Python · MIT
OnePunchMonk/AgentQuant
A failure-aware harness for reproducible quantitative-strategy research, with typed agent workflows and inspectable experiment memory.
★ 220
Stars
46 forks · 21 open issues
+2.0/wk
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
30.2
Momentum / 100
see the breakdown below
15mo ago
Created
last push 4d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 2.1 | +2.0/wk, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 6.4 | last week ran 1.43× the monthly pace |
| Freshness | 15 | 14.8 | last push 4d ago; decays to zero at 180 days |
| Scale | 15 | 6.8 | 220 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 30.2 | sum of the above |
Detail
| Topics | agentic-aiautonomous-agentfinance-aifintechharness-engineeringlangchainlanggraphllm-agentsportfolio-optimizationquant-agentquantitative-financequantitative-researchreact-agentself-evolving-agentsself-improving-aistock-aivectorbtyfinance |
| Matched on | Finance (fintech) |
| Short window | +2 stars over 7 days = 0.3/day |
| Long window | +3 stars over 15 days = 0.2/day |
| Lifetime average | 0.49 stars/day over 450 days |
| First seen here | 2026-10-21 |
| Last read | 2d ago |