rediscover your social memories with local, AI-powered analysis. 本地化的聊天记录分析工具，通过 AI Agent 回顾你的社交记忆。

AgentHub is the LLM API Hub for the Agent era, built for high-precision autonomous agents. (GPT-5.4/Claude 4.6/Gemini 3.1)

AI agents running research on single-GPU nanochat training automatically

把Openclaw 变成小红书运营助手，帮你分析、选题、创作、复盘、复刻，甚至全面托管

Kimi-Vendor-Verifier

ASTRA is an end-to-end system for synthesizing agentic trajectories and rule-verifiable environments for SFT and RL training, developed by Beike Language and Intelligence (BLI).

给 AI 一篇文章，自动生成一款可以玩的 RPG Maker MZ 游戏

OneEval: Open EvalScope evaluation artifacts for LLMs — subset breakdowns, pass@k curves, and reproducible evaluation protocols.

Chat-channel ↔ ACP agent gateway with scheduler

A lightweight, AI-native training framework for large language models. Designed for fast iteration, reproducible experiments, and modular configuration across SFT, RLVR, and evaluation workflows.

A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

We Speech Toolkit, LLM based Speech Toolkit for Speech Understanding, Generation, and Interaction