Kheish Persistent agent runtime and control plane for long-lived, tool-using AI workflows.   --- Kheish enforces one rule: Everything else in this README is a consequence of that single invariant.

AI-powered penetration testing assistant using local LLM on linux (Parrot OS) --- Metatron is a CLI-based AI penetration testing assistant that runs entirely on your local machine — no cloud, no API keys, no subscriptions. It runs real recon tools (nmap, whois, whatweb, curl, dig, nikto), feeds all results to a locally running AI model, and the AI analyzes the target, identifies vulnerabilities, suggests exploits, and recommends fixes.

This is a port of BlinkDL/RWKV-LM to ggerganov/ggml. Besides the usual FP32, it supports FP16, quantized INT4, INT5 and INT8 inference.

This is the official repository for ICLR 2025 paper "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Magpie generates high-quality alignment data by prompting aligned LLMs with their pre-query templates.

go-agent is a Go framework for building AI agents with pluggable LLM providers, memory, file context, guardrails, UTCP tool orchestration, and multi-agent coordination. Use it when you want agent runtime pieces that stay idiomatic in Go: For this repository: The module currently targets Go 1.25.10.

RouteLLM is a framework for serving and evaluating LLM routers. [Blog ] [Paper ] Our core features include: From PyPI From source Let's walkthrough replacing an existing OpenAI client to route queries between LLMs instead of using only a single model.

MASFactory is a graph-centric framework for orchestrating Multi-Agent Systems with Vibe Graphing: Start from intent, generate a graph design, preview and refine it in a visual environment, compile it into an executable workflow, and trace node states, messages, and shared state at runtime. Turn natural-language intent into a structural design, then iteratively converge to an executable, reusable workflow.

Designed for research exploration and industrial prototyping, UltraRAG standardizes core RAG components (Retriever, Generation, etc.) as independent MCP Servers, combined with the powerful workflow orchestration capabilities of the MCP Client. Developers can achieve precise orchestration of complex control structures such as conditional branches and loops simply through YAML configuration.

A self-evolving librarian agent for document collections. AutoRAG searches your PDFs, wikis, notes, research papers, and knowledge bases — then curates the results into clean, numbered knowledge units.

This monorepo contains a set of dev-friendly, framework agnostic components offering 3 main capabilities: Framework integration packages: The library offers a set of small, focused building blocks. Purpose: turn messy model output into typed PHP data.

A self-contained image bundles the tool + the Claude Code and Codex CLIs. You log in once and the sessions persist in named volumes — no re-login on later runs.

Towards Async, Omni-Modal RL at Scale, Just Relax. 📖 English | 📖 中文 Relax (Reinforcement Engine Leveraging Agentic X-modality) is a high-performance reinforcement learning post-training framework open-sourced by the Xiaohongshu AI Infra Team for multimodal large language models.

React Native binding of llama.cpp - LLM inference in C/C++ Key Features: llama.rn downloads the pre-built ios/rnllama.xcframework and android/src/main/jniLibs from the matching GitHub release during postinstall. Existing downloads are reused, and each archive is verified with SHA-256 before extraction.

⚡LLM Zoo is a project that provides data, models, and evaluation benchmark for large language models.⚡ [[Tech Report]](assets/llmzoo.pdf) technology gifted by the creator. For example, many pioneers have made great efforts to spread the use of light bulbs and vaccines to developing countries.

DocStrange converts documents to Markdown, JSON, CSV, and HTML quickly and accurately. --- August 2025 --- Convert and extract data from PDF, DOCX, images, and more into clean Markdown and structured JSON.

🦞 OpenClaw is a great personal AI assistant — connecting all major IMs as conversation channels, supporting any LLM, running autonomously 24/7. But when we bring it into an enterprise context, new challenges naturally emerge: data scattered across individual accounts, no budget guardrails, output that stops at plain text, high-risk actions without an approval gate.

Convert any image, PDF or Office document to Markdown text or JSON structured document with super-high accuracy, including tabular data, numbers or math formulas. The API is built with FastAPI and uses Celery for asynchronous task processing.

Augustus is a Go-based LLM vulnerability scanner for security professionals. It tests large language models against a wide range of adversarial attacks, integrates with 28 LLM providers, and produces actionable vulnerability reports.

What is GitMCP • Features • Getting Started • How It Works • Badge • Examples • FAQ • Privacy • Contributing • License Stop vibe-hallucinating and start vibe-coding! GitMCP is a free, open-source, remote Model Context Protocol (MCP) server that transforms any GitHub project (repositories or GitHub pages) into a documentation hub.

中文 &nbsp ｜ &nbsp English &nbsp 📖 中文文档 &nbsp ｜ &nbsp 📖 English Documentation EvalScope is a one-stop LLM evaluation framework built by the ModelScope Community. Just one command to start — it supports model capability evaluation, inference performance stress testing, and result visualization.