Starred repositories
A micro-benchmark suite to assess the stability of taint-analysis tools for Android
OpenHarmony Test Framework | OpenHarmony 自动化测试框架
Flame Chasoid for hmz: the flame chase and its variants (agent cleanup, fixed interrupt, parallel lanes) as subflows of one flow.
Triton is a dynamic binary analysis library. Build your own program analysis tools, automate your reverse engineering, perform software verification or just emulate code.
CyberGym-E2E is a large-scale benchmark built from real-world vulnerabilities in widely used open-source projects to evaluate AI agents' end-to-end cybersecurity capabilities, from discovering vuln…
An open-source graph engineering runtime that keeps orchestration in TypeScript and delegates semantic work to replaceable Agent runtimes.
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
Meta-Harness: 76.4% on Terminal-Bench 2.0 (Claude Opus 4.6)
[NeurIPS 2026] Training with Harnesses: On-Policy Harness Self-Distillation for Complex Reasoning
Let Pi control your apps on MacOS & Windows
Open-source AI reverse-engineering agent platform and MCP server for Ghidra, Frida, x64dbg and Rizin — automated PE/APK/binary analysis, CTF and malware research, with 100+ MCP tools and a 194-arti…
Run Claude Code dynamic workflows on a local Codex (GPT) backend, plus an interactive run viewer
Fusing automated UI testing with scripts (property-based testing) for effectively fuzzing Android apps
Waydroid uses a container-based approach to boot a full Android system on a regular GNU/Linux system like Ubuntu.
The code of Passing the Turing Test on Screen
CUA-Gym-Hub: mock web apps as reproducible RL training environments for computer-use agents
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"
[NeurIPS'26] "Autonomous Continual Learning for Environment Adaptation of Computer-Use Agents"
slime is an LLM training framework for RL Scaling.
Post-training framework for large models, from new objectives to new rollout systems.
Official implementation for "Android in the Zoo: Chain-of-Action-Thought for GUI Agents" (Findings of EMNLP 2024)
Distributed reliable key-value store for the most critical data of a distributed system
ChatGPT Plus/Team/Pro 订阅协议端到端重放工具集 · hCaptcha 视觉求解器 · 反欺诈机制实证研究 / End-to-end protocol replay toolkit for ChatGPT Plus/Team/Pro subscription with from-scratch hCaptcha solver and empirical anti-frau…