by prime-vector · AI 工具 · ★ 13
Open Agent Spec (OA) Define AI agents as contracts, not scattered prompts. Open Agent Spec lets you define an agent once in YAML, validate inputs and outputs against a schema, and either run it directly with or generate a Python scaffold with . Why This Exists Most agent systems are hard to reason about: outputs are not strictly typed behaviour is buried in prompts logic is split across Python, Markdown, and framework abstractions swapping models often breaks things in subtle ways The Idea Open Agent Spec treats an agent like infrastructure. Think OpenAPI or Terraform, but for AI agents.
| Stars | 13 |
| Forks | 2 |
| Language | Python |
| Category | AI 工具 |
| License | MIT |
| Quality Score | 39.7/100 |
| Open Issues | 1 |
| Last Updated | 2026-06-11 |
| Created | 2025-07-21 |
| Platforms | claude-code, cli, python |
| Est. Tokens | ~6482k |
These tools work well together with open-agent-spec for enhanced workflows:
Explore other popular ai 工具 tools:
open-agent-spec is Open Agent Spec is a declarative YAML standard and CLI for defining and generating AI agents. One spec, any LLM engine (OpenAI, Anthropic, Grok, Cortex, local, custom).. It is categorized as a AI 工具 with 13 GitHub stars.
open-agent-spec is primarily written in Python. It covers topics such as agent-framework, agentic-ai, ai.
You can find installation instructions and usage details in the open-agent-spec GitHub repository at github.com/prime-vector/open-agent-spec. The project has 13 stars and 2 forks, indicating an active community.
open-agent-spec is released under the MIT license, making it free to use and modify according to the license terms.