Features
Declarative .mthds file format
Typed concept schemas with validation
Deterministic orchestration (no freeform prompting)
Integration with Claude Code and Codex
Built-in concept system (text, number, list, references)
Executable runtime (Pipelex run)
Composable pipelines (PipeLLM, PipeExtract, PipeCondition, PipeSequence)
Choice enumeration for outputs
Compilable specs to code, tests, and agent guidance
Cloud-hosted runtime (Pipelex Cloud)
Conditional routing with PipeCondition
Validation before runtime
Multi-agent orchestration with handoffs
Sandbox Agents for containerized long-running tasks
Agent-as-tool delegation (v0.15.0+)
Realtime Agents with gpt-realtime-2 voice support (v0.17.6+)
Human-in-the-loop mechanisms
Automatic session history management
Built-in tracing for debugging
Provider-agnostic LLM support (100+ models via LiteLLM)
Redis session support (optional, v0.17.6+)
Instructions, tools, and guardrails configuration
Jupyter notebook compatibility
Supports OpenAI Responses and Chat Completions APIs
