Julep
Platform for durable AI agent workflows that can crash, resume and retry safely.
Updated
✨ Try AgentScout's free AI image generator →Good for: automating workflows, building AI agents
Use cases
About Julep
Julep is listed in our frameworks category and is aimed at builders. Platform for durable AI agent workflows that can crash, resume and retry safely. Pricing, as the maker states it: Open source + cloud. Maturity: Mature. We last checked the official link on 2026-10-16.
What is Julep?
Julep builds AI agents as composable, durable dataflows rather than ad-hoc loops. Flows can crash and resume, retry safely, explain every step, and deny any tool the model was not explicitly allowed to call.
The main authoring style is a Python @flow, where ordinary Python names graph steps such as tools, reasoners, branches, fan-out and retries. A cloud option is available.
Sources: the official README and our directory listing, checked 2026-10-18. Official site: docs.julep.ai/introduction/julep.
Who is Julep for?
Python developers who need reliable, explainable agent workflows that survive crashes.
Julep at a glance
- Open source: Yes (Apache License 2.0)
- GitHub: julep-ai/julep · 6,575 stars (as of Oct 21, 2026)
Key features
- Durable flows that resume after crashes
- Safe retries
- Explicit tool allow-lists
- Python @flow authoring
Julep FAQ
What is Julep?
Julep builds AI agents as composable, durable dataflows rather than ad-hoc loops. Flows can crash and resume, retry safely, explain every step, and deny any tool the model was not explicitly allowed to call.
Who is Julep for?
Python developers who need reliable, explainable agent workflows that survive crashes.
Is Julep free?
Julep's pricing, as the maker states it: Open source + cloud. Open-source tools are free to use, though you may still pay for model API usage or a hosted plan. Check the official site for current plans.
Is Julep open source?
Yes. Julep is released under the Apache License 2.0, according to its GitHub repository.
What are alternatives to Julep?
Similar tools include Orkes, Trigger.dev, Workflow SDK, Sage, Mastra and Open Multi-Agent.
Julep ratings and reviews
Be the first to rate Julep: tap 1 to 5 stars below. A written review is optional.
Julep alternatives
Other frameworks tools in our directory. See all frameworks tools →
Orkes
Orchestration platform built on Conductor for durable workflows and AI agents.
Trigger.dev
Platform for building and deploying durable background AI agents and workflows in TypeScript.
Workflow SDK
Vercel's TypeScript SDK for building durable, reliable and observable apps and AI agents.
Sage
Sage is an MIT-licensed framework for building configurable, self-improving AI agents from reusable agent packages, tools, Skills and MCP services. It supports multi-agent workflows and multi-round self-improvement, keeping a version history of agent packages so you choose which version to adopt.
Mastra
TypeScript framework for agents, workflows and RAG.
Open Multi-Agent
Self-hosted TypeScript agent runtime with durable approvals and verifiable run records.
Related lists
🏆 Ranked in: AutoGPT alternatives
🔁 Listed in: AutoGPT alternatives
🧭 Task guides: AI workflow automation tools
💲 Estimate API cost: compare per-request and monthly costs for GPT, Claude, Gemini and Grok models.
Badge for makers
Built Julep? Add this badge to your README or site. It links back to this page. About badges
