HYSEN LABS DIRECTORY

#AI Agents

Capability tag · curated repositories and deep analysis.

4,545 curated open-source projects

mem-eval-suite

LoCoMo_refined

★ 672

LoCoMo Refined: Recalibrating LoCoMo with stricter LLM judging and a cleaned dataset.

Python10 forks

lencx

Minke

★ 671

🐳 DeepSeek Harness Desktop

TypeScript70 forks

yejiming

Create your own AI characters and step into their story worlds. Chat, go on adventures and dive into stories with characters, building bonds through every interaction. Supports DeepSeek Harness plugins.

TypeScript62 forks

AgentTeam-TaichuAI

ScienceClaw

★ 671

ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, adopting a completely new architecture beyond OpenClaw. It offers stronger security, better transparency, and a more user-friendly experience.

Python73 forks

simonlin1212

vibe-astock

★ 670

A-share short-term review dashboard covering limit-up pools, consecutive-limit ladders, dragon-tiger lists and sector capital flow in one screen. Derived sentiment metrics (profit effect, promotion rate, ladder gaps, sentiment cycle) are computed locally, not by AI; AI only turns the data into readable commentary. Runs fully locally, works with Claude/Codex subscriptions without an API key.

Python181 forks

narumiruna

pi-extensions

★ 669

A monorepo of Pi Coding Agent extensions

TypeScript134 forks

fufankeji

deepseek-harness-studio

★ 669

A no-code desktop client for DeepSeek Harness. One-click launch on Windows and macOS, with built-in plugin discovery, trending plugin push, one-click install and management, AI recommendations and visual enhancements.

TypeScript71 forks

corespeed-io

wechatbot

★ 668

WeChat iLink Bot SDK for OpenClaw/AI Agent

TypeScript90 forks

Calix-L

DanKS

★ 667

RL‑Empowered Small‑Scale Competitive Guandan Agent

Python17 forks

arinspunk

claude-talk-to-figma-mcp

★ 667

A Model Context Protocol (MCP) that allows Claude Desktop and other AI tools (Claude Code, Cursor, Antigravity, etc.) to read, analyze, and modify Figma designs

TypeScript131 forks

scanaislop

aislop

★ 667

Catch and fix the code-quality issues AI coding agents leave behind - dead code, unsafe casts, swallowed errors, duplication, security risks, and more. 50+ deterministic rules across 10 language targets, with CLI, CI, and GitHub Actions. No LLM at runtime. MIT.

TypeScript36 forks

MORTEN-BUUR

nordef-matrix-open-control

★ 667

NORDEF Matrix Open Control: model-independent AI safety belt with 0/1/2 decisions, Ed25519 root gate, replay protection, evidence chain, and incident-pattern eval bank

Python2 forks

Snailclimb

AIGuide

★ 667

A guide to AI application development, hands-on AI programming and interviews, covering core technologies and engineering practices such as LLM, Agent, RAG, MCP, Claude Code and Codex.

Unknown74 forks

agent-sh

computer-use-linux

★ 666

Linux desktop control over MCP — AT-SPI, GNOME Shell, Wayland portals, ydotool

Rust74 forks

henrydaum

second-brain

★ 666

Second Brain is an agentic framework that acts as an operating system, using local file intelligence, workflow automation, and LLMs to complete tasks and communicate over multiple modalities and messaging platforms.

Python85 forks