PRO-LONG
Programmatic memory for long-horizon LLM agents: the harness appends everything to one log, and the agent searches it with code. 97.4% on ARC-AGI-3 (arXiv:2607.20064)
alexisfox7/PRO-LONG
View on GitHub ↗Programmatic memory for long-horizon LLM agents: the harness appends everything to one log, and the agent searches it with code. 97.4% on ARC-AGI-3 (arXiv:2607.20064)
PRO-LONG grew +0.2% in the last 30 days, ranks 701st of 1,530 in Memory & Knowledge (RAG), last commit 63 days ago.
Star trajectory
89 days tracked+0.2% in 30d, below the Memory & Knowledge (RAG) median of +1.0%.
Last commit 63 days ago, staler than the median of 16.5d.
How it compares in Memory & Knowledge (RAG)
Ranked 701st of 1,530 by stars.
- Language
- Python
- License
- MIT License
- Contributors
- 2
- Forks
- 47
- Watchers
- 6
- Open issues
- 0
- Releases
- 0
- Created
- 2026-03-07
- Stars this week
- +0
You've seen where PRO-LONG stands today.
Get the moves before everyone else: the 5 Memory & Knowledge (RAG) repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.