open-harness
Lightweight, composable building blocks for creating capable AI agents. Built on Vercel AI SDK.
open-harness at a Glance
- Pricing
- Free
- How you use it
- TypeScript SDK installed with npm
- Who it's for
- Developers building AI agent products
- Works with
- Vercel AI SDK OpenAI Anthropic Google
open-harness Key Features
- Composable agent primitives
- Context compaction
- Hierarchical subagents
- MCP integration
- Tool permissions
Can't Find What You're Looking For?
We build custom AI agents tailored to your specific business needs. From ideation to deployment, TinyAI.Tools is your partner in AI innovation.
No commitment required. Let's discuss your ideas.
open-harness Alternatives
Deuz-SDK
A pure, web-first, multi-provider TypeScript AI SDK with zero runtime dependencies and one canonical streaming wire.
AgentsKit
Build agents without gluing many libraries together. A composable TypeScript foundation for runtime, tools, memory, RAG, and chat interfaces.
Hypha
Harness-oriented agent system framework for production-grade LLM agent applications - CodeSoul-co/Hypha
Octochains
A lightweight Python framework for parallel, isolated, collaborative AI reasoning. - ahmadvh/octochains
Strands Agents
Strands is the open source toolkit for building production AI agents in Python and TypeScript: an agent harness and SDK, sandboxed shell, evals, and research labs.
Agenticle
A lightweight, extensible Python framework for building and orchestrating single or multi-agent AI systems. | 一个轻量、可扩展的 Python 框架，用于构建和编排单智能体或多智能体 AI 系统。 - A03HCY/Agenticle