Pentagi is a fully autonomous AI agents system designed to execute complex penetration testing tasks. Developed by vxcontrol, the project leverages artificial intelligence to automate advanced security testing workflows.…
→ View original sourceAn Open Source Machine Learning Framework for Everyone
→ View original sourceLLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional RAG (retrieve-and-answer from scratc...
→ View original sourceNever stop coding. Free MIT AI gateway: one endpoint, 352 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline
→ View original sourceContext window optimization for AI coding agents that reduces tool output by 98% through sandboxing, persists session memory, and enforces routing across 17 platforms using MCP and hooks. Read original
→ View original sourceOpenAI has released a skills catalog designed for Codex. This repository serves as a resource for managing and implementing specific capabilities within the Codex model. Read original
→ View original sourceOpen-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
→ View original sourceThe open-source project browser-use enables AI agents to interact with and automate tasks on websites. It provides a framework for making web content accessible to AI, simplifying online automation workflows. The project…
→ View original sourceThe blender-mcp plugin enables control of Blender 3D software through any language model (LLM), allowing users to manipulate 3D objects and scenes via natural language prompts. Developed by ahujasid, it acts as a bridge …
→ View original sourceSGLang is a high-performance serving framework for large language models and multimodal models.
→ View original sourceAnthropic has released a public GitHub repository dedicated to Agent Skills. This repository provides resources and implementations for enhancing the capabilities of AI agents. Read original
→ View original sourceClaude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows through natural lang…
→ View original sourceruflo is an agent meta-harness designed for deploying intelligent multi-player swarms and coordinating autonomous workflows. It enables the creation of conversational AI systems with adaptive memory and self-learning cap…
→ View original sourceThis repository offers a structured workflow for academic research using Claude Code, covering research, writing, review, revision, and finalization phases. It aims to streamline scholarly work through a systematic, iter…
→ View original sourceNVIDIA has released SkillSpector, a security scanner designed to detect vulnerabilities and malicious patterns in AI agent skills before installation. The tool identifies security risks including prompt injection, data e…
→ View original sourcecc-switch is a cross-platform desktop All-in-One assistant designed for various AI agents, including Claude Code, Codex, OpenCode, OpenClaw, Grok Build, and Hermes Agent. The project provides a centralized interface for …
→ View original sourceThe GitHub project minimind by jingyaogong demonstrates training a 64M-parameter large language model (LLM) from scratch in approximately 2 hours. This Python-based implementation highlights efficient model training tech…
→ View original sourceHeretic is a fully automatic censorship removal system for language models, developed by p-e-w and hosted in the p-e-w/heretic repository on GitHub. It aims to eliminate content filters programmatically, enabling unrestr…
→ View original sourceThe ggml-org/llama.cpp repository provides a C/C++ implementation for large language model inference, offering optimized performance across various hardware platforms. It enables developers to run
→ View original sourceCrawl4AI is an open-source web crawler and scraper designed to be LLM-friendly, enabling efficient data extraction for large language model applications. The project provides a Python-based solution optimized for AI work…
→ View original sourceGitNexus: The Zero-Server Code Intelligence Engine - GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a git repository (Github, Gitlab, Azure, Local) or ZI
→ View original sourceLiveKit/agents is a framework designed for constructing real‑time voice AI agents, integrating audio and video capabilities. It provides developers with tools to build interactive, multimodal voice applications. The repo…
→ View original sourceK-Dense-AI/scientific-agent-skills is an Agent Skills library that transforms AI agents into scientific research assistants, offering 163 validated skills and access to 100+ scientific databases spanning biology, chemist…
→ View original sourceOpenMontage is the world's first open‑source, agentic video production system. It provides 12 production pipelines, over 100 tools, and more than 700 agent skill and production‑knowledge files. Users can transform an AI …
→ View original sourceClaude-obsidian is an open-source personal knowledge management tool that integrates Claude Code with Obsidian to create a self-organizing AI second brain. It automatically processes sources into a connected knowledge gr…
→ View original sourceOpenHuman is a personal AI superintelligence project by tinyhumansai that builds a local-first memory of the user's life and orchestrates agent fleets and workflows for deep research. It is designed as a personal brain t…
→ View original sourceUse Claude Code, Codex, Pi, and OpenCode for free (1.3B+ free tokens) from your terminal, app, IDE, or phone like OpenClaw (voice supported + ToS friendly)
→ View original sourceOpenAI's Codex is a lightweight coding agent designed to run directly in the terminal, enabling automated code generation and execution. It is an open‑source project hosted on GitHub. Read original
→ View original sourceThe repository provides 817 structured cybersecurity skills for AI agents, mapped to six major frameworks including MITRE ATT&CK, NIST CSF 2.0, and MITRE ATLAS. It follows the agentskills.io standard and is compatible wi…
→ View original sourceHere's a thinking process: 1. **Analyze User Input:** - **Role:** Technical news summarizer - **Task:** Condense provided news into brief HTML summary - **Input:** A news item with title, source, URL, author, date, and d…
→ View original sourceRAGFlow is an open-source Retrieval-Augmented Generation (RAG)
→ View original sourceJuliusBrussee's caveman project reduces token usage by 65% through simplified, caveman-like communication patterns. This approach minimizes token count while maintaining functionality. The technique leverages minimalisti…
→ View original sourceUnsloth provides a local UI for running and training large language models (LLMs) and diffusion models, supporting frameworks like Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, and FLUX. It enables users to fine-tu…
→ View original source🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
→ View original sourceThe open-source app everyone uses to manage agents at work
→ View original sourceDSPy: The framework for programming—not prompting—language models
→ View original sourceZhuLinsen's daily_stock_analysis is an LLM-powered system for multi-market stock analysis, integrating real-time market data, news, and decision dashboards with automated notifications. It supports zero-cost scheduled ex…
→ View original sourceCherryHQ launched CherryStudio, an AI productivity platform offering smart chat, autonomous agents, and over 300 assistants that provide unified access to frontier large language models. The tool aims to streamline workf…
→ View original sourceAgent skill that removes signs of AI-generated writing from text
→ View original sourceAgent-Reach is a command-line interface that equips AI agents with the ability to read and search across major internet
→ View original sourceThe voice-pro project by abus-aikorea offers a Gradio WebUI for creators and developers, integrating advanced TTS engines (Edge-TTS, kokoro) and zero-shot voice cloning (E2 & F5-TTS,
→ View original sourceDeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.
