HYSEN LABS DIRECTORY

#AI Agents

Capability tag · curated repositories and deep analysis.

4,545 curated open-source projects

sxhxliang

agent-studio

★ 511

AgentX is a GPU-accelerated, cross-platform desktop application that brings AI agents to your workflow.

Rust55 forks

iusztinpaul

designing-real-world-ai-agents-workshop

★ 511

Hands-on workshop: Build a multi-agent AI system from scratch — Deep Research Agent + Writing Workflow served as MCP servers. Includes code, slides, and video

Python139 forks

tryproduck

produck-skills

★ 510

Agent skills to help you build products your users love.

HTML10 forks

mll-lab-nu

VAGEN

★ 510

World model reinforcement learning for multi-turn VLM agents. RL for vision framework (NeurIPS 2025).

Python61 forks

datadrivenconstruction

cad2data-Revit-IFC-DWG-DGN

★ 510

Workflow for AI Agents enables automated conversion of CAD files (such as `.rvt`, `.ifc`, `.dwg`) using command-line converters on a local Windows machine

Jupyter Notebook107 forks

huggingface

funes

★ 510

Durable, searchable memory of your past agent sessions.

Rust44 forks

Callous-0923

A 36-chapter full-stack AI Agent course: from the ReAct loop to reverse-engineering Claude Code, MCP/A2A protocols, RAG, DSPy and production observability — all as runnable Python files, interview-oriented.

HTML57 forks

cordum-io

cordum

★ 509

The action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence.

Go34 forks

bytedance

vArmor

★ 509

vArmor is a cloud-native container hardening system that leverages AppArmor/BPF/Seccomp and NetworkProxy technologies to enforce access control from system calls to application protocols — protecting workloads including AI Agents.

Go69 forks

justinwetch

HIGAgentSkills

★ 509

Apple Human Interface Guidelines for Agents

Python22 forks

slowmist

slowmist-agent-security

★ 509

SlowMist Agent Security Skill: A comprehensive security review framework for AI agents operating in adversarial environments. Core principle: Every external input is untrusted until verified.

Unknown30 forks

Justin0504

Aegis

★ 509

Runtime policy enforcement for AI agents. Cryptographic audit trail, human-in-the-loop approvals, kill switch. Zero code changes.

TypeScript47 forks

Forsy-AI

biosecurity-agent

★ 508

AI agent that builds a live biosecurity world around any target.

TypeScript22 forks

echoVic

orca-agent

★ 508

Orca is a DeepSeek-native coding agent.

Rust4 forks

HKUDS

CatchMe

★ 508

"CatchMe: Make Your AI Agents Truly Personal"

Python82 forks

chattymin

PokeTokenBar

★ 508

Use your tokens to raise, evolve, and collect Pokémon! 🥚

Swift144 forks

huawei-csl

KVarN

★ 508

KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.

Python37 forks