Sàn agent

Agent Graph is a Multi-Agent System built on the principles of Context Engineering

The work experience layer for autonomous agents. Open-source core: https://github.com/ShuxinYang111/oysterworkflow-core

A fully-featured, GUI-powered local LLM Agent sandbox with complete MCP protocol support. Features both CLI and full desktop environment, enabling AI agents to operate browsers, terminal, and other desktop applications just like humans. Based on E2B oss code.

An autonomous research colleague — from a question to a compiled manuscript, while you sleep.

GBase — Recursive Self-Improvement Agent Framework. Memory, evolution, quality gates, identity system, and 40+ auto-registered tools.

Your efficient agentic AI coding CLI assistant

Move from idea to production in hours with policy-driven autonomous AI agents. Unified Control Plane: Centralised tools, MCPs, models, data, and policies with consistent observability and governance.

Build programmatically custom agentic workflows, AI Agents, RAG systems for java

小龙虾 openclaw 的 onebot 接入框架，可用于接入 QQ

An agent orchestration framework for economic agents

File Storage & Sandbox Backends for Pydantic AI: console tools for file operations, Docker-isolated sandboxes for safe execution, and permission system with presets for access control. Enables secure multi-user handling and testing in agents via in-memory, local, or containerized storage.

🏆 Ranked list of 100+ agent harnesses. Scored and updated weekly.

Create custom DevOps AI agents that understand and manage your infrastructure.

AURA is an agentic harness that turns an LLM model into a reliable, autonomous service capable of executing real SRE work. AURA provides the guardrails, API servers, state management, authentication, streaming, error handling, and tool integrations necessary to run AI SRE agents safely in production.

tinyAgent uniquely treats functions as first-class citizens, easily transforming them into powerful AI tools. Inspired by human organizational structures, it dynamically orchestrates specialized agents, balancing security and capability for complex tasks.

A declarative way to control LLMs.

Task Planning and Tracking toolset for Pydantic AI agents, enabling hierarchical task management with subtasks, PostgreSQL storage for multi-tenancy, and an event system for webhooks and callbacks.

Another curated list of Python frameworks

An enterprise framework implementing the Agent Operation Authorization protocol with cryptographic identity binding, fine-grained authorization, and semantic audit trails for secure AI agent operations.

Nevron: highly customizable, extremely lightweight and fully scalable AI Agent Framework

Subagent Delegation framework for Pydantic AI, enabling nested subagents that can spawn their own specialists on-the-fly, with smart sync/async/auto mode selection, runtime agent creation, and clean multi-agent architecture. Adds specialization, parallel execution, and task cancellation.

let LLMs control your desktop for tasks

A local AI agent platform for people who want broad, real-world automation with a design that makes powerful actions safer and easier to predict

JL Engine Local is a local ai agent stabilization layer With a focus on ai personality. Including an Emotional and speach rythum focused control protocol + headless engine and more.