DISCOVER THE FUTURE OF AI AGENTS

GitHub Agentic Workflows

Added Feb 23, 2026
Agent & Tooling
Open Source
Workflow AutomationModel Context ProtocolGoAI AgentsAgent FrameworkAgent & ToolingDeveloper Tools & CodingAutomation, Workflow & RPA

Write agentic workflows in natural language markdown and run them in GitHub Actions. Developed by GitHub Next and Microsoft Research.

Overview#

gh-aw is an open-source framework developed by GitHub Next and Microsoft Research that enables writing AI agent workflows in natural language markdown and running them in GitHub Actions.

Core Features#

Workflow Orchestration#

  • Markdown Workflow Definition: Use .md files + YAML frontmatter to define triggers, permissions, tools, etc.
  • Natural Language Instructions: Describe AI tasks in natural language within Markdown body—no traditional programming required
  • Modular Imports: Support for workflow snippet reuse and composition
  • Compile-time Validation: Schema validation, expression safety checks, Action SHA pinning

Multi-AI Engine Support#

EngineConfiguration
GitHub CopilotDefault engine, authenticated via COPILOT_GITHUB_TOKEN
Anthropic ClaudeConnected via ANTHROPIC_API_KEY
OpenAI CodexConnected via OPENAI_API_KEY

MCP Protocol Integration#

  • Connect external tools and services via Model Context Protocol (MCP)
  • MCP Gateway serves as unified HTTP gateway, isolating MCP servers from Agent runtime

Security Mechanisms (Defense-in-Depth)#

LayerMechanismProtection Goal
SubstrateGitHub Actions VM, Docker containers, iptablesMemory, process, and network isolation
ConfigurationSchema validation, Action SHA pinning, security scanningConfiguration validity, supply chain security
PlanLockdown Mode, Safe Outputs, threat detectionOperation scope limiting, output sanitization

Specific Security Features:

  • Safe Outputs: AI Agent has read-only permissions by default; write operations execute through pre-approved independent Jobs
  • Agent Workflow Firewall (AWF): Network egress control with domain-based access control
  • MCP Gateway: Unified HTTP gateway routing MCP calls, isolating MCP servers
  • Content Sanitization: @mention neutralization, Bot trigger protection, XML/HTML tag conversion
  • Secret Redaction: Automatic scanning and masking of sensitive information
  • Threat Detection Pipeline: AI-driven threat detection jobs, integrable with TruffleHog, Semgrep

Typical Use Cases#

ScenarioDescription
Automated Daily ReportsGenerate daily repository status reports, analyze issues/PRs/discussions/releases
Intelligent Issue TriageAutomatic triage, labeling, and commenting
Code Review AssistanceAutomated code review suggestion generation
Continuous DocumentationKeep README, API docs synchronized with code
Incremental Code ImprovementBatched, auditable code quality improvements

CLI Core Commands#

CommandPurpose
gh aw compileGenerate .lock.yml GitHub Actions config from .md workflow
gh aw compile --watchWatch mode, auto-compile on file changes
gh aw run <workflow>Trigger specified workflow run
gh aw logsDownload and analyze run logs
gh aw audit <run-id>Investigate specific run details
gh aw statusCheck workflow health status

Quick Start#

# 1. Install extension
gh extension install github/gh-aw

# 2. Add sample workflow
gh aw add-wizard githubnext/agentics/daily-repo-status

# 3. Wait for workflow completion (~2-3 minutes)

# 4. Customize workflow
gh aw compile

Companion Projects#

  • Agent Workflow Firewall (AWF): AI Agent network egress control
  • MCP Gateway: Unified gateway for MCP server calls

Related Projects

View All

STAY UPDATED

Get the latest AI tools and trends delivered straight to your inbox. No spam, just intelligence.