AppFactor vs Moderne (2026)

MCP Bridge, AppFactor's own product, generates MCP tool definitions from the customer's REST, GraphQL, SOAP and gRPC APIs with tool curation so agents can call existing systems without rewrites, self hosted inside the customer network; changes ship as pull requests through the customer's own pipelines and the action log exports to the customer's SIEM.

Sourcemcp-bridge.ai, appfactor.io and appfactor.io/enterpriseread 2026-09-29

Version control integration covers GitHub, GitLab and Bitbucket at multi-repository scale, artifact repository integration covers Artifactory and Nexus, build tool plugins cover Gradle and Maven, an IntelliJ plugin supports code search and recipe development, and a multi-repo CLI builds Lossless Semantic Trees and runs recipes locally.

Local and remote MCP servers expose recipes and type-aware search as deterministic tool calls to coding agents, and installable skills teach detected agents the recipe workflow. Language coverage spans Java, Kotlin and Groovy natively with JavaScript, TypeScript, C#, Python, Go, Ruby and COBOL added commercially.

Sourcemoderne.ai/technology, docs.moderne.io and github.com/openrewrite/rewriteread 2026-08-30

Work is carried by multiple agents with approval gates set per agent, per repository and per environment, and the agent that writes a change never approves it. Modernization runs through analysis, generation, testing and review phases, and capabilities run one at a time or together as a standing campaign across the estate.

Sourceappfactor.io, appfactor.io/capabilities and legacy-app-modernizationread 2026-09-29

Moddy is a multi-repo AI agent that takes natural language requests, such as help me upgrade to Spring Boot 3.5, searches for the appropriate OpenRewrite recipes and executes them across thousands of repositories.

It runs inside the Moderne Platform through the find, frame, fix and govern loop shared by humans and coding agents, and it is currently in a restricted beta that an administrator must configure in the tenant before use.

The generally available path is deterministic recipe execution, in which the Platform ingests repositories into Lossless Semantic Trees, runs recipes against them in parallel across the estate and surfaces every diff for review. There is no coordination between multiple agents and no agent handoff.

Sourcedocs.moderne.io/user-documentation/moddy/moddy-platform and moderne.ai/openrewriteread 2026-08-30

Auto maintenance runs as a standing policy across the estate, handling dependencies, patches and bugs as they appear instead of in a quarterly push or a one off project, within limits the customer sets for unattended work, so no one has to start each run.

Sourceappfactor.io/capabilities and agentic-software-engineering-team; appfactor.io/agentic-software-engineering-teamread 2026-09-29

Recipes run on demand through the Moderne Platform, the multi-repo CLI, and Gradle and Maven build tool plugins in continuous integration, with the IntelliJ plugin invoking search and recipes from the IDE and local and remote MCP servers letting coding agents trigger recipe runs. Moddy accepts natural language requests inside the Platform. There is no event-driven trigger such as a commit, pull request or newly published vulnerability, no scheduled run and no inbound chat or ticketing channel.

Sourcedocs.moderne.io and github.com/openrewrite/rewriteread 2026-08-30

Discovery reads every application, dependency and environment as it actually runs and maps services and endpoints into the reference agents work from, and documentation is rebuilt when the system changes, with ambiguities flagged for human review.

Sourceappfactor.io/discovery-and-documentationread 2026-09-29

The Lossless Semantic Tree is a type-aware model of source code preserving structure, types and formatting, which Moderne describes as going beyond code as text and beyond abstract syntax trees and as roughly equivalent to an IDE's internal representation. It powers the recipe catalog, semantic search across the estate, context resolution for coding agents over MCP and DevCenter visualizations from one foundation.

Prethink recipes generate pre-resolved structured knowledge about service endpoints, dependencies and test coverage so agents stop inferring architecture from raw code, and Trigrep provides type-aware search. The model spans dependencies and configuration across repository boundaries, so a question such as where payments processing occurs in a business unit can be answered across the estate.

