Skip to main content
Ragen is actively developed, and this page shows the shape of what is coming — both what is being built right now and what is planned further out. Nothing here carries a release date. Open work lives in GitHub Issues, and this page changes when a real install needs something that wasn’t anticipated.

​
Choosing Your Own Infrastructure

Three parts of Ragen are things you should be able to pick rather than inherit: what runs background jobs, what stores vectors, and what parses documents. The first has shipped — WORKER_RUNTIME picks between BullMQ and Temporal, and BullMQ is now the default, which is what took two containers and a gRPC dependency out of a standard install. The other two get the same treatment: a seam in front, a second implementation behind it.
Nothing is being taken away. Qdrant stays the default vector store and Docling stays the default parser, and Temporal remains a supported runtime for anyone who selects it — in ragen-enterprise, Apache-2.0 like Ragen itself, with its own worker image and its own parity suite.
One upgrade is not a no-op, and it is the one that looks like one. Temporal used to be what WORKER_RUNTIME resolved to when it was unset, so a deployment installed before the seam existed is running Temporal without ever having named it. That default is now bullmq. Upgrading such a deployment without setting anything moves it to a different engine at restart, and work already accepted by Temporal is orphaned — the new engine has never heard of it, and those documents sit in processing until something re-indexes them.Set WORKER_RUNTIME=temporal explicitly before you upgrade, and then decide about the move separately. If you do want BullMQ, follow switching runtimes on a running deployment: drain first, delete the schedules on the engine you are leaving, then switch.A deployment that already sets WORKER_RUNTIME explicitly, either way, is unaffected.
Two things worth understanding before assembling the smallest possible install:
  • The hosted parser is a data-processing decision, not a performance one. With DOCUMENT_PARSER=mistral, every ingested document is transmitted to a third party. That is the right trade for some deployments and disqualifying for others, which is why it will never be a silent fallback. See the Security page.
  • pgvector is a different retrieval system, not a port of the current one. Qdrant scores sparse vectors server-side; Postgres has no equivalent, so the lexical half of retrieval changes and the results change with it. It ships with published measurements or it does not ship.
The designs are public, one file each, in docs/specs/ — they name the trade-offs and failure modes rather than only the upside.

​
Also Next

These are the things actively in progress alongside the infrastructure flexibility work above.

Command Line

npm i -g ragen-cli installs a ragen command that scaffolds an installation, signs in, checks its connection, uploads documents, searches the knowledge base and asks it questions today. Managing custom MCP connectors comes next. See the CLI page.

Python Client

The TypeScript SDK is official and published. Python is the language most people integrating the API are actually writing in, and a Python client is next.

Slack Integration

An assistant you talk to in a channel, carrying the same retrieval-time access filter as the main application. This is distinct from the Slack connector that reads Slack as a source.

Verified Air-Gapped Config

A local model, local embeddings, no outbound path, and a script that demonstrates it end to end. The script exists: npm run appliance:egress-check. It runs the local-model stack on a network with no way out. It names any container that tries to leave. It covers ingest and chat today. Brain and the guardrails come next.

SAML, SCIM and MFA

Company sign-in over OpenID Connect, including Entra ID and Google Workspace, has shipped. See Company sign-in. SAML, SCIM directory sync and MFA come next.

docker compose up Demo

A docker compose up command that starts Ragen with sample documents and sample questions already loaded, so evaluating Ragen doesn’t begin with an empty knowledge base.

Microsoft 365 Connectors

SharePoint, OneDrive, Outlook, and Teams connectors to bring your Microsoft 365 content into a Ragen knowledge base.

Feedback Collection

In-application feedback on answers — the signal that retrieval quality work has been missing.

​
Later

These are planned but not actively in progress. They are on the list because real installs will eventually need them.
  • Permissions inherited from the source system, so revocation in Google Drive or SharePoint takes effect without waiting for a re-index.
  • Confluence and Jira connectors.
  • Web search and multi-step research as opt-in tools, because some installs deliberately have no outbound path and that must remain possible.
  • Audit log and security-event export to a SIEM, with retention and automatic deletion.
  • Organization export, so leaving Ragen is a documented procedure.
  • MFA and passkeys.
  • Per-user permissions for individual MCP tools.
  • Usage drill-down from organization to team to user to request, with budget alerts.
  • A sizing guide, a versioning policy, and a CHANGELOG.

​
Not Planned

Worth saying plainly, because it saves you evaluating Ragen for something it is not going to be.
  • Image generation, advanced voice mode, a code interpreter. Ragen answers from your documents. A general-purpose assistant is a different product, and there are good ones.
  • A knowledge graph layer. Improving retrieval that can be measured is the priority over adding a stage that cannot.

​
Follow Open Work

All open issues are tracked publicly. If something you need isn’t listed here, open an issue — this roadmap changes when a real install needs something unexpected.

GitHub Issues

Browse open issues, follow progress on active work, or file a new request.