Skip to main content

Integrations

CoderFlow works with a wide range of platforms and technologies. Agents run in Docker containers, so any development environment that can be containerized can be used with CoderFlow.

Standard Platforms​

Modern development platforms work with CoderFlow through standard Docker environments:

  • Node.js — JavaScript and TypeScript applications
  • .NET — C# and F# applications
  • Java — Spring, Maven, Gradle projects
  • Python — Django, Flask, data science workflows
  • Go, Rust, Ruby — And other languages with Docker support

For these platforms, administrators configure environments with the appropriate runtimes, tools, and dependencies. Agents then use standard development workflows—editing code, running builds, executing tests.

Automation Triggers​

CoderFlow automations can be started by external systems:

  • Inbound webhooks - GitHub, Stripe, internal services, or other JSON senders post to a secret CoderFlow URL.
  • SCM polling - Scheduled automations poll GitHub or Azure DevOps and run only when a watched branch changes.
  • Microsoft 365 — Mailbox automations receive push notifications through a webhook or Azure Event Hubs. New emails start tasks and replies follow up on their conversation's task. Mailbox access is read-only.

See Webhooks & SCM Triggers for setup, signature verification, examples, and troubleshooting.

Agent Handoff (MCP)​

CoderFlow can also run as a Model Context Protocol (MCP) server. External agents such as Claude Code, Claude Desktop / Cowork, and GitHub Copilot connect with a personal API key and hand work to CoderFlow directly: they create tasks (including a summary and transcript of the session they are coming from), check status, read the results (judge and review verdicts, agent responses, failure diagnostics, and output files), and send follow-ups.

See MCP Server for enabling the endpoint and connecting clients.

Email (Outlook)​

The optional Outlook add-in adds a Create CoderFlow task button to the email a user is reading. The user picks the environment, adds instructions and chooses attachments, and CoderFlow starts a task with the email. The add-in does not monitor mailboxes: only emails users send with its button reach the server through the add-in. Automatic monitoring is available separately through an opt-in Microsoft 365 mailbox automation.

See Outlook Add-in for enabling, deploying through the Microsoft 365 admin center, and using it.

IBM i​

IBM i is a specialized integration for enterprise legacy systems. Most AI tools cannot work with IBM i applications, but CoderFlow provides deep integration:

  • Compile RPG, COBOL, and CL programs using native IBM i compilers
  • Query DB2 databases via high-performance RAS connections
  • Test applications through 5250 terminal and Rich Display sessions
  • Modernize legacy code with automated verification

See the IBM i section for details on RAS, codermake, and AI tools for IBM i development.

Custom Environments​

Organizations can create custom environments tailored to their specific needs:

  • Legacy systems — Mainframe, AS/400, or other platforms with remote access
  • Specialized toolchains — Custom build systems, proprietary compilers
  • Hybrid architectures — Combinations of modern and legacy components

Custom environments are configured by administrators with the necessary tools, connections, and agent instructions. Once configured, agents work with these environments like any other.

Configuring Integrations​

All integrations are configured at the environment level. Administrators define:

  • Docker images with required tools and runtimes
  • Connection details for remote systems
  • Agent instructions (AGENTS.md)
  • Skills assigned to the environment (managed in Administration -> Skills)
  • Build and test commands

See Environments in the Administration section for configuration details.