A · leads
orca
94.6
127,431 stars · MIT
AI Agents
orca leads by 10.9 · clear
A · leads
94.6
127,431 stars · MIT
B
83.7
80,149 stars · MIT
orca versus Prompt-Engineering-Guide is a AI Agents comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. orca is written mainly in TypeScript; Prompt-Engineering-Guide is written mainly in MDX. The composite score is 94.6 for orca and 83.7 for Prompt-Engineering-Guide.
orca has 127,431 GitHub stars to Prompt-Engineering-Guide's 80,149, a gap of 47,282 (1.59×). Forks are 8,082 for orca and 8,790 for Prompt-Engineering-Guide. On the log scale used inside this pair, adoption is 100 versus 96, and the fork community is 99 versus 100.
Push history: orca was last pushed on 17 November 2026 (0 days ago), and Prompt-Engineering-Guide was last pushed on 11 March 2026 (250 days ago). Open issues stand at 8,552 for orca (0.067 per star) and 300 for Prompt-Engineering-Guide (0.004 per star). Issue-health scores are 52 and 96; activity scores are 100 and 36.
Both orca and Prompt-Engineering-Guide 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 orca (127,431 stars) and Prompt-Engineering-Guide (80,149 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: orca is open source, Prompt-Engineering-Guide is open source.
The lead is split. orca is furthest ahead on recent activity (100 to 36), while Prompt-Engineering-Guide is furthest ahead on issue health (96 to 52). Choose the dimension a rollout cannot compromise on.
orca finishes ahead at 94.6 against Prompt-Engineering-Guide at 83.7, a 10.9 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 | orca | Prompt-Engineering-Guide |
|---|---|---|
| GitHub stars | 127,431 | 80,149 |
| Forks | 8,082 | 8,790 |
| Open issues | 8,552 | 300 |
| Adoption | 100 | 96 |
| Activity | 100 | 36 |
| Community | 99 | 100 |
| Issue health | 52 | 96 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 94.6 | 83.7 |
Orca lets you run a fleet of coding agents (e.g. Claude Code, Codex) with your own subscription. Available on desktop, mobile and remote runtime.
🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
orca has more GitHub stars: 127,431 versus 80,149 for Prompt-Engineering-Guide. The gap is 47,282 stars.
orca was pushed more recently: 17 November 2026 versus 11 March 2026 for Prompt-Engineering-Guide. That is 250 days apart.
Yes. This catalog marks both orca and Prompt-Engineering-Guide as self-hostable. Confirm each project's deploy docs before you plan a migration.
orca 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. Prompt-Engineering-Guide 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.
orca scores 94.6 and Prompt-Engineering-Guide scores 83.7. This page calls that a clear lead for orca.