Search

Private AI Agent Control Plane for Solana - CLI runtime connector

Scaffold a Vexel Multi-Agent Intelligence Framework project. Build AI agent squads with ETL mind-cloning and automated squad creation.

Multi-agent orchestrator skill for Claude Code — intelligently coordinate AI agents in parallel

Scaffold a MeowKit AI agent toolkit for your project

Automated eval & improvement loop for AI agents. Generates test scenarios, runs the agent, scores with multi-model consensus (Claude + GPT + Gemini), and iteratively patches code until quality targets are met.

Zone � AI Code Agent: deterministic, explainable, safe

General-purpose agent framework for Python — multi-turn tool execution, hooks, event streaming

LLM-powered game agents for chess, Go, poker, social deduction, and 20+ other games

Production-ready agent implementations: SimpleAgent, ReactAgent, MultiAgent, MemoryAgent, RAG variants, and more

TypeScript SDK for EdgeBets sports simulation API with x402 payment support

OS-enforced sandbox backend for LangChain Deep Agents using Landlock (Linux) and Seatbelt (macOS)

ML classifier add-on for Agent Armor. Downloads and runs a DeBERTa-v3-small ONNX model for agent trap detection.

Automation monitoring that never sleeps. Monitors Make.com scenarios, n8n workflows, Zapier zaps, AI agents, and CLI scripts. Alerts you by email, Slack, or SMS when something breaks silently.

HDP (Human Delegation Provenance) middleware for LangChain — cryptographic audit trail for multi-agent delegation

Run LLM agents inside disposable Docker sandboxes.

Collapse consecutive read/search tool calls to reduce agent context size

CLI tool for LLM agents to operate Jupyter Lab servers

Agent client for OpenEnv environments - connects RL agents to OpenEnv servers for inference and training

Turbo-Agent 任务调度与执行单元（由 worker 迁移而来）

Runtime orchestration for turbo-agent