智能体市场

AI-Native Risk Intelligence Systems, OpenDeRisk——Your application system risk intelligent manager provides 7* 24-hour comprehensive and in-depth protection.

Multi-Agent Framework

A curated list of OpenClaw resources, tools, skills, tutorials & articles. OpenClaw (formerly Moltbot / Clawdbot) — open-source self-hosted AI agent for WhatsApp, Telegram, Discord & 50+ integrations.

[CVPR 2024 🔥] Grounding Large Multimodal Model (GLaMM), the first-of-its-kind model capable of generating natural language responses that are seamlessly integrated with object segmentation masks.

Open source voice dictation technology

A fork of Windows Terminal with native agent integration, right in your command line.

Awesome Game AI materials of Multi-Agent Reinforcement Learning

Hexabot v3 is an AI automation platform, combining workflows, actions, agents, and conversational channels in one runtime.

Open Source Autonomous Software Development System

Multi-agent autonomous SDLC framework. Spec to deployed app. PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief. 5 AI providers, 11 quality gates.

A security scanner for your LLM agentic workflows

Curated list of AutoResearch use cases with optimization traces and open source implementations

[ICML 2026 Spotlight] Latent Collaboration in Multi-Agent Systems

The Agent Harness for AI-Human Collaboration, inspired by the AI-DLC (AI-Driven Development Lifecycle)

Working, locally-running, low-cost implementation of Generative Agents: Interactive Simulacra of Human Behavior.

📚 Real-world OpenClaw automation examples from Moltbook

MCP server for Google Ads, Meta Ads & GA4 — works with ChatGPT, Claude, Cursor, n8n, Windsurf & more. 250+ tools for campaign management, analytics & optimization.

🐝 The First Self-Improving agents with RL / Prompting Optimization

Use sidecar next to CLI agents for diffs, file trees, conversation history, and task management with td

TypeScript AI AI Function Calling Framework enhanced by compiler skills.

LuaN1aoAgent is a cognitive-driven AI hacker. It is a fully autonomous AI penetration testing agent, using dual-graph reasoning.

An autonomous agent that takes work, does work, gets paid, and gets better at it.

The batteries-included, No-Code FinOps automation platform, with the AI you trust.

The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.