#agent Repositories
830 repositories total
An agent tutorial website for applying to Agent R&D positions at major tech companies, covering technical roadmaps and standard interview questions.
Documents, songs, and screenplays become walkable 3D worlds that you and your own coding agents edit together. A Rust desktop app built on the Open World Format.
A desktop multi-agent harness built with Rust, Tauri, and React, powered by langgraph-rust.
The most comprehensive, continuously updated, and hottest collection of 100+ persona distillation skills on the web | Multi-agent systems | All categories: celebrities/directors/online legends/ancient texts/2D anime/workplace/emotions
World2Agent(W2A) is an open protocol that standardizes how AI agents perceive the real world.
Schema-Guided Reasoning (SGR) has an agentic system design created by the NeuralDeep community.
Trace-native CI/CD for AI agents โ production failures become regression tests that block the PR. Auto-detect, cluster, freeze into hermetic cases, replay in CI for $0.
OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards
A self-hosted command center for OpenCode. Sessions, git, terminal, and schedules in one web app, from your phone or desktop.
The cockpit for vibe coding: browse files on the left, command agents on the right, watch every change in between.
๐ Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support
AI-native, cloud-native file system in Rust. Full POSIX on object storage with a multi-tier distributed cache, for AI training, inference, and agents. CNCF Sandbox project.
Awesome-llm-role-playing-with-persona: a curated list of resources for large language models for role-playing with assigned personas
A hierarchical memory framework for personalized presentation agents. Try it at memslides.com.
The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.
Plan, build and launch products with AI: guided planning prompts, an AI App Starter for Next.js, Supabase and Vercel, and agent configurations.
ReachAI Enterprise AI Agent Development Platform: Quickly and securely modernize existing business systems with AI, enabling AI to query data, fill out forms, and handle business tasks directly within OA, ERP, CRM, and other existing business applications.
Agents-flex is a lightweight Java AI agent development framework (positioned as a counterpart to Spring AI). It supports features such as RAG, MCP, Skills, Text2SQL, LLM Wiki, Sub-agents, Web Search, TTS (synchronous and streaming), and STT.
Full-Chain Sentinel is a cybersecurity agent that integrates web penetration testing, Android app security testing, iOS app security testing, bulk attack-and-defense reconnaissance, automated incident response, open-source vulnerability monitoring, and cybersecurity inspections. It supports the automation of security service delivery and must not be used for illegal purposes.
OpenLoomi is an open-source AI coworker. It connects your work tools, understands what youโre working on, and tells you what needs your attention, why it matters, and what to do next. Itโs your open-source Attention Agent.
Open-source, self-hostable Web Agent foundation with multi-user support, isolated sandboxes, and extensibility through Skills and MCP.
Enterprise-grade AI resource management platform, providing unified AI gateway and token scheduling capabilities, managing mainstream models such as OpenAI, Azure, Claude, and DeepSeek, and supporting centralized registration and distribution of MCP tools and Skills. It features dual-track pricing for internal and external use, cost attribution, unified identity authentication, security auditing, and efficiency reports, helping enterprises precisely control costs, quantify ROI, and efficiently govern AI assets.
She's Different โ Relationship Analysis Room โ WeChat Chat History Relationship Analysis Agent Skill (formerly known as: Does She Love Me?)
An open-source AI agent designed for long-running operation and desktop collaboration, providing a persistent runtime, desktop agent, long-term memory, and continuous learning capabilities. It can be used for personal assistants, automated tasks, and local workflows.
Production-ready open source terminal coding agent with readable, layered code: permission rules, OS sandboxing, MCP, skills, sub-agents, and Anthropic, OpenAI-compatible, Gemini, or local models.
The simplest, thinnest harness that gives an LLM complete freedom to control a Mac.
AI writes code. This automates everything else ยท 24 plugins ยท 49 agents ยท 44 skills ยท for Claude Code, OpenCode, Codex, Cursor, Kiro.
JARVIS โ a voice assistant for Claude Code. Talk to your Mac and he brainstorms a project with you, builds it, and tells you out loud when a Claude Code session needs you. macOS, on your Claude subscription, no API key.
CodeAgent is an open-source coding agent that lives in your terminal. It understands your repository, plans multi-step changes, writes and edits files, runs commands and tests, and iterates until the task is done โ all with a transparent, extensible tool loop.