A · leads
deepseek-harness
97.4
282,805 stars · MIT
AI Agents
deepseek-harness leads by 13.1 · clear
A · leads
97.4
282,805 stars · MIT
B
84.3
25,471 stars · Apache-2.0
deepseek-harness versus letta is a AI Agents comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. deepseek-harness is written mainly in TypeScript; letta is written mainly in an unspecified language. The composite score is 97.4 for deepseek-harness and 84.3 for letta.
deepseek-harness has 282,805 GitHub stars to letta's 25,471, a gap of 257,334 (11.10×). Forks are 35,041 for deepseek-harness and 2,677 for letta. On the log scale used inside this pair, adoption is 100 versus 81, and the fork community is 100 versus 75.
Push history: deepseek-harness was last pushed on 13 November 2026 (4 days ago), and letta was last pushed on 18 October 2026 (29 days ago). Open issues stand at 0 for deepseek-harness (0.000 per star) and 0 for letta (0.000 per star). Issue-health scores are 96 and 96; activity scores are 92 and 78.
deepseek-harness 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. letta is listed as Apache-2.0, 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 96 for deepseek-harness and 96 for letta. This is a procurement signal, not legal advice.
In AI Agents, both deepseek-harness (282,805 stars) and letta (25,471 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: deepseek-harness is open source, letta is open source.
deepseek-harness is ahead on every scored dimension that is not level. Level dimensions: issue health, license flexibility, self-hosting. The widest gap is fork community at 25 points (100 vs 75), and the tightest is self-hosting at 0 points (100 vs 100).
deepseek-harness finishes ahead at 97.4 against letta at 84.3, a 13.1 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 | deepseek-harness | letta |
|---|---|---|
| GitHub stars | 282,805 | 25,471 |
| Forks | 35,041 | 2,677 |
| Open issues | 0 | 0 |
| Adoption | 100 | 81 |
| Activity | 92 | 78 |
| Community | 100 | 75 |
| Issue health | 96 | 96 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 97.4 | 84.3 |
DeepSeek Harness: Everything is a Plugin.
Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.
deepseek-harness has more GitHub stars: 282,805 versus 25,471 for letta. The gap is 257,334 stars.
deepseek-harness was pushed more recently: 13 November 2026 versus 18 October 2026 for letta. That is 25 days apart.
Yes. This catalog marks both deepseek-harness and letta as self-hostable. Confirm each project's deploy docs before you plan a migration.
deepseek-harness 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. letta is listed as Apache-2.0, 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.
deepseek-harness scores 97.4 and letta scores 84.3. This page calls that a clear lead for deepseek-harness.