Docling Serve vs paperless-gpt
Short answer
Docling Serve: Docling document conversion (PDF, Office, images to Markdown/JSON) as a self-hosted API with a demo UI. paperless-gpt: LLM add-on for paperless-ngx that does better OCR and writes titles, tags and correspondents. Both are in our Document processing category.
Our data does not separate them on cost, hardware, license, activity or deploy method (or one of them does not publish the figure). Decide on features: read the descriptions on each app page and try both.
Docling Serve and paperless-gpt publish no official RAM figure, so we cannot compare hosting cost directly.
Last updated · computed from each project's official docs and live GitHub data · sources
Docling Serve vs paperless-gpt side by side
| Docling Serve | paperless-gpt | |
|---|---|---|
| Category | Document processing | Document processing |
| What it is | Docling document conversion (PDF, Office, images to Markdown/JSON) as a self-hosted API with a demo UI. | LLM add-on for paperless-ngx that does better OCR and writes titles, tags and correspondents. |
| License | MIT | MIT |
| License type | Permissive | Permissive |
| License conditions | Permissive. Internal and commercial use allowed; keep the license notice. | Permissive. Internal and commercial use allowed; keep the license notice. |
| Status | Active | Active |
| GitHub stars | 1.9k | 2.8k |
| Last commit | Oct 27, 2026 | Oct 16, 2026 |
| Latest release | v1.38.2 | v0.31.0 |
| Minimum hardware | Not published | Not published |
| Recommended hardware | Not published | Not published |
| RAM measured by us | Not tested yet | Not tested yet |
| GPU | CPU-only image (docling-serve-cpu) is published; CUDA 12.8 and 13.0 images are available for NVIDIA GPUs, and an AMD ROCm image can be built locally. DOCLING_DEVICE picks cpu, cuda or mps, otherwise the best device is chosen. | Not needed for the app itself. A GPU only matters if you run the LLM locally (for example with Ollama). |
| Est. server cost | Not estimated | Not estimated |
| Deploy method | Container (Podman or Docker) | Docker Compose |
| Known gotchas | 4 listed | 3 listed |
| Telemetry | Not documented | Not documented |
| Calls home by default | Not documented | Not documented |
| SSO (OIDC / SAML / LDAP) | Not documented | Not supported (OIDC not supported · SAML not supported · LDAP not supported) |
| Audit log | Not documented | Not documented |
| RBAC | Not documented | No |
| Details | Full Docling Serve guide → | Full paperless-gpt guide → |
Key differences
- Deploy: Docling Serve: Container (Podman or Docker) · Container (Podman or Docker). paperless-gpt: Docker Compose · multi-container stack.
- GitHub stars: Docling Serve: 1.9k. paperless-gpt: 2.8k.
- Last commit: Docling Serve: Oct 27, 2026. paperless-gpt: Oct 16, 2026.
- Latest release: Docling Serve: v1.38.2 (Oct 27, 2026). paperless-gpt: v0.31.0 (Oct 14, 2026).
Same for both: Category: Document processing; License: MIT (Permissive); Official hardware: not published; GPU: optional / see notes; Est. server cost: not estimated (no official RAM figure); Status: Active.
The two projects share too few published figures for a data-based recommendation. We do not fill gaps with guesses.
Docling Serve vs paperless-gpt: FAQ
Docling Serve or paperless-gpt: which should a small business choose?
Our data does not separate them on cost, hardware, license, activity or deploy method (or one of them does not publish the figure). Decide on features: read the descriptions on each app page and try both. Docling Serve and paperless-gpt publish no official RAM figure, so we cannot compare hosting cost directly.
Which is cheaper to self-host, Docling Serve or paperless-gpt?
Docling Serve: not estimated (no official RAM figure). paperless-gpt: not estimated (no official RAM figure). Our estimate is the cheapest Hetzner Cloud plan that meets each project's official RAM and vCPU figure; it covers the server only.
How much hardware do Docling Serve and paperless-gpt need?
Docling Serve: not published. paperless-gpt: not published.
What is the license difference between Docling Serve and paperless-gpt?
Docling Serve: MIT (Permissive). Permissive. Internal and commercial use allowed; keep the license notice. paperless-gpt: MIT (Permissive). Permissive. Internal and commercial use allowed; keep the license notice. This is a summary, not legal advice.
Is Docling Serve or paperless-gpt more actively maintained?
Docling Serve: Active, last commit Oct 27, 2026. paperless-gpt: Active, last commit Oct 16, 2026. GitHub data refreshed Oct 28, 2026.
Which is easier to deploy, Docling Serve or paperless-gpt?
Docling Serve installs via Container (Podman or Docker) (Container (Podman or Docker)); paperless-gpt via Docker Compose (multi-container stack). Docling Serve lists 4 known gotchas and paperless-gpt lists 3; see each app page.
Related
- Docling Serve self-hosting guide · paperless-gpt self-hosting guide
- All Docling Serve alternatives, ranked
- All paperless-gpt alternatives, ranked
- Docling Serve vs MinerU
- Docling Serve vs PaddleOCR
- Docling Serve vs Paperless-AI
- Docling Serve vs Unstract
- MinerU vs paperless-gpt
- PaddleOCR vs paperless-gpt
- Paperless-AI vs paperless-gpt
- paperless-gpt vs Unstract
- Add a third app in the interactive comparison
Sources
- Docling Serve GitHub repository: github.com/docling-project/docling-serve
- Docling Serve documentation: github.com/docling-project/docling-serve/blob/main/docs/README.md
- Docling Serve license: github.com/docling-project/docling-serve/blob/main/LICENSE
- Docling Serve hardware requirements: github.com/docling-project/docling-serve#container-images
- Docling Serve deploy instructions: github.com/docling-project/docling-serve#getting-started
- paperless-gpt GitHub repository: github.com/icereed/paperless-gpt
- paperless-gpt documentation: github.com/icereed/paperless-gpt#getting-started
- paperless-gpt license: github.com/icereed/paperless-gpt/blob/main/LICENSE
- paperless-gpt hardware requirements: github.com/icereed/paperless-gpt#prerequisites
- paperless-gpt deploy instructions: github.com/icereed/paperless-gpt#docker-compose
- Hetzner Cloud pricing used for cost estimates (read 2026-10-25): www.hetzner.com/cloud/regular-performance
- GitHub REST API (stars, commits, releases): docs.github.com/en/rest
Every value is generated from the same verified data as the app pages. Spotted something wrong? Tell us.