A · level
deer-flow
97.0
85,441 stars · MIT
AI Agents
Too close to call · 97.0 to 96.7
A · level
97.0
85,441 stars · MIT
B · level
96.7
117,459 stars · MIT
deer-flow versus taste-skill is a AI Agents comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. deer-flow is written mainly in Python; taste-skill is written mainly in JavaScript. The composite score is 97.0 for deer-flow and 96.7 for taste-skill.
taste-skill has 117,459 GitHub stars to deer-flow's 85,441, a gap of 32,018 (1.37×). Forks are 12,046 for deer-flow and 7,858 for taste-skill. On the log scale used inside this pair, adoption is 97 versus 100, and the fork community is 100 versus 96.
Push history: deer-flow was last pushed on 17 November 2026 (0 days ago), and taste-skill was last pushed on 08 November 2026 (8 days ago). Open issues stand at 1,117 for deer-flow (0.013 per star) and 10 for taste-skill (0.000 per star). Issue-health scores are 84 and 96; activity scores are 100 and 92.
Both deer-flow and taste-skill are listed as MIT. 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 deer-flow (85,441 stars) and taste-skill (117,459 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: deer-flow is open source, taste-skill is open source.
The lead is split. deer-flow is furthest ahead on recent activity (100 to 92), while taste-skill is furthest ahead on issue health (96 to 84). Choose the dimension a rollout cannot compromise on.
Composite score: deer-flow 97.0, taste-skill 96.7. 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 | deer-flow | taste-skill |
|---|---|---|
| GitHub stars | 85,441 | 117,459 |
| Forks | 12,046 | 7,858 |
| Open issues | 1,117 | 10 |
| Adoption | 97 | 100 |
| Activity | 100 | 92 |
| Community | 100 | 96 |
| Issue health | 84 | 96 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 97.0 | 96.7 |
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
taste-skill has more GitHub stars: 117,459 versus 85,441 for deer-flow. The gap is 32,018 stars.
deer-flow was pushed more recently: 17 November 2026 versus 08 November 2026 for taste-skill. That is 8 days apart.
Yes. This catalog marks both deer-flow and taste-skill as self-hostable. Confirm each project's deploy docs before you plan a migration.
deer-flow 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. taste-skill 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. Read both grants before you embed either codebase in a hosted product. This is not legal advice.
Neither tool clears a one-point margin. deer-flow scores 97.0 and taste-skill scores 96.7.