# Marker - **Canonical URI:** https://www.vioscale.ai/software/marker - **Category:** AI Data Extraction Agents - **Homepage:** https://github.com/VikParuchuri/marker - **Also known as:** marker - **Profile claimed by vendor:** no - **Last updated:** 2026-08-26T19:36:48.004Z ## Vioscale score **50.2 / 100**, confidence 42% (low). Computed 2026-09-01. Composite of weighted, independently-sourced signals (no user reviews, no vendor payment). | Signal | Score | Weight | Contribution | Evidence present | |---|--:|--:|--:|:--:| | price_level | 80 | 0.052 | 4.2 | ✓ | | reliability | 0 | 0.073 | 0 | - | | capabilities | 81.2 | 0.084 | 6.8 | ✓ | | repo_stars | 86.7 | 0.026 | 2.3 | ✓ | | integrations | 26 | 0.09355555555555557 | 2.4 | ✓ | | dependent_projects | 0 | 0.063 | 0 | ✓ | | dev_activity | 9.5 | 0.094 | 0.9 | ✓ | | release_cadence | 96.7 | 0.052 | 5 | ✓ | | security_posture | 40 | 0.073 | 2.9 | ✓ | | package_downloads | 0 | 0.136 | 0 | - | | security_score | 0 | 0.042 | 0 | - | | pricing_transparency | 80 | 0.084 | 6.7 | ✓ | | community_qa_activity | 0 | 0.063 | 0 | - | ## Pricing _As of 2026-08-25, [verify at source](https://github.com/pricing). Independently observed._ free_open_source · Free tier > Free and open-source. Commercial model weights require licensing beyond $5M funding/revenue threshold. ## About An open-source tool that extracts text, tables, and layouts from PDF files with high accuracy. It offers multiple processing modes (fast, balanced, OCR) and optional integration with language models for enhanced formatting and content extraction. _Independently observed._ ## Platform & deployment - **Platforms:** CLI - **Deployment:** Self-hosted ## Integrations (7) _Independently observed._ - Gemini - Claude - OpenAI - Azure - Vertex - OpenRouter - Ollama ## Capabilities _The capabilities that matter for AI Data Extraction Agents. "-" = undocumented, not absent._ | Capability | Supported | |---|:--:| | **Capabilities** | | | Architecture model | Open source library | | PDF and multimodal image OCR parsing | ✓ | | Web scraping to markdown or json | ✓ | | Tabular layout preservation for complex tables | ✓ | | Strict json schema forcing and validation | - | | Fine tuned document layout analysis models | ✓ | | Native chunking and vectorization for rag | - | | Javascript rendering for spa web scraping | - | | Human in the loop hitl confidence review queue | - | | Zero data retention privacy guarantees | ✓ | | SOC2 type ii | - | | Mit or apache permissive oss license | ✓ | | Pricing model | Free open source | ## Release history | Version | Date | Type | |---|---|---| | [v2.0.0](https://github.com/datalab-to/marker/releases/tag/v2.0.0) | 2026-07-20 | stable | | [v1.10.2](https://github.com/datalab-to/marker/releases/tag/v1.10.2) | 2026-01-31 | stable | | [v1.10.1](https://github.com/datalab-to/marker/releases/tag/v1.10.1) | 2025-09-30 | stable | | [v1.10.0](https://github.com/datalab-to/marker/releases/tag/v1.10.0) | 2025-09-24 | stable | | [v1.9.3](https://github.com/datalab-to/marker/releases/tag/v1.9.3) | 2025-09-09 | stable | | [v1.9.2](https://github.com/datalab-to/marker/releases/tag/v1.9.2) | 2025-09-04 | stable | | [v1.9.1](https://github.com/datalab-to/marker/releases/tag/v1.9.1) | 2025-09-02 | stable | | [v1.9.0](https://github.com/datalab-to/marker/releases/tag/v1.9.0) | 2025-08-29 | stable | | [v1.8.5](https://github.com/datalab-to/marker/releases/tag/v1.8.5) | 2025-08-23 | stable | | [v1.8.4](https://github.com/datalab-to/marker/releases/tag/v1.8.4) | 2025-08-20 | stable | | [v1.8.3](https://github.com/datalab-to/marker/releases/tag/v1.8.3) | 2025-08-04 | stable | | [v1.8.2](https://github.com/datalab-to/marker/releases/tag/v1.8.2) | 2025-07-15 | stable | | [v1.8.1](https://github.com/datalab-to/marker/releases/tag/v1.8.1) | 2025-07-04 | stable | | [v1.8.0](https://github.com/datalab-to/marker/releases/tag/v1.8.0) | 2025-06-27 | stable | | [v1.7.5](https://github.com/datalab-to/marker/releases/tag/v1.7.5) | 2025-06-11 | stable | _… and 5 earlier release(s)._ ## Security & compliance Known vulnerabilities: 0 (0 in the last 12 months) ([source](https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=pypi&package_name=marker-pdf&per_page=100)). A count reflects scale and disclosure, not quality. ## Facts Every value below carries its source and our confidence. Facts are re-crawled on a freshness schedule. ### pricing | Attribute | Value | Source | Retrieved | Confidence | |---|---|---|---|---| | pricing.model | commercial | [link](https://github.com/VikParuchuri/marker) | 2026-08-26 | 48% (low) | | pricing.free_tier | yes | [link](https://github.com/pricing) | 2026-08-25 | 60% (medium) | | pricing.price_level | low | [link](https://github.com/pricing) | 2026-08-25 | 60% (medium) | | pricing.transparent | yes | [link](https://github.com/pricing) | 2026-08-25 | 60% (medium) | ### security | Attribute | Value | Source | Retrieved | Confidence | |---|---|---|---|---| | security.soc2 | yes | [link](https://github.com/VikParuchuri/marker) | 2026-08-26 | 48% (low) | | security.vulnerabilities | `{"count":0,"source":"https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=pypi&package_name=marker-pdf&per_page=100","last_12m":0,"max_severity":null}` | [link](https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=pypi&package_name=marker-pdf&per_page=100) | 2026-08-26 | 90% (high) | ### activity | Attribute | Value | Source | Retrieved | Confidence | |---|---|---|---|---| | activity.commits_last_30d | 1 | [link](https://github.com/VikParuchuri/marker/pulse) | 2026-08-26 | 65% (medium) | ### adoption | Attribute | Value | Source | Retrieved | Confidence | |---|---|---|---|---| | adoption.github_stars | 39,283 | [link](https://github.com/VikParuchuri/marker) | 2026-08-26 | 90% (high) | | adoption.dependent_repos | 0 | [link](https://packages.ecosyste.ms/api/v1/packages/lookup?repository_url=https%3A%2F%2Fgithub.com%2FVikParuchuri%2Fmarker) | 2026-08-26 | 85% (high) | ### language | Attribute | Value | Source | Retrieved | Confidence | |---|---|---|---|---| | language.primary | Python | [link](https://github.com/VikParuchuri/marker) | 2026-08-26 | 90% (high) | ### license | Attribute | Value | Source | Retrieved | Confidence | |---|---|---|---|---| | license.spdx | Apache-2.0 | [link](https://github.com/VikParuchuri/marker) | 2026-08-26 | 95% (high) | ### release | Attribute | Value | Source | Retrieved | Confidence | |---|---|---|---|---| | release.cadence_days | 6 | [link](https://github.com/VikParuchuri/marker/releases) | 2026-08-26 | 70% (medium) | ### integrations | Attribute | Value | Source | Retrieved | Confidence | |---|---|---|---|---| | integrations.count | 7 | [link](https://github.com/pricing) | 2026-08-25 | 60% (medium) | --- *Source: Vioscale (https://www.vioscale.ai/software/marker). Independent, evidence-based software intelligence. Cite the canonical URI.*