A · leads
AutoGPT
99.1
188,072 stars · MIT
AI Agents
AutoGPT leads by 4.9 · narrow
A · leads
99.1
188,072 stars · MIT
B
94.2
94,309 stars · Apache-2.0
AutoGPT versus ragflow is a AI Agents comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. AutoGPT is written mainly in Python; ragflow is written mainly in Go. The composite score is 99.1 for AutoGPT and 94.2 for ragflow.
AutoGPT has 188,072 GitHub stars to ragflow's 94,309, a gap of 93,763 (1.99×). Forks are 45,866 for AutoGPT and 11,335 for ragflow. On the log scale used inside this pair, adoption is 100 versus 94, and the fork community is 100 versus 87.
Push history: AutoGPT was last pushed on 17 November 2026 (0 days ago), and ragflow was last pushed on 17 November 2026 (0 days ago). Open issues stand at 676 for AutoGPT (0.004 per star) and 1,317 for ragflow (0.014 per star). Issue-health scores are 96 and 84; activity scores are 100 and 100.
AutoGPT is listed as MIT, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. ragflow is listed as Apache-2.0, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. License scores in this pair are 96 for AutoGPT and 96 for ragflow. This is a procurement signal, not legal advice.
In AI Agents, both AutoGPT (188,072 stars) and ragflow (94,309 stars) are marked self-hostable. Deploy scores are 100 and 100. Running either one means you own upgrades, backups, and the license duties that follow a modified copy. Pricing labels on file: AutoGPT is open source, ragflow is open source.
AutoGPT is ahead on every scored dimension that is not level. Level dimensions: recent activity, license flexibility, self-hosting. The widest gap is fork community at 13 points (100 vs 87), and the tightest is self-hosting at 0 points (100 vs 100).
AutoGPT finishes ahead at 99.1 against ragflow at 94.2, a 4.9 point narrow margin under the published weights.
Scores are computed inside this pair only. Method and weights.
Bars are scaled within the row. Higher is stronger. Open issues are a raw count, so that row has no bar.
| Signal | AutoGPT | ragflow |
|---|---|---|
| GitHub stars | 188,072 | 94,309 |
| Forks | 45,866 | 11,335 |
| Open issues | 676 | 1,317 |
| Adoption | 100 | 94 |
| Activity | 100 | 100 |
| Community | 100 | 87 |
| Issue health | 96 | 84 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 99.1 | 94.2 |
AutoGPT is an experimental agent project that tries to break a goal into tool-using steps. It is a reference point in autonomous-agent work more than a finished business suite.
RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.
AutoGPT has more GitHub stars: 188,072 versus 94,309 for ragflow. The gap is 93,763 stars.
Both were last pushed on 17 November 2026.
Yes. This catalog marks both AutoGPT and ragflow as self-hostable. Confirm each project's deploy docs before you plan a migration.
AutoGPT is listed as MIT, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. ragflow is listed as Apache-2.0, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. Read both grants before you embed either codebase in a hosted product. This is not legal advice.
AutoGPT scores 99.1 and ragflow scores 94.2. This page calls that a narrow lead for AutoGPT.