Features
Autonomous agent creation from high-level goals
Self-hosted sandboxed environments with CPU, memory, disk limits
Network sandboxing with domain allow/block lists
Credential management via 1Password, Bitwarden, HashiCorp Vault, KeePass
Real-time credential approval requests
Agent-to-agent delegation with context passing
Web browsing and code execution
Application deployment from code to running service
Unified policy language for tools, sandbox, channels
Agent memory across conversations
Real-time connectivity feedback for permitted domains
Automatic enforcement of resource allocation
Secrets never stored in agent memory or sent to LLM providers
GLM-5.2 open-source flagship model with 1M context
GLM-5V-Turbo multimodal coding model
GLM-5-Turbo agent-optimized base model
AutoGLM autonomous planning and execution agent (50+ steps)
GLM-PC computer-operating agent via screen input
AutoClaw 1-minute PC agent deployment
MaaS high-performance model API services
Model fine-tuning for language and multimodal models
AI search tool with multi-engine integration
General translation with context recognition
GLM PPT/Poster one-click presentation generation
CogAgent-9B open-source GLM-PC base model
End-side deployment with Intel partnership
CodeGeeX smart coding assistant for AIPC
