agent-kit and agentsdk

These are competitors targeting the same problem space—both provide TypeScript SDKs for building AI agents with tool integration—though AgentKit is significantly more mature and production-ready with its MCP-based tooling and deterministic multi-agent orchestration versus Agent SDK's nascent system tools approach.

agent-kit
83
Verified
agentsdk
32
Emerging
Maintenance 16/25
Adoption 20/25
Maturity 25/25
Community 22/25
Maintenance 10/25
Adoption 4/25
Maturity 9/25
Community 9/25
Stars: 800
Forks: 121
Downloads: 42,224
Commits (30d): 1
Language: TypeScript
License: Apache-2.0
Stars: 7
Forks: 1
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.

Leverages a shared state machine (key-value store) combined with conversation history, enabling code-based or LLM-driven routers to orchestrate agent handoffs deterministically. Integrates with multiple model providers, MCP servers (via HTTP or stdio transports), and the Inngest orchestration platform for cloud deployment with built-in fault tolerance and tracing.

About agentsdk

Recusive/agentsdk

Agent SDK toolkit for Building AI agents with system tools

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