Use this command to install Argy Code with WinGet:
winget install --id=demkada.ArgyCode -e
Argy Code is an AI-powered coding tool designed to enhance productivity in the terminal environment. It provides developers with intelligent code suggestions, command history integration, real-time feedback, and multi-language support. Key Features include context-aware code completion that adapts to your workflow, seamless integration with terminal commands for a unified experience, and robust support for multiple programming languages.
Ideal for developers seeking to streamline their coding process in the terminal, Argy Code helps improve efficiency and accuracy while maintaining focus on development tasks. It can be installed via winget, making it easy to integrate into your existing workflow.
README
Argy Code
Your governed AI development team in the terminal.
50+ expert AI profiles in one agent — Clean Code, TDD, cloud architects, security, networks, COBOL, ABAP, every programming language. Interactive for daily work, autonomous for CI/CD. Governed by the Argy LLM Gateway (quotas, filters, audit).
Full terminal UI with chat interface, tool confirmations, session management, slash commands, and sub-agent orchestration. Designed for daily development work with human-in-the-loop confirmation.
Autonomous mode
argy run "Write unit tests for src/auth.ts"
argy run --agent code-reviewer --model argy-gateway/claude-sonnet-4-5 "Review PR #42"
argy run --max-turns 10 "Refactor the database layer"
# Stdin support
git diff | argy run "Summarize these changes for a PR description"
cat error.log | argy run "Diagnose this error and suggest a fix"
Non-interactive, deterministic, machine-readable. Designed for CI/CD pipelines, cron jobs, and orchestrators.
# Multi-step pipeline
argy run "Analyze the codebase and list all API endpoints" && \
argy run -c "Generate OpenAPI documentation for each endpoint" && \
argy run -c "Write integration tests for the 3 most critical endpoints"
# Parallel agents
argy run --agent security-auditor "Audit authentication flows" &
argy run --agent performance-analyst "Profile the database queries" &
wait
# JSON output for programmatic consumption
argy run --format json "Run security scan" | jq '.events[]'
# Exit code usage
argy run "Deploy to staging" && echo "Deployed" || echo "Deployment failed"
Built-in agents
Agent
Mode
Description
build
primary
Default. Full tool access with write governance
plan
primary
Research-first, read-only by default
docgen
primary
Generate PowerPoint and Excel documents
general
subagent
General-purpose parallel sub-agent
explore
subagent
Fast read-only codebase exploration
Custom agents can be defined in .argy/agent/ as Markdown files with YAML frontmatter.