🧰ИИ-агенты: Фреймворки для агентов

OSS trading workspace with your favorite agents

The agent-native OS for companies.

A Massively Parallel Large Scale Self-Play Framework

Give you decision-ready references for the most common AI engineering problems

Learning to Communicate with Deep Multi-Agent Reinforcement Learning in PyTorch

Source-available, self-hosted platform for building AI agent flows - visual editor over a Django backend.

A research framework for principled agent self-improvement under frozen evaluators and declared mutation boundaries, recording verifiable lineage to make it reproducible and auditable.

Multi-agent orchestration system for Claude Code with parallel execution, automated quality gates, Board of Directors, and bundled Superpowers skills

✨ Awesome AI Agents for 2026 ⭐ Star it

Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus.

One person, a team of agents: CLI, Web, Desktop & Python SDK with multi-session collaboration, persistent memory, and self-evolving skills. 一个人，一支 Agent 团队：支持多终端协作、持久记忆与技能自进化的 AI Agent 框架。

Use Web AI as an agent without an API key. $0 | litellm , local models via Ollama, /lang in 34 languages, Mesa Redonda, voice, OCR, MemPalace, embedded sandbox OS. (The Hermes Killer)

Orchestrate an entire AI dev team on 5GB VRAM. Ephemeral subagents, exact-match diffs. Single static binary, any model. Zero config, zero context bloat.

A curated list of plugins, skills, MCP servers, patch/profile layers, orchestrators & UIs for DeepSeek Harness (DSH). Visualization · PPT · Coding · Agents · Loops (auto-research) and more. #dsh

Yet another coding agent harness, lightweight and written in go.

Restack AI examples for Python

Clouds Coder is a local-first coding agent platform centered on separating the CLI execution plane from the Web user plane, with Web UI, Skills Studio, resilient streaming, and long-task recovery controls.

Architect-centric agentic swarm plugin for OpenCode. Hub-and-spoke orchestration with SME consultation, code generation, and QA review.

A Production-Ready Framework for Building Composable AI Agents

A Datalog engine for LLM agent memory: stratified rules, provenance-tracked facts, incremental derivation, and an MCP server that lets your harness use it as a shared brain.

syftr is an agent optimizer that helps you find the best agentic workflows for your budget.

Monocle is a framework for tracing GenAI app code. This repo contains implementation of Monocle for GenAI apps written in Python.

🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and RVM (hardware-isolated sandbox).

AI Agent 教学仓库 | 系统化 LangChain、RAG、LangGraph、MCP 全栈实战代码 | 万字博客详解 | 开源可运行示例 | 从零构建智能体