Sourcemoderne.ai/technology, docs.moderne.io and github.com/openrewrite/rewriteread 2026-08-30

Discovery builds an estate map from running systems that the agents work from, and no memory the agents keep between runs is described.

Sourceappfactor.io and appfactor.io/capabilitiesread 2026-09-29

OpenRewrite builds the Lossless Semantic Tree in memory each time a recipe runs, while Moderne batch-builds LSTs once and serializes them so they are reused across repositories and across teams without rebuilding. That gives agents pre-computed context that persists between runs and lowers token overhead compared with reading a codebase file by file, and the Platform holds the ingested LSTs for the tenant. There is no conversational memory, learned context or adaptation from prior interactions.

Sourcegithub.com/openrewrite/rewrite and moderne.ai/technologyread 2026-08-30

Everything ships as a pull request reviewed by the customer's engineers, approval gates are set per agent, per repository and per environment, and an agent can never approve its own change. The customer sets what agents may do unattended, agents do not widen their own scope, and the console lists the items waiting on a person.

Sourceappfactor.io and appfactor.io/enterpriseread 2026-09-29

The Platform ingests repositories, runs recipes against them and surfaces every diff for the team to review. Changes are previewed before any ship, and every transformation can be reviewed and tested before mass commit. A govern stage is built into the find, frame, fix and govern loop shared by humans and coding agents, and Moderne holds that human judgment is essential when modifying code at scale. Because transformations are deterministic, the reviewed diff is exactly what lands. There is no configurable approval policy, permission scoping or role-based gate on agent actions.

Sourcemoderne.ai/openrewrite, moderne.ai/technology and the Moderne myths blogread 2026-08-30

AppFactor lists ISO 9001, 27001, 27017 and 27701 certifications, SAML, SCIM provisioning and role scoped gates, an immutable action log exportable to the customer's SIEM, and VPC, on premises or air gapped deployment with no egress to the vendor.

Sourceappfactor.io/enterpriseread 2026-09-29

The Moderne Platform is SOC 2 Type 2 compliant and available in multi-tenant or single-tenant deployment, with single sign-on and version control integration for GitHub, GitLab and Bitbucket plus Artifactory and Nexus for artifact repositories. A govern stage is built into the find, frame, fix and govern loop, and because transformations are deterministic, changes are provably consistent and traceable for compliance and audits. Moderne DX runs air-gapped and on premises so code never leaves the customer environment.

Sourcemoderne.ai/technology and docs.moderne.ioread 2026-08-30

Every action an agent takes is logged and attributed to an agent, a model and a cost in an immutable log exportable to the customer's SIEM, and the console collects every agent run, gate and cost in one place, with a log line behind every number.

Sourceappfactor.io/agentic-software-engineering-team, appfactor.io/enterprise and appfactor.ioread 2026-09-29

The Moderne Platform keeps a structured audit log of every user and system initiated action, recipe runs and commits among them, retained for a year and queryable through the GraphQL API or exported as CEF or CSV to a SIEM, and an activity view shows each organization's recipe runs, commits and visualizations. Every diff is previewed before it ships.

Sourcedocs.moderne.io audit-logging and activity-viewread 2026-09-29

Deployment runs in the customer's VPC, on premises or air gapped with no egress to the vendor, and MCP Bridge is self hosted inside the customer network and sold through the AWS and Azure marketplaces.

Sourceappfactor.io/enterprise and mcp-bridge.airead 2026-09-29

Moderne DX is an air-gapped, on-premises unified refactoring CLI and IDE solution with recipes and reporting, offered as a first-class product line. The hosted Platform is available in multi-tenant or single-tenant deployment, and the multi-repo CLI builds Lossless Semantic Trees and runs recipes locally, with a local MCP server operating directly on repositories checked out on the developer's own workstation. A free public service runs for tens of thousands of open source projects.

