A · leads
deepseek-harness
97.4
282,805 stars · MIT
AI Agents
deepseek-harness leads by 23.8 · decisive
A · leads
97.4
282,805 stars · MIT
B
73.6
18,321 stars · license n/a
deepseek-harness versus WrenAI is a AI Agents comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. deepseek-harness is written mainly in TypeScript; WrenAI is written mainly in Python. The composite score is 97.4 for deepseek-harness and 73.6 for WrenAI.
deepseek-harness has 282,805 GitHub stars to WrenAI's 18,321, a gap of 264,484 (15.44×). Forks are 35,041 for deepseek-harness and 2,115 for WrenAI. On the log scale used inside this pair, adoption is 100 versus 78, and the fork community is 100 versus 73.
Push history: deepseek-harness was last pushed on 13 November 2026 (4 days ago), and WrenAI was last pushed on 17 November 2026 (0 days ago). Open issues stand at 0 for deepseek-harness (0.000 per star) and 251 for WrenAI (0.014 per star). Issue-health scores are 96 and 84; activity scores are 92 and 100.
deepseek-harness 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. WrenAI is listed as no SPDX license on file, which this catalog treats as no clear license grant in the data stored here. Public code without a license is not free to use. License scores in this pair are 96 for deepseek-harness and 30 for WrenAI. This is a procurement signal, not legal advice.
Only deepseek-harness is marked self-hostable here (282,805 stars, deploy score 100). WrenAI is not (18,321 stars, deploy score 35). For a team with a data-residency rule, that gap can outweigh a star-count lead. Pricing labels on file: deepseek-harness is open source, WrenAI is unpriced in this catalog.
The lead is split. deepseek-harness is furthest ahead on license flexibility (96 to 30), while WrenAI is furthest ahead on recent activity (100 to 92). Choose the dimension a rollout cannot compromise on.
deepseek-harness finishes ahead at 97.4 against WrenAI at 73.6, a 23.8 point decisive 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 | deepseek-harness | WrenAI |
|---|---|---|
| GitHub stars | 282,805 | 18,321 |
| Forks | 35,041 | 2,115 |
| Open issues | 0 | 251 |
| Adoption | 100 | 78 |
| Activity | 92 | 100 |
| Community | 100 | 73 |
| Issue health | 96 | 84 |
| License | 96 | 30 |
| Self-hosting | 100 | 35 |
| Composite | 97.4 | 73.6 |
DeepSeek Harness: Everything is a Plugin.
GenBI (Generative BI) for AI agents, an open-source, governed text-to-SQL through an open context layer that turns natural-language questions into trusted dashboards, charts, and SQL across 20+ data sources, such as BigQuery, Snowflake, PostgreSQL, ClickHouse, Amazon Redshift, Databricks and more.
deepseek-harness has more GitHub stars: 282,805 versus 18,321 for WrenAI. The gap is 264,484 stars.
WrenAI was pushed more recently: 17 November 2026 versus 13 November 2026 for deepseek-harness. That is 4 days apart.
Only deepseek-harness is marked self-hostable. WrenAI is not.
deepseek-harness 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. WrenAI is listed as no SPDX license on file, which this catalog treats as no clear license grant in the data stored here. Public code without a license is not free to use. Read both grants before you embed either codebase in a hosted product. This is not legal advice.
deepseek-harness scores 97.4 and WrenAI scores 73.6. This page calls that a decisive lead for deepseek-harness.