HYSEN LABS DIRECTORY

#Large Language Models

Capability tag · curated repositories and deep analysis.

6,244 curated open-source projects
tomascupr

sandstorm

★ 450

Run Claude agents in secure cloud sandboxes — via API, CLI, or Slack. One call. Full agent. Zero infrastructure.

Python42 forks9 min read
★ 450

VexJoy AI Agent with Intelligent Routing - /do routes plain-English requests to the right specialist agent and gates the work with reviews, tests, and a learning loop.

Python51 forks8 min read
smithersai

smithers

★ 449

Agent workflows with full observability and time travel: watch every step live, rewind, fork, replay any run. Claude Code, Codex, Gemini, any model or harness. The same workflow runs across Claude Code, Codex, Pi, AI SDK models, and remote sandboxes.

JavaScriptAI & Machine Learning50 forks4 min read
canwhite

AgentEval

★ 449

The agent responsible for conducting the agent evaluation

Rust3 forks7 min read
ChatLunaLab

chatluna

★ 449

A bot plugin for LLM chat with multi-model integration, extensibility, and various output formats.

TypeScript52 forks6 min read
jagmarques

asqav-sdk

★ 449

Python and TypeScript SDKs for verifiable evidence of AI agent actions. Signed receipts, policy enforcement, audit trails. Works with LangChain, CrewAI, MCP.

Python30 forks6 min read
Community-Access

accessibility-agents

★ 448

Accessibility review agents for Claude Code, GitHub Copilot, and Claude Desktop. Eleven specialists that enforce WCAG 2.2 AA compliance so AI coding tools stop generating inaccessible code.

JavaScript53 forks6 min read
pzqpzq

LSF_MDia

★ 448

[ICML 2026] Let LLMs invent and evolve languages for efficient reasoning.

Python14 forks7 min read
AIProxyTeam

AIProxySwift

★ 448

Swift clients for AI providers. You can make requests straight to the provider or proxied through our abuse protection backend

Swift101 forks7 min read
GresonKwan

JobOK

★ 448

Job OK: an evidence-driven job-search Agent Skill for Chinese-speaking job seekers, supporting strength discovery, job matching, resume optimization, interview training, and application tracking.

Python5 forks7 min read
bam-bam-2

solo-skills

★ 448

A productivity kit for solo entrepreneurs - automated 58 tasks without employees, releasing 38 ready-to-use AI agent skills (plus 19 execution scripts).

Python102 forks7 min read
exploitbench

exploitbench

★ 448

ExploitBench measures how far AI agents climb, from reaching vulnerable code, to triggering the bug, to building exploit primitives, to arbitrary code execution.

Python49 forks6 min read
AndraxDev

speak-gpt

★ 447

Your personal voice assistant based on OpenAI ChatGPT.

Kotlin81 forks7 min read
★ 447

Claude Code skill for OWASP security best practices (2025-2026). Includes Top 10:2025, ASVS 5.0, Agentic AI security, and 20+ language-specific security quirks.

Unknown39 forks6 min read
ghostsecurity

skills

★ 446

Ghost Security's collection of AppSec skills for AI coding agents

Python27 forks6 min read
pranshuchittora

simvyn

★ 446

Universal mobile devtool for Agents & Humans - control iOS Simulators, Android Emulators, and real devices from a single dashboard and CLI

TypeScript32 forks7 min read
chr15m

runprompt

★ 446

Run LLM prompts from your shell

Python18 forks5 min read
poolsideai

pool

★ 445

pool is Poolside’s coding agent that runs in your terminal or integrates with any ACP-compatible editor

Unknown27 forks7 min read
★ 445

Give Claude Code's ultracode mode to ANY model you already pay for. A tiny local proxy + one config.json. Point your AI at AGENTS.md and it sets itself up.

Python41 forks7 min read
momori777

Artemis

★ 445

An uncensored, fully offline AI-girlfriend harem: OpenClaw/Claude Code plus a local LLM, GPT-SoVITS voice, ComfyUI image generation, Live2D, a desktop pet, SillyTavern character-card import, and a frontend. Dual channels for QQ and Telegram, with dynamic 8GB VRAM scheduling and mem0/Qdrant; can run fully offline.

Python25 forks6 min read