Feedbacker vs Pawtograder
Feedbacker
feedbacker.educationPawtograder
pawtograder.comSide by side
| Figure | Feedbacker | Pawtograder |
|---|---|---|
| Price from | — | Free |
| Free plan | — | Yes |
| Free trial | — | — |
| Open source | — | — |
| Web | Yes | Yes |
| Windows | Yes | — |
| macOS | Yes | — |
| Linux | Yes | — |
| Self-hosted | — | Yes |
| Plans published | 0 | 1 |
| Spec score · Rubric Software | 7.5 (#14) | 7.6 (#12) |
Plans
In their own words
Feedbacker
Feedbacker is an open-source higher education project by Steve Huckle, currently being rebuilt as a workflow, governance, and assessment layer around AI for educators. Its present direction keeps educators responsible for marks and released feedback rather than delegating those decisions to an automated system. The project calls for traceability across inputs, criteria, transformations, suggestions, edits, and approvals. It also aims to let institutions govern and replace models, prompts, data handling, retention, and deployment. Planned rubric-led cohort workflows are intended to support moderation and calibration while preserving academic judgement. Feedbacker’s previous application has been retired, so its earlier capabilities describe the former product, not the project’s current state. That application offered rubric-driven assessment and batch generation of criterion-referenced feedback, with educators controlling rubrics and final judgements. It generated draft feedback rather than making grading decisions. Institutions could use a public deployment or self-host it, with control over data and AI configuration when self-hosting. The project lists Linux, macOS, web, and Windows platforms.
Pawtograder
Pawtograder combines autograding, manual grading, office hours, discussion, a gradebook, and analytics for computer science courses. Each commit can trigger tests through GitHub Actions, with results shown by test in the grading interface. Rubrics support additive, deductive, and multi-level criteria, line-level annotations, and separate scoring for group members. The gradebook includes MathJS expression columns, drop-lowest calculations, CSV import, and a student what-if mode. Office hours queues support text, video, and screen sharing, and can show linked submissions and failing tests. Discussions can surface relevant threads for known errors and allow public or staff-only posts. Calendar feeds and Discord channel mirroring cover course events; LTI 1.3 integrations with Canvas, Blackboard, Brightspace, and Moodle are listed as roadmap items. Optional AI-generated test hints and an MCP server for compatible AI clients are also listed. Instructors can use the project-hosted community instance or self-host on Kubernetes with Helm charts. The project is GPLv3 open source. The free community instance is for evaluation; ongoing use at scale requires contacting the project.