Agent Runbook is an open-source contract-based multi-agent skill framework developed by KnoxOps. It acts as an orchestrator and compiler that converts declarative YAML runbooks into structured SKILL.md documentation and executable agent skills with strict output validation.
YAML to SKILL.md Compilation — Compiles high-level YAML runbook specifications into structured, standardized SKILL.md agent execution files. - Contract-Based Step Execution — Enforces rigid output schemas across multi-step agent workflows using JSON Schema validation. - Zero-Dependency Schema Validation — Bundles a Python standard-library JSON Schema validator (validate_schema.py) without requiring third-party dependencies. - Multi-Language i18n Support — Built-in localization support for generating runbook skills across 9 different languages. - Control Flow & Loops — Supports advanced step orchestration patterns including loop strategies, automated remediation cycles, and human approval steps.
Use cases
Use Case: Automated Host Health Remediation Engineers define a multi-step host diagnostic and fix runbook in YAML with loop controls and human-in-the-loop approval triggers. Agent Runbook compiles this into executable skills that guide agents through diagnostic steps and schema-validated remediation reports.
Use Case: Schema-Enforced Multi-Step Tool Workflows Developers requiring deterministic structured outputs from agent tool calls use Agent Runbook to compile steps with embedded JSON Schema validations. The generated skill ensures that the agent checks schemas and runs strict validation before completing a task.
Use Case: Standardized Team Operations Runbooks Platform teams compile standard operating procedures into multi-lingual Markdown skills so that AI coding agents across distributed teams execute identical operational procedures predictably.
Who it is for
Agent Runbook is intended for platform engineers, DevOps teams, and AI tool developers building deterministic multi-step agent skills and automated operational runbooks. It is not designed as a standalone interactive chat interface or single-turn coding assistant.
Install guide
Installation Clone the repository and install the package using Python: bash git clone https://github.com/KnoxOps/agent-runbook.git cd agent-runbook pip install -e . To install development dependencies: bash pip install -e ".[dev]"
First Run Verify that the runbook generator is operational by running tests: bash pytest
Example Session Compile a YAML runbook into a validated skill package: bash python -m agent_runbook.generator --input examples/host-health-loop.yaml --output ./skills/host-health To run strict validation on an agent's step output: bash python scripts/validate_schema.py --schema path/to/schema.json --data path/to/output.json --strict
SWE-agent — SWE-agent is an open-source autonomous software engineering agent harness built and maintained by researchers from Princeton University and Stanford University.…
AgentLint — AgentLint is an open-source repository linting, validation, and workflow enforcement harness developed by 0xmariowu. It is designed to enforce structural…
Weaver — Weaver is an open-source agent harness and orchestration framework maintained by sean35mm on GitHub. Built on top of the Bun…
Context Bridge — Context Bridge is an open-source CLI agent harness and context orchestration utility developed by serdardb. It is built to facilitate…
Hivelore — Hivelore is an open-source agent harness and contextual memory orchestrator created by Doucs91. It provides persistent project memory, decision tracking,…
Agentic Engineering Framework — Agentic Engineering Framework is an open-source orchestration harness and governance layer developed by Dimitri Geelen. It is designed to constrain,…