A
corsair
70.0
15,648 stars · license n/a
AI Agents
ECC leads by 29.1 · decisive
A
70.0
15,648 stars · license n/a
B · leads
99.1
305,069 stars · MIT
corsair versus ECC is a AI Agents comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. corsair is written mainly in TypeScript; ECC is written mainly in JavaScript. The composite score is 70.0 for corsair and 99.1 for ECC.
ECC has 305,069 GitHub stars to corsair's 15,648, a gap of 289,421 (19.50×). Forks are 724 for corsair and 44,923 for ECC. On the log scale used inside this pair, adoption is 76 versus 100, and the fork community is 62 versus 100.
Push history: corsair was last pushed on 17 November 2026 (0 days ago), and ECC was last pushed on 17 November 2026 (0 days ago). Open issues stand at 320 for corsair (0.020 per star) and 149 for ECC (0.000 per star). Issue-health scores are 70 and 96; activity scores are 100 and 100.
corsair 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. ECC 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. License scores in this pair are 30 for corsair and 96 for ECC. This is a procurement signal, not legal advice.
Only ECC is marked self-hostable here (305,069 stars, deploy score 100). corsair is not (15,648 stars, deploy score 35). For a team with a data-residency rule, that gap can outweigh a star-count lead. Pricing labels on file: corsair is unpriced in this catalog, ECC is open source.
ECC is ahead on every scored dimension that is not level. Level dimensions: recent activity. The widest gap is license flexibility at 66 points (30 vs 96), and the tightest is recent activity at 0 points (100 vs 100).
ECC finishes ahead at 99.1 against corsair at 70.0, a 29.1 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 | corsair | ECC |
|---|---|---|
| GitHub stars | 15,648 | 305,069 |
| Forks | 724 | 44,923 |
| Open issues | 320 | 149 |
| Adoption | 76 | 100 |
| Activity | 100 | 100 |
| Community | 62 | 100 |
| Issue health | 70 | 96 |
| License | 30 | 96 |
| Self-hosting | 35 | 100 |
| Composite | 70.0 | 99.1 |
Connect your users to their apps
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
ECC has more GitHub stars: 305,069 versus 15,648 for corsair. The gap is 289,421 stars.
Both were last pushed on 17 November 2026.
Only ECC is marked self-hostable. corsair is not.
corsair 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. ECC 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.
ECC scores 99.1 and corsair scores 70.0. This page calls that a decisive lead for ECC.