Search

AI model: md896/sql-debug-agent-qwen05b-grpo

AI model: praveenkrovvidi/rl-cas-trl-agent

AI model: bavatharani/gemma-support-agent

Official, AWS-supported MCP servers, skills, and plugins to help AI agents build on AWS

Durable iMessage AI agent template. Text your agent, get retryable LLM + tool replies, full observability. Production-ready, deployed on Vercel

Agent-Pilot · 飞书 AI 校园挑战赛 · 从 IM 对话到演示稿的一键智能闭环 | 6 Agent Multi-Agent Pipeline · MiniMax M2.7 Tool Calling · 飞书 Bot 全生态集成

Provide automated binary analysis via a CLI tool using Hex-Rays' idalib without requiring the IDA Pro GUI or MCP layer.

An intelligent, Dockerized Personal Assistant AI featuring a ReAct loop with tool-calling capabilities. Built with FastAPI & Streamlit, and deployed via automated CI/CD.

🧠 AI Knowledge Engine. Turn any AI coding agent into a self-learning knowledge engine. Modular instruction framework for building personal knowledge bases with local NLP, provenance tracking, and smart scheduling.

Unofficial MCP server exposing the Wealthsimple Help Center to AI agents — 7 typed tools, public Zendesk JSON API only. No scraping, no auth, no account data. TypeScript + Zod-validated. Opt-in Datadog LLM Observability with privacy redaction.

event-sourced adk for go

Unified AI orchestration engine | 26 modules | 9 specialized agents | MCP protocol | Foundation layer for JARVIS OS

A stateful runtime middleware that adds FSM-based execution semantics, state-aware retry, and structured deterministic paths to browser agents. Designed to reduce redundant visual inference and improve reliability in multi-step web workflows.

Values, beliefs, and purpose as inspectable data for long-lived AI agents — a research-grounded experiment in agent motivation, with calibrated empirical claims and an open lab notebook.

Open-source AI-to-AI bus for connecting agents, model routers, rooms, and remote assistant nodes

Novita sandbox backend integration for LangChain Deep Agents

MobileUse: an open-source mobile GUI agent for Android phone automation, AndroidWorld/AndroidLab evaluation, hierarchical reflection, and proactive exploration.

Security scanner for AutoGen multi-agent conversations — powered by AgentSentinel on SingularityNET

Security scanner for CrewAI multi-agent workflows — powered by AgentSentinel on SingularityNET

Self-improving algorithmic trading bot with Claude-Code-driven reflection.