🧰ИИ-агенты: Фреймворки для агентов

Deep Reinforcement Learning in C#

A local-first, encrypted Slack/Discord alternative built for the agentic era. AI agents, such as openclaw, join channels, receive tasks, and coordinate on equal footing with humans — over a serverless P2P mesh.

verl for a single consumer GPU. PPO, GRPO and on-policy distillation on NVIDIA GPUs.

Remote approvals, policy checks, and execution evidence for unattended AI agents.

ANOLISA(Agentic Nexus Operating Layer & Interface System Architecture)

Open-Source Framework for Development, Simulation and Benchmarking of Behavior Planning Algorithms for Autonomous Driving

A Text-Based Environment for Interactive Debugging

Local-first, governed AI agent runtime for Python — embed it in your app, or run it as a CLI or ACP server. Permissions, MCP, memory and audit replay built in.

Python functions powered by AI agents - with runtime post-conditions for reliable agentic workflows.

[Public preview] Externally scored agentic ML research benchmark: 60 tasks, real competition ground truth. Open protocol, operated evaluation.

The original Tiny Claw as your personal autonomous AI companion. 🐜

Agentic Development Environment

Evolutionary multi-agent runtime that breeds, evaluates, and improves autonomous agents across reproducible epochs to converge on optimization of a goal.

Build, test, and deploy intelligent AI agents the Laravel way

The production-ready agent harness framework for Python

A Multi-Agent framework that enables AI agents to collaborate effectively, helping you build powerful agent teams for solving complex tasks.

Secure runtime to sandbox AI agent tasks. Run untrusted code in isolated WebAssembly environments.

Give AI agents ambitious work without losing the plot. nac is an open-source harness for long-running tasks, using a central orchestrator, threads, and structured episodes to stay aligned with your intent.

Agentic RAG for any scenario. Customize sources, depth, and width

This MCP server provides documentation about Strands Agents to your GenAI tools, so you can use your favorite AI coding assistant to vibe-code Strands Agents.

Fully Autonomous AI Research System with Self-Evolution, built natively on Claude Code

Multi-Agent System Powered by LLMs for End-to-end Multimodal ML Automation

让智能体像人一样学习和工作，共享智能体和项目记忆

Running local Language Language Models (LLM) to perform Retrieval-Augmented Generation (RAG)