ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits.

Telegram ↔ tmux bridge for Claude Code: 1 topic = 1 window = 1 session

A better /goal

ToolJet is the open-source foundation of ToolJet AI - the enterprise app generation platform for building internal tools, dashboard, business applications, workflows and AI agents 🚀

A free, open source, and extensible speech-to-text application that works completely offline.

A powerful, flexible, Markdown-based authoring framework.

🎯 All you need. Nothing you don't. Open source project management that works for you, not against you.

Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference

Official DESIGN.md files published by companies themselves. First-party design systems that AI agents read to generate consistent UI.

An AI Gateway, registry, and proxy that sits in front of any MCP, A2A, or REST/gRPC APIs, exposing a unified endpoint with centralized discovery, guardrails and management. Optimizes Agent & Tool c…

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

The batteries-included agent harness.

A Model Context Protocol server for converting almost anything to Markdown

Build, Manage and Deploy AI/ML Systems

😎 A curated list of awesome MLOps tools

Easy Data Preparation with latest LLMs-based Operators and Pipelines.

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

🗂️ Explore Dosu assets here

💬 Dosu Community for questions, feature requests, bug tracking, and roadmap discussion

AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,005+ agentic skills. Includes CLI, local MCP, cat…

UniClawBench project page: https://uniclawbench.github.io/

Pure Javascript OCR for more than 100 Languages 📖🎉🖥

A visualization tool that replays coding-agent sessions on a 3D map of your codebase.

An open source design system that's fully customizable and agent ready

TabFM (Tabular Foundation Model) is a pretrained tabular foundation model developed by Google Research for tabular data regression and classification.

Paste any GitHub URL → interactive architecture map. See how files connect, find what breaks if you change something. No install, no accounts — runs entirely in your browser.

The Security Toolkit for LLM Interactions

OpenWiki is a CLI that writes and maintains agent documentation for your codebase.

Hebrew PHI identification and redaction toolkit

Light, fluffy, and always free - The AWS Local Emulator alternative