AlphaUncommon
alexisfox7/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)
- Owner
- alexisfox7 (personal account)
- Stars
- Stars: 465
- Forks
- Forks: 47
- Language
- Python
- License
- MIT
- Created
- 2026
- Topics
- agent-memoryarc-agillm-agentslong-horizon
- Tier
- Alpha (250 to 699 ★) What this tier means
Nearby in Python
All Python repos- llnl/OGhidraStars: 465PythonAlpha
- PleasePrompto/ductorStars: 465PythonAlpha
- iamzulx/crypto-ragStars: 465PythonAlpha
- saxix/django-concurrencyStars: 465PythonAlpha
- jamielennox/requests-mockStars: 465PythonAlpha
- python-xlib/python-xlibStars: 465PythonAlpha