Skip to content

Concepts

This section explains the core ideas behind Pipelit. Understanding these concepts will help you design effective workflows and get the most out of the platform.

Workflows

The central organizing unit in Pipelit. A workflow is a visual pipeline you design on a canvas, connecting triggers, agents, tools, and logic nodes into an executable graph.

Nodes & Edges

Nodes are the building blocks of workflows. Edges are the connections between them. Together they form a typed, directed graph with validated data flow.

Triggers

Triggers are specialized nodes that initiate workflow execution. Pipelit supports chat, Telegram, manual, scheduled, workflow, and error triggers -- all as first-class nodes on the canvas.

Agents

LLM-powered nodes that reason, call tools, and produce responses. Agents use LangGraph's ReAct architecture and support conversation memory, tool calling, and model selection.

Tools

Sub-component nodes that give agents capabilities: execute shell commands, make HTTP requests, search the web, evaluate math, and check the current time.

Expressions

Jinja2 template expressions let you reference upstream node outputs in system prompts and configuration fields. Use {{ nodeId.portName }} syntax with filters and fallbacks.

Execution

How workflows run: trigger-scoped compilation, topological node ordering, real-time WebSocket status updates, and result propagation through the graph.

Memory

Persistent knowledge storage across executions. Conversation memory gives agents continuity. Global memory stores facts, episodes, and procedures that any agent can recall.

Epics & Tasks

A task delegation system for multi-agent coordination. Epics group related tasks with budgets and deadlines. Agents can create, query, and update them autonomously.

Cost Tracking

Per-execution token counting and USD cost calculation. Tracks input/output tokens across all LLM calls with Epic-level budget enforcement.

Scheduler

Self-rescheduling recurring execution without external cron. Configurable intervals, repeat counts, retry with exponential backoff, pause/resume, and crash recovery.

Security

Authentication, authorization, credential encryption, and sandboxed code execution. Bearer token API keys, Fernet-encrypted secrets, and restricted execution environments.