→ View original sourceOpenWork is an open-source project by different-ai that serves as an alternative to Claude Cowork, utilizing opencode as its underlying engine. It is built with TypeScript and has gained traction on GitHub's trending rep…
→ View original sourceGet up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
→ View original sourceOpenViking is a self-evolving Context Database designed for AI agents, integrating memory, knowledge retrieval (RAG), and skills into a unified framework. It enables dynamic adaptation and context management for autonomo…
→ View original sourceA TypeScript-based proxy service aggregating free tiers of 28 LLM providers through a single OpenAI-compatible endpoint, featuring smart routing, failover, and secure key management. Supports additional custom endpoints …
→ View original sourcePageIndex, developed by VectifyAI, is a document indexing solution designed for vectorless, reasoning-based retrieval-augmented generation (RAG) systems. Unlike traditional RAG approaches that rely on vector embeddings, …
→ View original sourceOpen-source AI penetration testing tool to find and fix your app’s vulnerabilities.
→ View original sourceAlibaba's open-code-review is a hybrid architecture code review tool designed for large-scale applications. It combines deterministic pipelines with LLM agents, offering precise line-level comments and built-in fine-tune…
→ View original sourceRTK is a CLI proxy written in Rust designed to reduce LLM token consumption by 60-90% for common development commands. It is distributed as a single binary with zero dependencies. Read original
→ View original sourceoh-my-pi is an AI coding agent designed for the terminal, featuring hash‑anchored edits and an optimized tool harness. It integrates LSP support, Python execution, browser automation, and sub
→ View original sourceFacebook has released Astryx, an open-source design system that is fully customizable and built to be agent-ready. Developed in TypeScript, Astryx aims to provide developers with a flexible and extensible foundation for …
→ View original sourceJCodesMore introduced an AI website cloner template that enables cloning any site with a single command using AI coding agents. Implemented in TypeScript and published on GitHub, the tool simplifies website replication. …
→ View original sourceVery low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces
→ View original sourceWrenAI is an open-source Generative BI (GenBI) solution designed for AI agents to facilitate governed text-to-SQL transformations. By utilizing an open context layer, it converts natural-language queries into reliable da…
→ View original sourcekvcache-ai/ktransformers is a flexible framework designed to explore heterogeneous optimizations for LLM inference and fine‑tuning. It provides tools to experiment with various optimization strategies across different ha…
→ View original sourceUse Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
→ View original sourceSigNoz is an open-source observability platform that integrates with OpenTelemetry to provide logs, metrics, and traces in a unified interface. It supports APM, distributed tracing, log management, and infrastructure mon…
→ View original sourceLobeHub functions as a Chief Agent Operator, orchestrating AI agents for continuous 24/7 operations. It facilitates hiring, scheduling, and reporting across the entire AI team, ensuring seamless task management and perfo…
→ View original sourcePostHog is an open-source platform for building self-driving products, offering developer tools
→ View original sourceMemvid is a memory layer designed for AI agents, offering serverless, single-file implementation to replace complex RAG pipelines. It enables instant retrieval and long-term memory for agents, streamlining memory managem…
→ View original sourceHKUDS presents nanobot, a lightweight open‑source AI agent designed to integrate with tools, chats, and workflows. It is hosted on GitHub under the HKUDS organization and aims to enhance automation and interaction for de…
→ View original sourceBrowserOS is an open‑source agentic browser
→ View original sourcescreenpipe is a Y Combinator-backed AI project that continuously records local user activity (sight, speech, audio) in a private and secure manner, integrating with OpenClaw, Hermes agents, and over 100 applications. It …
→ View original source