A · leads
ECC
99.1
305,069 stars · MIT
AI Agents
ECC leads by 10.3 · clear
A · leads
99.1
305,069 stars · MIT
B
88.8
25,274 stars · MIT
ECC versus learn-harness-engineering is a AI Agents comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. ECC is written mainly in JavaScript; learn-harness-engineering is written mainly in TypeScript. The composite score is 99.1 for ECC and 88.8 for learn-harness-engineering.
ECC has 305,069 GitHub stars to learn-harness-engineering's 25,274, a gap of 279,795 (12.07×). Forks are 44,923 for ECC and 2,902 for learn-harness-engineering. On the log scale used inside this pair, adoption is 100 versus 80, and the fork community is 100 versus 74.
Push history: ECC was last pushed on 17 November 2026 (0 days ago), and learn-harness-engineering was last pushed on 15 November 2026 (2 days ago). Open issues stand at 149 for ECC (0.000 per star) and 25 for learn-harness-engineering (0.001 per star). Issue-health scores are 96 and 96; activity scores are 100 and 100.
Both ECC and learn-harness-engineering 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 ECC (305,069 stars) and learn-harness-engineering (25,274 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: ECC is open source, learn-harness-engineering is open source.
ECC is ahead on every scored dimension that is not level. Level dimensions: recent activity, issue health, license flexibility, self-hosting. The widest gap is fork community at 26 points (100 vs 74), and the tightest is self-hosting at 0 points (100 vs 100).
ECC finishes ahead at 99.1 against learn-harness-engineering at 88.8, a 10.3 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 | ECC | learn-harness-engineering |
|---|---|---|
| GitHub stars | 305,069 | 25,274 |
| Forks | 44,923 | 2,902 |
| Open issues | 149 | 25 |
| Adoption | 100 | 80 |
| Activity | 100 | 100 |
| Community | 100 | 74 |
| Issue health | 96 | 96 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 99.1 | 88.8 |
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Harness engineering beginner tutorial, from 0 to 1
ECC has more GitHub stars: 305,069 versus 25,274 for learn-harness-engineering. The gap is 279,795 stars.
ECC was pushed more recently: 17 November 2026 versus 15 November 2026 for learn-harness-engineering. That is 2 days apart.
Yes. This catalog marks both ECC and learn-harness-engineering as self-hostable. Confirm each project's deploy docs before you plan a migration.
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. learn-harness-engineering 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 learn-harness-engineering scores 88.8. This page calls that a clear lead for ECC.