agent-kit and adk-ts

These are competitors—both provide TypeScript frameworks for building multi-agent systems with LLM integration, though AgentKit offers more mature production features (deterministic routing, MCP tooling, established adoption) while ADK-TS provides a lighter-weight alternative with multi-provider LLM abstraction.

agent-kit
70
Verified
adk-ts
51
Established
Maintenance 13/25
Adoption 10/25
Maturity 25/25
Community 22/25
Maintenance 10/25
Adoption 10/25
Maturity 15/25
Community 16/25
Stars: 800
Forks: 121
Downloads:
Commits (30d): 2
Language: TypeScript
License: Apache-2.0
Stars: 115
Forks: 17
Downloads:
Commits (30d): 0
Language: TypeScript
License: MIT
No risk flags
No Package No Dependents

About agent-kit

inngest/agent-kit

AgentKit: Build multi-agent networks in TypeScript with deterministic routing and rich tooling via MCP.

AgentKit helps TypeScript developers build robust multi-agent systems that can handle complex workflows. It takes in plain language requests and orchestrates various 'agents' (which are essentially specialized AI functions) to collaboratively process information and produce a final output. This tool is for developers creating AI applications that require agents to work together efficiently and reliably.

AI application development multi-agent systems workflow automation TypeScript development large language models

About adk-ts

IQAIcom/adk-ts

A robust framework for building AI agents with multi-provider LLM support

This framework helps TypeScript developers build sophisticated AI agents that can automate complex, multi-step tasks. You provide the agent's logic and integrate various large language models (LLMs) and tools, and the framework helps orchestrate their interactions. The output is a production-ready AI application capable of handling dynamic conversations and workflows, ideal for software engineers creating intelligent systems.

AI-agent-development software-engineering intelligent-automation TypeScript-development LLM-application-development

Scores updated daily from GitHub, PyPI, and npm data. How scores work