1.Danielxu0208 / rsi_eval
A lightweight Python SDK and CLI for evaluating recursive self-improvement (RSI) methods across agent benchmarks.
- ai-agents
- benchmarking
- llm-evaluation
- python
- recursive-self-improvement
- rsi
+168 stars
from 191 · score 5.13
Trending repositories
Ranked by Attention Score: stars gained over the last 7 complete days
14 repositories by Attention Score · Oct 28, 2026 – Nov 3, 2026 (UTC)
2.arjaythedev / twelve-dollar-server-challenge
Implement one small API on SQLite in any language; we benchmark it on a $12 server (1 vCPU, 2 GB)
+139 stars
from 499 · score 4.94
3.lingquan11 / cpp-matmul-performance
C++ 矩阵乘法性能实验：从三重循环到分块优化与脉动阵列 —— AI 芯片（NPU）方向本科入门成果展示项目
+123 stars
from 1 · score 4.82
+55 stars
from 109 · score 4.03
+44 stars
from 29,160 · score 3.81
+15 stars
from 10,485 · score 2.77
7.GoogleChrome / lighthouse-ci
Automate running Lighthouse for every commit, viewing the changes, and preventing regressions
- lighthouse
- webperf
+12 stars
from 7,117 · score 2.56
+8 stars
from 6,411 · score 2.20
9.nicorobinreal / llmspeed
Feel how fast a local LLM runs before you buy the hardware
+7 stars
from 161 · score 2.08
10.dotnet / BenchmarkDotNet
Powerful .NET library for benchmarking
- benchmark
- benchmarking
- c-sharp
- dotnet
- performance
- csharp
- +1 more
+6 stars
from 11,521 · score 1.95
11.ai / size-limit
Calculate the real cost to run your JS app or lib to keep good performance. Show error in pull request if the cost exceeds the limit.
+4 stars
from 7,039 · score 1.61
12.gilnett / learned_index_lab
High-performance Piecewise Geometric Model (PGM) learned index implementation in pure Rust with strict epsilon error guarantees
+4 stars
from 162 · score 1.61
13.akopytov / sysbench
Scriptable database and system performance benchmark
- benchmark
- mysql
- postgresql
- lua
- luajit
- console
- +6 more
+1 stars
from 6,813 · score 0.69
+1 stars
from 5,238 · score 0.69