Stars
Ephemeral Workspaces, durable shared history. LayerFS gives every agent a complete, writable filesystem Workspace over shared committed history, without copying the base. Agents work in parallel, c…
A simple, decentralized mesh VPN with WireGuard support.
塔台 — 原生 SwiftUI iOS App，在本机管理机场订阅与自有节点，生成 Surge / Clash / Shadowrocket / Loon / Quantumult X 配置
A local AI gateway for AI agents, unifying your subscriptions and API providers with smart routing and on-device privacy protection.
Self-organizing AI second brain for Obsidian + Claude Code. Drop any source and Claude reads, links, and files it into one connected knowledge graph of plain Markdown you own. AI note-taking, perso…
Didasync/Tickticksync is a TickTick synchronization plugin that syncs TickTick tasks into Obsidian, or edits native Obsidian tasks to sync them back to TickTick, enabling two-way sync management. I…
DeepSeek Harness: Everything is a Plugin.
ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits.
oiia — hosted agent sessions that execute wherever you point them: a cloud sandbox, an SSH host, or a machine with no public IP. Multi-agent, durable across reloads, installable as a PWA. Built by …
Fast, accurate & comprehensive text measurement & layout
Switch between Claude accounts, Gemini, Copilot, OpenRouter (300+ models) via CLIProxyAPI OAuth proxy. Visual dashboard, remote proxy support, WebSearch fallback. Zero-config to production-ready.
archersama / harbor
Forked from harbor-framework/harborHarbor is a framework for running agent evaluations and creating and using RL environments.
Framework for evaluating and improving agents
A lightweight harness designed to be simple to use, efficient, universially compatible with any coding agent to evaluate them over a broad set of coding tasks and languages.
A convenient and user-friendly anime-style image data processing library that integrates various advanced anime-style image processing models
Teams-first Multi-agent orchestration for Claude Code
Show usage stats for OpenAI Codex and Claude Code, without having to login.
beatkind / watchtower
Forked from containrrr/watchtowerA process for automating Docker container base image updates.
Code distribution for arXiv paper: Beyond Line-Level Filtering for the Pretraining Corpora of LLM
Extending the Context of Pretrained LLMs by Dropping Their Positional Embedding
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot, dete…
Accelerating MoE with IO and Tile-aware Optimizations