🧰ИИ-агенты: Фреймворки для агентов

[ICRA 2022] An opensource framework for cooperative detection. Official implementation for OPV2V.

OpenSwarm — Autonomous AI dev team orchestrator powered by Claude Code CLI. Discord control, Linear integration, cognitive memory.

[EMNLP'25] s3 - ⚡ Efficient & Effective Search Agent Training via RL for RAG (RLVR for Search with Minimal Data)

Real-time web cockpit for OpenClaw: voice conversations, agent automated kanban board, workspace/file control, sub-agent sessions, inline charts, and usage visibility.

♾️ 开源数字永生框架 — 从聊天记录蒸馏任何人的七维数字分身。支持微信/飞书/iMessage/Telegram等12+平台，7种角色模板，对齐 OpenClaw Soul Spec 标准。一行指令让你的AI学会蒸馏。

♾️ Private Agent Fleet with Spec Coding. Each agent gets their own GPU-accelerated desktop. Run Claude, Codex, Gemini and open models on a full private AI Stack ♾️

More is Different. A multi-agent world engine where AI agents live, talk, compete, ally.

A flexible multi-interface AI agent framework for building agents with reasoning, tool use, memory, deep research, blockchain interaction, MCP, and agents-as-a-service.

Your Company Agentic Operating System

The first open-source agentic AI physicist, by Physical Superintelligence PBC (PSI).

Blades is a Go-based multimodal AI Agent framework.

Open source file-system and knowledge based agent template. Build AI agents that stay up to date with your knowledge base

PowerMem: AI Memory Plugin— Accurate, Agile, Affordable. Make AI Agent smarter.

AINL helps turn AI from "a smart conversation" into "a structured worker." It is designed for teams building AI workflows that need multiple steps, state and memory, tool use, repeatable execution, validation and control, and lower dependence on long prompt loops. AINL is a compact, graph-canonical, AI-native programming system for (READ: README)

Core 7 layers of production grade agentic system

Self-healing infrastructure for AI agent payments. 90.3% auto-recovery.

semantic agent kernel which make agent efficient and self-evolve

Autonomous development for real products. Governed agents build from specs you approve, follow the rules you set, and nothing merges until another agent proves it. Your decisions, judgement and taste are the bar that work must clear. Declare your vision and let agents build it.

EMNLP 2026 Main Conference Paper: MASCOT: Towards Multi-Agent Socio-Collaborative Companion Systems (https://aclanthology.org/2026.emnlp-main.878/))

State of the Art 82% OSWorld Computer Using Agent, production-ready. Remote and Local! Setup using one API Key

Unified Rust framework for building, verifying, and testing web apps. Kernel-based architecture for Lean 4 verification and GPU acceleration. Built-in red-teaming tools for automated vulnerability detection.

Data API Framework for AI Agents and Data Apps

The most autonomous AI agent framework: runs unattended on GitHub Actions, self-healing skills, drives Claude Code, Grok, Codex & more. No approval loops. Configure once, forget forever.

Cayu is an open-source Python framework for building and running domain-specific long-horizon agents, with a durable runtime built in.