A · leads
hermes-agent
92.9
264,096 stars · MIT
AI Agents
hermes-agent leads by 8.9 · clear
A · leads
92.9
264,096 stars · MIT
B
84.0
25,471 stars · Apache-2.0
hermes-agent versus letta is a AI Agents comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. hermes-agent is written mainly in Python; letta is written mainly in an unspecified language. The composite score is 92.9 for hermes-agent and 84.0 for letta.
hermes-agent has 264,096 GitHub stars to letta's 25,471, a gap of 238,625 (10.37×). Forks are 59,569 for hermes-agent 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 72.
Push history: hermes-agent was last pushed on 17 November 2026 (0 days ago), and letta was last pushed on 18 October 2026 (29 days ago). Open issues stand at 53,403 for hermes-agent (0.202 per star) and 0 for letta (0.000 per star). Issue-health scores are 34 and 96; activity scores are 100 and 78.
hermes-agent 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 hermes-agent and 96 for letta. This is a procurement signal, not legal advice.
In AI Agents, both hermes-agent (264,096 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: hermes-agent is open source, letta is open source.
The lead is split. hermes-agent is furthest ahead on fork community (100 to 72), while letta is furthest ahead on issue health (96 to 34). Choose the dimension a rollout cannot compromise on.
hermes-agent finishes ahead at 92.9 against letta at 84.0, a 8.9 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 | hermes-agent | letta |
|---|---|---|
| GitHub stars | 264,096 | 25,471 |
| Forks | 59,569 | 2,677 |
| Open issues | 53,403 | 0 |
| Adoption | 100 | 81 |
| Activity | 100 | 78 |
| Community | 100 | 72 |
| Issue health | 34 | 96 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 92.9 | 84.0 |
The agent that grows with you
Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.
hermes-agent has more GitHub stars: 264,096 versus 25,471 for letta. The gap is 238,625 stars.
hermes-agent was pushed more recently: 17 November 2026 versus 18 October 2026 for letta. That is 29 days apart.
Yes. This catalog marks both hermes-agent and letta as self-hostable. Confirm each project's deploy docs before you plan a migration.
hermes-agent 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.
hermes-agent scores 92.9 and letta scores 84.0. This page calls that a clear lead for hermes-agent.