Sourcemoderne.ai/technology, docs.moderne.io and github.com/openrewrite/rewriteread 2026-08-30

Ten named capabilities (discovery, documentation, test generation, bug fixing, code smells, dependency upgrades, migration, Rust code generation, build and deploy, auto maintenance) can each be adopted alone, one capability on one service in one environment, or run together as a standing campaign.

Sourceappfactor.io/capabilitiesread 2026-09-29

The community-vetted OpenRewrite recipe catalog ships prepackaged deterministic transformations covering the most common modernization, migration and security work. Moderne says many enterprise teams arrive without prior OpenRewrite experience because the catalog covers that work, and expertise is needed only for authoring custom recipes.

Recipes compose and are extended commercially across JavaScript, TypeScript, C#, Python, Go, Ruby and COBOL beyond the native Java, Kotlin and Groovy. Moddy ships as a prebuilt multi-repo agent, and installable agent skills package recipe workflow guidance for any detected coding agent.

Sourcedocs.openrewrite.org, moderne.ai/openrewrite and docs.moderne.io/user-documentation/agent-tools/skillsread 2026-08-30

No model provider or model choice is named, and the action log attributes each action to a model without naming its provider.

Sourceappfactor.ioread 2026-09-29

Moddy takes a bring your own model approach. It ships no model of its own and the customer configures one, with Anthropic and OpenAI models among those supported and traffic routed through the customer's on premises agent. Moddy is still in a restricted beta that an administrator must configure per tenant, and the recipe engine itself uses no model.

Sourcedocs.moderne.io moddy-data-privacy and moddy-platformread 2026-09-29

No API, SDK, CLI or MCP server for the AppFactor platform itself is described, and the documentation covers the scanner, orchestrator and architecture. MCP Bridge works in the other direction, letting agents call the customer's own systems.

Sourcedocs.appfactor.io and mcp-bridge.airead 2026-09-29

A local MCP server runs through the Moderne CLI as a subprocess of the developer's coding agent, giving semantic code search, navigation and refactoring tools backed by the Lossless Semantic Tree and Trigrep against locally checked-out repositories. A remote MCP server hosted on the Moderne Platform runs recipes against repositories already ingested into the tenant.

The CLI installs agent tools, both skills and MCP servers, for all detected agents with a single command, teaching them recipe creation, running at scale and impact analysis. Customers can develop custom recipes on an open-source engine, with a multi-repo CLI and an IntelliJ plugin for recipe development.

Sourcedocs.moderne.io/user-documentation/agent-tools/mcp/overview, docs.moderne.io/user-documentation/agent-tools/skills and github.com/openrewrite/rewriteread 2026-08-30

Test generation pins existing behavior with generated tests before anything changes so a later rewrite can be proven, and each capability ships as a reviewed pull request. Those tests check the customer's code and the agents' output, and no tools to test or regression test the agents' own behavior are described.

Sourceappfactor.io/capabilitiesread 2026-09-29

Every transformation can be reviewed and tested before application, with the platform previewing changes before anything ships, and custom recipe development includes testing idioms and a testing framework so recipe authors verify a recipe's behavior before it runs at scale. Agent skills teach coding agents to analyze the impact of what changed. These test transformations and recipes. There is no evaluation harness, benchmark suite or regression testing surface for Moddy or for connected coding agents.

Sourcedocs.openrewrite.org, docs.moderne.io and the Moderne myths blogread 2026-08-30

The platform works through code, running systems, pipelines and APIs, and no browser control or operation of software through a graphical interface is described.

Sourceappfactor.io, appfactor.io/capabilities and mcp-bridge.airead 2026-09-29

The platform operates on Lossless Semantic Trees built from source code and acts through programmatic interfaces throughout, namely source control APIs for GitHub, GitLab and Bitbucket, Gradle and Maven build tooling, Artifactory and Nexus artifact repositories, a CLI, an IntelliJ plugin and MCP tool calls. It offers no browser control, screenshot capture, visual verification or operation of software lacking a programmatic interface.

Sourcemoderne.ai/technology and docs.moderne.ioread 2026-08-30