HYSEN LABS DIRECTORY

#Large Language Models

Capability tag · curated repositories and deep analysis.

6,244 curated open-source projects
raphaelmansuy

code2prompt

★ 888

Code2Prompt is a powerful command-line tool that simplifies the process of providing context to Large Language Models (LLMs) by generating a comprehensive Markdown file containing the content of your codebase. ⭐ If you find Code2Prompt useful, consider giving us a star on GitHub! It helps us reach more developers and improve the tool. ⭐

Python58 forks6 min read
shaneholloman

mcp-knowledge-graph

★ 888

MCP server enabling persistent memory for Claude through a local knowledge graph - fork focused on local development

JavaScript102 forks7 min read
invergent-ai

surogate

★ 888

Train and serve LLMs at extreme speed and massive throughput.

C++15 forks6 min read
evilsocket

audit

★ 888

An 8-stage vulnerability-discovery agent.

Python119 forks5 min read
wecode-ai

Wegent

★ 888

Plan, build, and deliver with an open-source, self-hostable AI workspace for coding, collaboration, and automation.

TypeScript148 forks6 min read
★ 888

Some commonly used research experiences and processes are encapsulated into Agent skills.

Python107 forks9 min read
huggingface

llm-ls

★ 887

LSP server leveraging LLMs for code completion (and more?)

Rust73 forks7 min read
utensils

mcp-nixos

★ 886

MCP-NixOS - Model Context Protocol Server for NixOS resources

Python51 forks6 min read
alisaitteke

photoshop-mcp

★ 886

MCP server for Adobe Photoshop — 102 tools, recipe workflows, generative AI, standalone web UI. Control Photoshop from Cursor, Claude, or natural language.

TypeScript86 forks6 min read
karanb192

itr-wala

★ 886

File your Indian income tax return (ITR) from your terminal. Deterministic tax engine, both regimes, AY 2026-27. Claude Code / Codex / Gemini skill.

Python129 forks7 min read
★ 885

Official repository of the Tencent Cloud Intelligent Penetration Hackathon. Showcases top open-source projects of LLM-based autonomous penetration agents, including multi-agent collaboration, automated penetration, AI-driven offensive security, and intelligent attack-defense solutions.

Python103 forks5 min read
Salomondiei08

oh-my-hermes

★ 885

An opinionated workflow layer for building, shipping, and operating apps with Hermes Agent

Shell80 forks4 min read
eastriverlee

LLM.swift

★ 884

LLM.swift is a simple and readable library that allows you to interact with large language models locally with ease for macOS, iOS, watchOS, tvOS, and visionOS.

Swift127 forks5 min read
★ 884

The #1 open-source SWE-bench Verified implementation

Python156 forks5 min read
★ 884

Brand building skills for Claude Code and AI agents. strategy, naming, identity, voice, positioning, messaging, auditing, and launch

Shell109 forks6 min read
taracodlabs

aiden

★ 884

Aiden — Autonomous AI agent that operates your computer with prompts: browser control, terminal execution, workflows, tools, recovery systems, and persistent memory. Built solo. AGPL-3.0.

TypeScript151 forks6 min read
★ 884

Managed Claude Code instruction deployment with safe CLI recovery and an unsigned macOS/Windows desktop beta.

Python152 forks5 min read
★ 883

Multiple modes built on dsh web for authorized red-team security research, covering penetration testing, red-team assessment and code auditing. Not for illegal use. Open for customization so each module can carry its own logic.

Python138 forks5 min read
AgriciDaniel

jev-seo

★ 883

Live SEO audit for any website from one homepage URL, judged by Jev. PDF, XLSX and Markdown reports.

Python131 forks6 min read
riponcm

projectmem

★ 882

Open-source coding agents memory. Records issues, attempts, fixes and decisions, then warns your agent before it repeats an approach that already failed. Native MCP server for Claude Code, Cursor, Antigravity and Codex. 100% local, no cloud, no telemetry. MIT.

Python55 forks5 min read