A
cangjie-skill
83.8
12,943 stars · MIT
Workflow Automation
Huginn leads by 12.4 · clear
A
83.8
12,943 stars · MIT
B · leads
96.2
50,561 stars · MIT
cangjie-skill versus Huginn is a Workflow Automation comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. cangjie-skill is written mainly in Python; Huginn is written mainly in Ruby. The composite score is 83.8 for cangjie-skill and 96.2 for Huginn.
Huginn has 50,561 GitHub stars to cangjie-skill's 12,943, a gap of 37,618 (3.91×). Forks are 1,533 for cangjie-skill and 4,356 for Huginn. On the log scale used inside this pair, adoption is 87 versus 100, and the fork community is 88 versus 100.
Push history: cangjie-skill was last pushed on 02 October 2026 (46 days ago), and Huginn was last pushed on 09 November 2026 (8 days ago). Open issues stand at 21 for cangjie-skill (0.002 per star) and 692 for Huginn (0.014 per star). Issue-health scores are 96 and 84; activity scores are 58 and 92.
Both cangjie-skill and Huginn 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 Workflow Automation, both cangjie-skill (12,943 stars) and Huginn (50,561 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: cangjie-skill is open source, Huginn is open source.
The lead is split. cangjie-skill is furthest ahead on issue health (96 to 84), while Huginn is furthest ahead on recent activity (92 to 58). Choose the dimension a rollout cannot compromise on.
Huginn finishes ahead at 96.2 against cangjie-skill at 83.8, a 12.4 point clear 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 | cangjie-skill | Huginn |
|---|---|---|
| GitHub stars | 12,943 | 50,561 |
| Forks | 1,533 | 4,356 |
| Open issues | 21 | 692 |
| Adoption | 87 | 100 |
| Activity | 58 | 92 |
| Community | 88 | 100 |
| Issue health | 96 | 84 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 83.8 | 96.2 |
把书、长视频、播客等高价值内容蒸馏成可执行的 Agent Skills(Distill high-value content from books, long-form videos, podcasts, and more into executable Agent Skills)
Huginn is a self-hosted agent system that watches the web and triggers actions from events. It predates the current wave of LLM agents and is closer to a personal IFTTT you run yourself.
Huginn has more GitHub stars: 50,561 versus 12,943 for cangjie-skill. The gap is 37,618 stars.
Huginn was pushed more recently: 09 November 2026 versus 02 October 2026 for cangjie-skill. That is 38 days apart.
Yes. This catalog marks both cangjie-skill and Huginn as self-hostable. Confirm each project's deploy docs before you plan a migration.
cangjie-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. Huginn 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.
Huginn scores 96.2 and cangjie-skill scores 83.8. This page calls that a clear lead for Huginn.