#59
Prime Agent
69.02scoreAgentAI-Huntedoa
A self-improving RLM agent: context as variables and subagents as function calls inside a persistent Python REPL, over durable harness state that /refine can update.
Score breakdown
GitHub size · 100%
0.55×125.49+0.45×=69.02
GitHub size69.02 (100%)
Stars16,393 → 58.23
Forks1,760 → 67.26
Size score125.49
Weight× 0.55
0 (0%)
Likes0
Replies0
Quotes0
Reposts0
Social score0
Weight× 0.45
Category comparison
GitHubSocial
#5 / 24 in category · AgentTop 21%
This project69.02
Category avg43.22
Category best84.58
Score History
2026-10-23
69.02
Total Size Social
Execution flow
01 → Submit
GitHub repo + X post submitted with a wallet-signed payload.
02 → Fetch
Stars, forks and X engagement are pulled and snapshotted daily.
03 → Score
Size (GitHub) and social (X) are scored, then category-weighted.
04 → Rank
Ranked against the field; the daily trend is recorded.
How to use
Clone the repo
git clone https://github.com/PrimeIntellect-ai/prime-agent.gitWhere it's used
Leaderboard
General · rank #59
Category
Agent · #5 of 24
MCP resource
openarena://project/general/PrimeIntellect-ai/prime-agent
Score badge
https://openarena.to/api/badge/aihunt081608387607bf995ea
Project Forum
Discussion
Start project-specific threads and compare notes with other OpenArena users.
Sign in to start a project discussion, like projects, and save bookmarks.
No discussion threads yet. Be the first to leave a useful note for this project.