AgentsKit vs OxyGent
JavaScript agent toolkit and Python multi-agent framework compared
agentskit is a TypeScript toolkit for composing AI agents from model adapters, runtime, tools, memory, retrieval, and interfaces. OxyGent is a Python framework centered on reusable components and collaboration among agents, with planning and execution visibility as part of its approach.
AgentsKit: Build Modular AI Agents in JavaScript
AgentsKit is a TypeScript toolkit for building AI agents in JavaScript, from chat interfaces to autonomous runtimes. Its small core and shared contracts connect provider adapters, tools, memory, retrieval, and UI packages.
OxyGent: Build Modular Multi-Agent AI Systems
OxyGent is a Python framework for assembling tools, language models, and agents into modular multi-agent systems. It suits developers who need reusable components, configurable agent collaboration, and observable execution paths.
| AgentsKit | OxyGent | |
|---|---|---|
| Language | TypeScript | Python |
| License | MIT | NOASSERTION |
| Stars | 36 | 2.1k |
| Forks | 3 | 276 |
| Last analyzed | Oct 20, 2026 | Oct 4, 2026 |
Key differences
- agentskit targets JavaScript and TypeScript, while OxyGent targets Python.
- agentskit supports assembling a broad agent stack, including React and terminal interfaces; OxyGent focuses on multi-agent systems with configurable agent relationships and sub-agents.
- agentskit offers provider adapters and packages that can be adopted individually; OxyGent organizes tools, models, and agents around its shared Oxy component model and supports hot-swapping.
- agentskit identifies its core package as stable and the rest of its ecosystem as beta; OxyGent describes dynamic planning, dependency mapping, visual debugging, and decision auditability.
- agentskit lists an MIT license; OxyGent's repository data reports NOASSERTION, while its README advertises Apache 2.0, so verify the applicable license.
- agentskit targets Node.js 20+ and modern JavaScript runtimes; OxyGent needs provider configuration and credentials for LLM use, and its README recommends Node.js when using MCP.
Choose AgentsKit if you…
- need a JavaScript or TypeScript toolkit with interchangeable model adapters and composable agent packages.
- want React, terminal, or headless options for building an agent application.
- plan to add tools, memory, or retrieval, and can check the stability of beta packages.
Choose OxyGent if you…
- need reusable Python components for systems where agents collaborate or delegate tasks.
- want to configure agent relationships and explore dynamic or hybrid planning.
- need execution visibility features such as dependency mapping, visual debugging, or decision auditability.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.