openlumara

handwritten harness for AI, not vibecoded, everything is a module/plugin, tailor made for use with local models, tiny system prompt (around 1k by default), support for exclusive llamacpp features, strong security, strict zero-trust-in-the-ai policy (the code hard limits the ai, no amount of prompt engineering will bypass it)

Rose22/openlumara

View on GitHub ↗

handwritten harness for AI, not vibecoded, everything is a module/plugin, tailor made for use with local models, tiny system prompt (around 1k by default), support for exclusive llamacpp features, strong security, strict zero-trust-in-the-ai policy (the code hard limits the ai, no amount of prompt engineering will bypass it)

openlumara grew +6.3% in the last 30 days, ranks 909th of 2,590 in Agent SDK / Framework, actively maintained, last commit today.

Star trajectory

116 days tracked
2026-07-02523 stars today2026-10-26
Momentum

+6.3% in 30d, above the Agent SDK / Framework median of +1.5%.

Maintenance

Last commit today, fresher than the median of 14d.

How it compares in Agent SDK / Framework

openlumara
523
stars
+6.3% 30d
commit today
Agent SDK / Framework median
310
stars
+1.5% 30d
commit ~14d ago
Leader · rea
388.5k
stars
+93516.9% 30d
commit today

Ranked 909th of 2,590 by stars.

Language
Python
License
GNU General Public License v3.0
Contributors
11
Forks
61
Watchers
5
Open issues
21
Releases
0
Created
2026-02-27
Stars this week
+7

You've seen where openlumara stands today.

Get the moves before everyone else: the 5 Agent SDK / Framework repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain openlumara?

Claim this page to add your own call-to-action.

Claim this page