A · leads
mem0
96.2
69,113 stars · Apache-2.0
AI Agents
mem0 leads by 1.5 · narrow
A · leads
96.2
69,113 stars · Apache-2.0
B
94.7
127,431 stars · MIT
mem0 versus orca is a AI Agents comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. mem0 is written mainly in Python; orca is written mainly in TypeScript. The composite score is 96.2 for mem0 and 94.7 for orca.
orca has 127,431 GitHub stars to mem0's 69,113, a gap of 58,318 (1.84×). Forks are 8,226 for mem0 and 8,082 for orca. On the log scale used inside this pair, adoption is 95 versus 100, and the fork community is 100 versus 100.
Push history: mem0 was last pushed on 17 November 2026 (0 days ago), and orca was last pushed on 17 November 2026 (0 days ago). Open issues stand at 963 for mem0 (0.014 per star) and 8,552 for orca (0.067 per star). Issue-health scores are 84 and 52; activity scores are 100 and 100.
mem0 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. orca 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 mem0 and 96 for orca. This is a procurement signal, not legal advice.
In AI Agents, both mem0 (69,113 stars) and orca (127,431 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: mem0 is open source, orca is open source.
The lead is split. mem0 is furthest ahead on issue health (84 to 52), while orca is furthest ahead on adoption (100 to 95). Choose the dimension a rollout cannot compromise on.
mem0 finishes ahead at 96.2 against orca at 94.7, a 1.5 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 | mem0 | orca |
|---|---|---|
| GitHub stars | 69,113 | 127,431 |
| Forks | 8,226 | 8,082 |
| Open issues | 963 | 8,552 |
| Adoption | 95 | 100 |
| Activity | 100 | 100 |
| Community | 100 | 100 |
| Issue health | 84 | 52 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 96.2 | 94.7 |
The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
Orca lets you run a fleet of coding agents (e.g. Claude Code, Codex) with your own subscription. Available on desktop, mobile and remote runtime.
orca has more GitHub stars: 127,431 versus 69,113 for mem0. The gap is 58,318 stars.
Both were last pushed on 17 November 2026.
Yes. This catalog marks both mem0 and orca as self-hostable. Confirm each project's deploy docs before you plan a migration.
mem0 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. orca 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.
mem0 scores 96.2 and orca scores 94.7. This page calls that a narrow lead for mem0.