Features
5-10x faster inference via native vLLM integration with auto multi-GPU and PagedAttention
Grounded citations: response.sources/.citations filled from retrieved URLs
Reasoning model support: gpt-5, o-series complete with cost/token/latency reporting
One-call domain agent creation: LegalDomain().to_agent()
Custom personas enforced on every execution path
Fail-closed agent.run(): never returns success with empty output
Self-updating model catalog with drift warnings
Sandboxed built-in tools with SSRF guard and path-confined file tools
Policy-based ModelRouter: FirstAvailable, CostBased, LatencyBased with transparent failover
Automatic task decomposition and sub-agent routing (AgentMode.AUTO)
Multi-agent orchestration with team patterns, shared state, and message bus
14 inference backends: 5 local engines + 9 cloud providers (OpenAI, Anthropic, Gemini, Cerebras, Groq, Together,
Unified ProviderRegistry with list_providers()/list_models() and API readiness checks
66+ built-in tools covering computation, code execution, web search, documents, media, and more
9 agent presets: math, research, coding, general, rag, media, notify, multimodal, minimal
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
