Inngest
Inngest is a durable workflow orchestration platform for running stateful step functions and AI workflows on serverless, servers or the edge. You write functions in TypeScript, Python or Go with automatic retries, queues, throttling and human-in-the-loop waits, and its AgentKit and AI inference steps let you build durable, long-running AI agents with tracing and evals. The server is source-available (SSPL, converting to Apache 2.0 later) and can be self-hosted, or you can use Inngest Cloud.
Updated
✨ Try AgentScout's free AI image generator →Good for: automating workflows, building multi-agent systems, memory for agents, evaluating agents, monitoring agents in production, deploying and hosting agents
Use cases
About Inngest
Inngest is listed in our agent infra category and is aimed at builders. Inngest is a durable workflow orchestration platform for running stateful step functions and AI workflows on serverless, servers or the edge. You write functions in TypeScript, Python or Go with automatic retries, queues, throttling and human-in-the-loop waits, and its AgentKit and AI inference steps let you build durable, long-running AI agents with tracing and evals. The server is source-available (SSPL, converting to Apache 2.0 later) and can be self-hosted, or you can use Inngest Cloud. Pricing, as the maker states it: Inngest Cloud: Free $0/mo (50k executions, 5 seats), Pro $99/mo, Business $499/mo, Enterprise custom (inngest.com/pricing, checked Oct 22 2026). Server is source-available (SSPL with delayed Apache 2.0) and self-hostable.. Maturity: Mature. We last checked the official link on 2026-10-22.
Inngest at a glance
- Category: Agent infra
- Built for: Developers and teams building with AI agents
- Pricing: Inngest Cloud: Free $0/mo (50k executions, 5 seats), Pro $99/mo, Business $499/mo, Enterprise custom (inngest.com/pricing, checked Oct 22 2026). Server is source-available (SSPL with delayed Apache 2.0) and self-hostable. (as the maker states it)
- GitHub: inngest/inngest · 5,970 stars (as of Oct 22, 2026)
- Official site: inngest.com
- Listed on AgentScout: Oct 22, 2026
Inngest FAQ
What is Inngest?
Inngest is a durable workflow orchestration platform for running stateful step functions and AI workflows on serverless, servers or the edge. You write functions in TypeScript, Python or Go with automatic retries, queues, throttling and human-in-the-loop waits, and its AgentKit and AI inference steps let you build durable, long-running AI agents with tracing and evals. The server is source-available (SSPL, converting to Apache 2.0 later) and can be self-hosted, or you can use Inngest Cloud.
How much does Inngest cost?
Inngest's pricing, as the maker states it: Inngest Cloud: Free $0/mo (50k executions, 5 seats), Pro $99/mo, Business $499/mo, Enterprise custom (inngest.com/pricing, checked Oct 22 2026). Server is source-available (SSPL with delayed Apache 2.0) and self-hostable.. Check the official site for current plans.
Where can I find Inngest's source code?
On GitHub at inngest/inngest, which had 5,970 stars as of Oct 22, 2026.
What are alternatives to Inngest?
Similar tools include Kestra, Windmill, OpenComputer, Groq, Agent Barn and Sentio.
Facts from our link-checked listing, the GitHub repository and the official site. See something wrong? Suggest an edit.
Inngest ratings and reviews
Be the first to rate Inngest: tap 1 to 5 stars below. A written review is optional.
Inngest alternatives
Other agent infra tools in our directory. See all agent infra tools →
Kestra
Kestra is an open-source, event-driven orchestration and scheduling platform where workflows are declared in YAML or built in a no-code editor. It includes an AI Agent task that gives flows an LLM with memory and tools, supports nested agents and the Agent-to-Agent (A2A) protocol, and can expose any flow as a tool to external AI agents through its MCP server. It runs in the cloud, on-prem or air-gapped and is Apache 2.0 licensed.
Windmill
Windmill is an open-source developer platform that turns scripts in Python, TypeScript, Go, SQL and other languages into webhooks, workflows and internal UIs. Its flows include AI agent steps that call an LLM with your scripts as tools, support nested agents and MCP, and run on a fast self-hostable workflow engine. It positions itself as an open-source alternative to Retool and Temporal.
OpenComputer
OpenComputer is a platform for building and deploying long-running AI agents as code. You define an agent as a TypeScript function with its model, tools and MCP servers, deploy it with one command, and every session gets its own real cloud computer, with managed sessions, schedules and API keys kept outside the agent's runtime. Templates include a coding agent that edits a repo, runs checks and opens a draft pull request, and market-research and GTM agents; its own Slack coding agent runs on it. Pricing is pay-as-you-go for model calls and per-second machine time.
Groq
Fast inference cloud running open models on custom LPU chips, used for low-latency agents.
Agent Barn
Agent Barn is an open-source (Apache-2.0) control plane for running a fleet of AI agents on your own Kubernetes: create, configure, run and monitor agents across Slack, Microsoft Teams and Telegram from one place.
Sentio
Sentio, from Truespar, is a self-hosted email inbox API for AI agents: a Rust SMTP server that gives each agent a real address, delivers inbound mail as authenticated webhooks and lets agents reply in-thread over REST, with multi-tenant isolation.
Popular searches with this tool
🏆 Ranked in: LiteLLM alternatives
🔁 Listed in: LiteLLM alternatives
🧭 Task guides: Eval and benchmark tools for monitoring agents in production · Local and self-hosted tools for agent memory · AI workflow automation tools
💲 Estimate API cost: compare per-request and monthly costs for GPT, Claude, Gemini and Grok models.
Badge for makers
Built Inngest? Add this badge to your README or site. It links back to this page. About badges
