Ein KI-Agent ist ein Programm, das mit einem Sprachmodell entscheidet, was als Nächstes zu tun ist, Werkzeuge wie einen Browser, einen Code-Interpreter oder eine API aufruft und das so lange wiederholt, bis die Aufgabe erledigt ist. Die Projekte hier reichen von Frameworks für eigene Agenten bis zu fertigen Agenten, die Code schreiben, im Web recherchieren oder Geschäftsabläufe ausführen.
Vergleichen Sie drei Dinge: welche Modelle der Agent nutzen kann (nur einen Anbieter oder jeden OpenAI-kompatiblen Endpunkt, auch lokale), wie begrenzt wird, was er tun darf (Sandbox, Freigabeschritte, Berechtigungslisten), und ob er zwischen Schritten und Sitzungen ein Gedächtnis behält. Ein Agent, der Code oder Shell-Befehle ausführt, gehört in eine Sandbox – prüfen Sie das, bevor Sie ihm Zugriff auf Ihren Rechner geben.
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.
Zero-dependency TypeScript framework for production AI agents: durable execution, long-term memory, hybrid RAG, MCP tool calling, human-in-the-loop approval, planning and CodeAct sandboxes. One streaming API for Claude, GPT, Gemini, Grok, Mistral and DeepSeek — Node, Bun, Deno, serverless and edge.
Elixir implementation of a LangChain style framework that lets Elixir projects integrate with and leverage LLMs.
AI辅助长篇小说创作，卡片式创作，支持基于 JSON Schema的结构化 AI 生成与上下文引用，可扩展性强。
Instant SECURE Full Stack Apps and AI Agents
Evaluate and improve models and agents using environments
Agentic SOC Platform: A powerful, flexible, open-source, and agent-centric automated security operations platform (AI SOC)
A practical lab for building, testing, and evaluating apps with Apple's Foundation Models framework.
Empryo issue tracker + SoulForge (v2). Empryo is the graph-powered AI coding agent that edits symbols, not strings: AST surgery, full LSP, a live code genome. Get it at https://empryo.com
A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Model Context Protocol (MCP) and enabling cross-vendor LLM API orchestration.
[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation
An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.
🚀 MassGen is an open-source multi-agent scaling system that runs in your terminal, autonomously orchestrating frontier models and agents to collaborate, reason, and produce high-quality results. | Join us on Discord: discord.massgen.ai
Your AI forgets. This remembers. Spec-driven coding harness for vibecoders, product owners, CEOs and real builders — self-improving context memory, 15 agents, 33 skills working with /goal, agent-team, & workflow on autopilot loops with 0 need for human gate. Kills context rot, ships features, not spaghetti. Claude Code & Codex. Any stack
An AI-powered threat modeling tool that leverages OpenAI's GPT models to generate threat models for a given application based on the STRIDE methodology.
Schema-Guided Reasoning (SGR) has agentic system design created by neuraldeep community
Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.
A desktop multi-agent harness built with Rust, Tauri, and React, powered by langgraph-rust.
The collaborative spreadsheet for AI. Chain cells into powerful pipelines, experiment with prompts and models, and evaluate LLM responses in real-time. Work together seamlessly to build and iterate on AI applications.
Open-source TypeScript terminal coding agent for DeepSeek-V4 — builds on DeepSeek's strong price-performance and ultra-cheap cache pricing, engineering byte-stable prefixes and cache-reusing forks so cross-session memory and a continuous self-correction layer add almost no token cost; 1M context, Skills/MCP/Hooks, Claude Code config compatible.
Give your coding agent the power to write and run agent evals.