Search

AIHouse - AI Agent 统一监控与管理平台

Voice synthesis endpoint for agent_core — per-agent Qwen3-TTS via ICL voice cloning

Webcam endpoint for agent_core — agent-driven on-demand frame capture

TokenOps control plane and SDK for run-aware agent token governance

Python client for the AgentPact API

Safety-first synthetic data generation agent

Drop-in launcher for Claude Code, Kilo & OpenCode. Run multiple Claude Pro/Max accounts, check usage limits and switch accounts without /login — or point any coding CLI at Ollama (local, no key), OpenRouter, z.ai/GLM, DeepSeek & Qwen. No proxy, no daemon.

Project Memory for AI Agents: a local CLI runtime for project context, recall, and memory updates

Self-orchestrated PR review agent using LangGraph + Claude Agent SDK

Token-budgeted structural briefs of messy CSVs, so LLM agents can write correct extractors without opening the file

Turn the OpenAI Codex Micro into a live status light for Claude Code: one Agent Key per project, lit with that project's real state, and every key remappable.

Self-Expanding State Machine: a Pydantic-bounded FSM that starts sparse and grows via discovery-driven coverage

Local LLM command agent with deterministic execution layer

An autonomous geospatial data science framework for reproducible analysis.

Vital Agent Container SDK

Fast-mode variant of [Opus 5](/anthropic/claude-opus-5) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 5. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...

This library provides standard Python APIs to interact with common penetration testing and cyberattack tools, enabling automated penetration testing, red team operations, and development of cybersecurity-related LLM agents.

A multi-user LLM agent whose knowledge, skills, and tools live in the database — grows at runtime, no redeploys. Web chat + Telegram bot on one core.

把操作手机点外卖封装成给 AI agent 调用的工具——文本进文本出(markdown表格)、对非视觉/远程 LLM 友好、可 MCP 封装或原生 tool 直用。基于 Open-AutoGLM。