opendraft
Free & open-source AI research-paper writer: 19 agents draft 20k-word academic papers in ~10 min with citations verified against CrossRef/OpenAlex/Semantic Scholar. Export PDF/Word/LaTeX. Hosted at openpaper.dev
HYSEN LABS DIRECTORY
Capability tag · curated repositories and deep analysis.
Free & open-source AI research-paper writer: 19 agents draft 20k-word academic papers in ~10 min with citations verified against CrossRef/OpenAlex/Semantic Scholar. Export PDF/Word/LaTeX. Hosted at openpaper.dev
The practical implementation of Aspire using Microservices, AI-Agents
State machine guardrails for AI agents
A small desktop robot that brings an AI coding assistant to life, physically acting out when it reads files, thinks, writes code, and finishes work.
900+ pure-markdown skills for autonomous AI research, organized as 9 freely-composable packages over a 4-layer hierarchy (Campaign → Strategy → Tactic → SOP). Non-linear orchestration with backtracking, 6 MCP integrations. The AI is the researcher — you set the direction.
A multimodal AI agent for geospatial data analysis and interactive visualization
A swarm orchestration system in Codex - use less quota, get more done.
A Xiaohongshu CLI for searching, analyzing and automating Xiaohongshu content. Built for AI agents.
II-Researcher: a new open-source framework designed to aid building search / research agents
Official Java SDK for the Agent2Agent (A2A) Protocol
lunar.dev: Agent native MCP Gateway for governance and security
Prove and remove accidental codebase complexity without breaking behavior.
A VSCode extension that lets you find and install Agent Skills and MCP Apps to use with GitHub Copilot, Claude Code, and Codex CLI.
A tutorial series on "langent", a portmanteau of "lang" and "agent".
Open source IM with AI-powered live chat, email, ticket support and omni-channel customer service; an alternative to Slack plus Zendesk/Intercom/HubSpot/Ada/Decagon/Sierra.
Keep Agent Notes the way the DeepSeek team does: record decisions, trade-offs and verification in one place so they're still traceable six months later. Can be layered onto any repository.
⚡ Blitz Strike — a universal MCP penetration-testing toolbelt. Structured methodology: reconnaissance & attack-surface mapping, source-to-sink analysis, and live validation. 57 escalation chains, 130-tool catalog, intelligence data layer. One server, every agent.
This repository provides a benchmark for prompt injection attacks and defenses in LLMs
Design, conduct and analyze results of AI-powered surveys and experiments. Simulate social science and market research with large numbers of AI agents and LLMs.
Open-source, channel-native agent gateway for Slack. Route team threads to Claude Code, Codex, OpenCode, Docker, HTTP agents, and custom CLIs with policy, approvals, memory, audit logs, and artifacts.