A · leads
claude-mem
94.7
117,865 stars · Apache-2.0
AI Agents
claude-mem leads by 1.8 · narrow
A · leads
94.7
117,865 stars · Apache-2.0
B
92.9
264,096 stars · MIT
claude-mem versus hermes-agent is a AI Agents comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. claude-mem is written mainly in TypeScript; hermes-agent is written mainly in Python. The composite score is 94.7 for claude-mem and 92.9 for hermes-agent.
hermes-agent has 264,096 GitHub stars to claude-mem's 117,865, a gap of 146,231 (2.24×). Forks are 10,242 for claude-mem and 59,569 for hermes-agent. On the log scale used inside this pair, adoption is 94 versus 100, and the fork community is 84 versus 100.
Push history: claude-mem was last pushed on 17 November 2026 (0 days ago), and hermes-agent was last pushed on 17 November 2026 (0 days ago). Open issues stand at 159 for claude-mem (0.001 per star) and 53,403 for hermes-agent (0.202 per star). Issue-health scores are 96 and 34; activity scores are 100 and 100.
claude-mem 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. 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. License scores in this pair are 96 for claude-mem and 96 for hermes-agent. This is a procurement signal, not legal advice.
In AI Agents, both claude-mem (117,865 stars) and hermes-agent (264,096 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: claude-mem is open source, hermes-agent is open source.
The lead is split. claude-mem is furthest ahead on issue health (96 to 34), while hermes-agent is furthest ahead on fork community (100 to 84). Choose the dimension a rollout cannot compromise on.
claude-mem finishes ahead at 94.7 against hermes-agent at 92.9, a 1.8 point narrow 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 | claude-mem | hermes-agent |
|---|---|---|
| GitHub stars | 117,865 | 264,096 |
| Forks | 10,242 | 59,569 |
| Open issues | 159 | 53,403 |
| Adoption | 94 | 100 |
| Activity | 100 | 100 |
| Community | 84 | 100 |
| Issue health | 96 | 34 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 94.7 | 92.9 |
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
The agent that grows with you
hermes-agent has more GitHub stars: 264,096 versus 117,865 for claude-mem. The gap is 146,231 stars.
Both were last pushed on 17 November 2026.
Yes. This catalog marks both claude-mem and hermes-agent as self-hostable. Confirm each project's deploy docs before you plan a migration.
claude-mem 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. 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. Read both grants before you embed either codebase in a hosted product. This is not legal advice.
claude-mem scores 94.7 and hermes-agent scores 92.9. This page calls that a narrow lead for claude-mem.