open-agent-spec and agentspecs

open-agent-spec
52
Established
agentspecs
38
Emerging
Maintenance 13/25
Adoption 11/25
Maturity 18/25
Community 10/25
Maintenance 13/25
Adoption 7/25
Maturity 18/25
Community 0/25
Stars: 6
Forks: 1
Downloads: 1,371
Commits (30d): 0
Language: Python
License: MIT
Stars: 2
Forks:
Downloads: 105
Commits (30d): 0
Language: Python
License: BSD-3-Clause
No risk flags
No risk flags

About open-agent-spec

prime-vector/open-agent-spec

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).

Enforces strict input/output schema validation to prevent silent failures when LLM responses deviate from expected structure, and supports both direct execution via `oa run` and Python scaffold generation via `oa init` for gradual customization. Uses Jinja2 templating for dynamic prompts and provides a CLI-first workflow that keeps agent definitions versioned in `.agents/` directories for CI/CD integration and multi-engine portability.

About agentspecs

datalayer/agentspecs

🤖 👷 Agentspecs - YAML-based specifications for AI agents, MCP servers, skills, and environment variables.

Related comparisons

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