A · level
gemini-cli
97.9
108,897 stars · Apache-2.0
AI Agents
Too close to call · 97.9 to 97.1
A · level
97.9
108,897 stars · Apache-2.0
B · level
97.1
94,309 stars · Apache-2.0
gemini-cli versus ragflow is a AI Agents comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. gemini-cli is written mainly in TypeScript; ragflow is written mainly in Go. The composite score is 97.9 for gemini-cli and 97.1 for ragflow.
gemini-cli has 108,897 GitHub stars to ragflow's 94,309, a gap of 14,588 (1.15×). Forks are 14,956 for gemini-cli and 11,335 for ragflow. On the log scale used inside this pair, adoption is 100 versus 99, and the fork community is 100 versus 97.
Push history: gemini-cli 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 739 for gemini-cli (0.007 per star) and 1,317 for ragflow (0.014 per star). Issue-health scores are 84 and 84; activity scores are 100 and 100.
Both gemini-cli and ragflow are listed as Apache-2.0. 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. The license score is therefore level at 96 versus 96, and the decision moves to adoption, activity, and hosting. This is a procurement signal, not legal advice.
In AI Agents, both gemini-cli (108,897 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: gemini-cli is open source, ragflow is open source.
gemini-cli is ahead on every scored dimension that is not level. Level dimensions: recent activity, issue health, license flexibility, self-hosting. The widest gap is fork community at 3 points (100 vs 97), and the tightest is self-hosting at 0 points (100 vs 100).
Composite score: gemini-cli 97.9, ragflow 97.1. The margin is under one point, so this page calls a tie. Use the dimension breakdown rather than the headline number.
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 | gemini-cli | ragflow |
|---|---|---|
| GitHub stars | 108,897 | 94,309 |
| Forks | 14,956 | 11,335 |
| Open issues | 739 | 1,317 |
| Adoption | 100 | 99 |
| Activity | 100 | 100 |
| Community | 100 | 97 |
| Issue health | 84 | 84 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 97.9 | 97.1 |
An open-source AI agent that brings the power of Gemini directly into your terminal.
RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.
gemini-cli has more GitHub stars: 108,897 versus 94,309 for ragflow. The gap is 14,588 stars.
Both were last pushed on 17 November 2026.
Yes. This catalog marks both gemini-cli and ragflow as self-hostable. Confirm each project's deploy docs before you plan a migration.
gemini-cli 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. 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.
Neither tool clears a one-point margin. gemini-cli scores 97.9 and ragflow scores 97.1.