Sub2API is an open-source relay platform that unifies Claude, OpenAI, Gemini, and Antigravity subscriptions into a single endpoint. It supports account sharing and cost-sharing, with seamless nativ…

本地 PaddleOCR-VL OCR 插件，支持文字定位与原图翻译。

Race-resistant root-bounded filesystem primitives for Node.js.

Scripts for agents, shared between my repositories.

Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI…

Point at any URL/YouTube/Podcast or file. Get the gist. CLI and Chrome Extension.

Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize

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…

Agents' Last Exam

LEAKED SYSTEM PROMPTS FOR CHATGPT, CLAUDE, GEMINI, GROK, PERPLEXITY, CURSOR, LOVABLE, REPLIT, AND MORE! - AI SYSTEMS TRANSPARENCY FOR ALL! 👐

Search and retrieval for AI agents

Native macOS semantic search over your local files - text, images, audio, video in one vector space, on-device on Apple silicon.

Χ-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?

The first benchmark that asks code agents to build agents.

AWS ECS/Fargate execution backend for Harbor benchmarks

Semantic version control => entity-level diffs, blame, and impact analysis on top of git. 26 languages via tree-sitter. Built for coding agents.

Air-gapped deployment toolkit for Jina AI models

AI agents now operate with authority. Authority without discipline is how complex systems fail. Nuclear’s control loop, ported to AI-assisted software engineering.

A digital camera you can build yourself with Codex.

Can Language Models Rebuild Programs From Scratch?

An agent for auditing repositories of traces for violations of safety properties. Automatically finds cheating (task-level gaming and harness-level cheating) on top benchmarks.

OpenAI Plugins

Secure, Fast, and Extensible Sandbox runtime for AI agents.

SAE (Self AI-agent-evals Evaluator): turn agent evaluation into self-improving infrastructure with Harbor benchmarks, agent trials, ATIF trace replay, parity review, and self-host eval loops.

Harbor Pro extends Harbor into a local-first eval runtime: richer job/trial/review workflows, ATIF telemetry, parity reports, expanded sandboxes, and self-host registry/ops.