🧰ИИ-агенты: Фреймворки для агентов

Vibe Check is a tool that provides mentor-like feedback to AI Agents, preventing tunnel-vision, over-engineering and reasoning lock-in for complex and long-horizon agent workflows. KISS your over-eager AI Agents goodbye! Effective for: Coding, Ambiguous Tasks, High-Risk tasks

AI software team for Claude Code - 138 agents, 295 skills, 73 hooks. Self-learning, multi-agent swarm, autonomous skill evolution.

Multi-agent end-to-end application - General-purpose artificial intelligence agent for multimodal agent collaboration

[ICLR 2023] Come & try Decision-Intelligence version of "Agar"! Gobigger could also help you with multi-agent decision intelligence study.

Agentspan is now part of Orkes Conductor

Openclaw多智能体协同系统 | Multi-Agent OS for Decision Makers — 基于 OpenClaw (Clawbot) + Slack，让 AI 团队各司其职、自主稳定迭代。

Mantis Hack

A fast and minimal framework for building agentic systems

Multi-agent end-to-end application - General-purpose artificial intelligence agent for multimodal agent collaboration

Flink Agents is an Agentic AI framework based on Apache Flink

Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets.

Multi-agent orchestration platform for Gemini CLI, Claude Code, Codex, and Qwen Code — 39 specialists, parallel subagents, persistent sessions, and built-in code review, debugging, security, SEO, accessibility, and compliance tools

Symbol Delta Ledger (SDL-MCP) is a policy-centered context budget layer for coding agents: Symbol-graph intelligence combined with precision tools. It turns sprawling codebases into compact, high-signal context that saves tokens, speeds up workflows, and improves agent output.

A highly customizable agentic harness for arXiv-ready ML/AI review papers (and beyond). It drives agentic AI like Codex CLI and Claude Code through a gated LaTeX workflow with verified BibTeX citations.

The open-source memory and observability layer for AI agents — persistent memory, loop detection, hash-chained audit trails, and a live dashboard, automatic on pip install.

A powerful browser assistant for vibe surfing 一个开源的AI浏览器智能助手

Create polished product demo videos with AI coding agents and Remotion. The UI is code, not a screen recording.

Self-hosted AI agent harness in a single Go binary — writes, sandbox-tests and repairs its own tools, and lets Claude Code, Codex and any MCP client build and share them.

mahilo: Multi-Agent Human-in-the-Loop Framework is a flexible framework for creating multi-agent systems that can each interact with humans while sharing relevant context internally.

First Principles Framework (FPF): Pattern language and core specification for admissible action in problematic engineering, research, and mixed human/AI work.

Transform any idea into a running AI-powered company

MCPMark is a comprehensive, stress-testing MCP benchmark designed to evaluate model and agent capabilities in real-world MCP use.

Agentic 3D Modeling with Procedural Control — turns a text prompt into an editable parametric program, with optional per-part materials and articulation.

AutoHarness: Automated Harness Engineering for AI Agents