AgentKit by InngestTypeScript framework for building and orchestrating AI agents with tools and workflows.

4.8 (4)

Reviewed by Daniel Nikulshyn·Updated July 2026

Open Source TypeScript AI Agents Developer Tools Orchestration Workflow Automation Framework

Overview

AgentKit by Inngest is an open-source TypeScript framework for building AI agent systems, ranging from simple single-model calls to complex multi-agent orchestrations. It provides primitives for defining agents, equipping them with tools, and routing tasks between them while maintaining state across steps. Built by the team behind Inngest, the framework integrates with their durable execution platform to handle long-running agent workflows, retries, and observability. Developers can connect to multiple LLM providers, expose external APIs as tools, and compose networks of specialized agents that collaborate to solve tasks. It targets engineers who want production-grade reliability for agentic applications without writing custom orchestration logic, offering a code-first approach over visual builders.

Key features

Agent and network primitives
Tool calling with structured inputs
Stateful multi-agent routing
Multiple LLM provider support
Durable workflow execution via Inngest
Observability and step-level retries

Pricing

Model: Freemium
Category: Code Assistants
Rating: 4.8 / 5 (4)

Use cases

Build multi-agent research systems

Compose networks of specialized agents that route tasks between each other to research topics, summarize findings, and produce structured outputs with maintained state across steps.

Production-grade AI workflows

Use Inngest's durable execution to run long-running agent workflows with automatic retries, observability, and step-level recovery for reliable production deployments.

Tool-augmented LLM applications

Equip agents with structured tool calls to external APIs, enabling them to query databases, trigger actions, or fetch live data within TypeScript applications.

Multi-provider LLM orchestration

Build agent systems that leverage multiple LLM providers, routing tasks to the most suitable model and composing single-model calls or complex multi-agent collaborations.

Pros & Cons

Pros

Open source and TypeScript-native
Supports multi-agent orchestration and routing
Integrates with Inngest for durable execution
Flexible tool and model provider support

Cons

Limited to TypeScript/JavaScript ecosystem
Requires coding knowledge, no visual builder
Best features tied to Inngest platform

Reviews

4.8

Average from 4 ratings.

Tariq Aziz

May 13, 2026

Does the job

Pretty happy overall. Observability and step-level retries just works and open source and TypeScript-native. but no dealbreakers — I'd recommend it to a friend without hesitating.

Beatriz Costa

Feb 17, 2026

Skeptical, then convinced

I went in skeptical — most tools in this space overpromise. It actually delivers on agent and network primitives, and flexible tool and model provider support caught me off guard. Best features tied to Inngest platform is why this isn't a perfect score, still, I'd recommend giving it a real trial.

Aisha Khan

Dec 1, 2025

Skeptical, then convinced

I went in skeptical — most tools in this space overpromise. It actually delivers on multiple LLM provider support, and supports multi-agent orchestration and routing caught me off guard. Limited to TypeScript/JavaScript ecosystem is why this isn't a perfect score, still, I'd recommend giving it a real trial.

Liam O’Connor

Nov 22, 2025

Skeptical, then convinced

I went in skeptical — most tools in this space overpromise. It actually delivers on multiple LLM provider support, and integrates with Inngest for durable execution caught me off guard. Best features tied to Inngest platform is why this isn't a perfect score, still, I'd recommend giving it a real trial.

Q&A

Do I need a visual builder to create multi‑agent networks?

No. AgentKit is code‑first; you define agents, tools, and routing logic programmatically using its primitives, so a visual builder is not required.

Asked by Ivana Novak · Sep 16, 2025

Which LLM providers can I connect to?

AgentKit supports OpenAI, Anthropic, Gemini, and any model that follows the OpenAI API compatibility layer, letting you switch providers without changing your code.

Asked by Sanjay Gupta · Aug 31, 2025

Can I run AgentKit workflows on my own infrastructure?

Yes. AgentKit is open source and can be run locally, but its durable execution, retries, and observability features are tied to the Inngest platform, which you can integrate with or replace if you handle orchestration yourself.

Asked by Boris Yankov · Aug 13, 2025

What programming languages does AgentKit support?

AgentKit is a TypeScript‑native framework, so it can only be used within the TypeScript/JavaScript ecosystem.

Asked by Miriam Cohen · Aug 2, 2025