Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats
Busbar
Busbar
Bifrost
Bifrost
ClawBench
ClawBench

bandr-ai/bandits

Trace mining for post-training. Filter trajectories, draft verifiers, export SFT and RL data.

Visit GitHub
Python
136
8
2 contributors
website
FeaturedAdvertise to 180K+ monthly visitors
Busbar

Control what AI can do before it acts

Bifrost

Enterprise AI Gateway Built For Scale: Route, Govern, and Secure All Your AI Traffic

ClawBench

a benchmark for personal agents

Momentum

How fast bandr-ai/bandits is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Sep 5 – Oct 22, 2026

Stars +115 in 48 days

0204060
58

Forks +8 in 48 days

0246
5

Merged PRs 65 in 48 days

051015
13

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Sep 5Sep 11Sep 17Sep 23Sep 29Oct 5Oct 11Oct 17
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRs
Sat, Sep 5, 2026+0+01
Sun, Sep 6, 2026+0+08
Mon, Sep 7, 2026+0+07
Tue, Sep 8, 2026+0+03
Wed, Sep 9, 2026+0+00
Thu, Sep 10, 2026+0+00
Fri, Sep 11, 2026+0+02
Sat, Sep 12, 2026+0+00
Sun, Sep 13, 2026+0+01
Mon, Sep 14, 2026+0+01
Tue, Sep 15, 2026+0+00
Wed, Sep 16, 2026+0+00
Thu, Sep 17, 2026+0+02
Fri, Sep 18, 2026+0+00
Sat, Sep 19, 2026+0+00
Sun, Sep 20, 2026+0+00
Mon, Sep 21, 2026+0+01
Tue, Sep 22, 2026+0+00
Wed, Sep 23, 2026+0+01
Thu, Sep 24, 2026+0+01
Fri, Sep 25, 2026+0+013
Sat, Sep 26, 2026+0+02
Sun, Sep 27, 2026+0+00
Mon, Sep 28, 2026+0+06
Tue, Sep 29, 2026+0+04
Wed, Sep 30, 2026+19+02
Thu, Oct 1, 2026+58+50
Fri, Oct 2, 2026+11+00
Sat, Oct 3, 2026+0+00
Sun, Oct 4, 2026+1+04
Mon, Oct 5, 2026+1+00
Tue, Oct 6, 2026+0+00
Wed, Oct 7, 2026+0+00
Thu, Oct 8, 2026+6+11
Fri, Oct 9, 2026+8+00
Sat, Oct 10, 2026+3+00
Sun, Oct 11, 2026+0+00
Mon, Oct 12, 2026+0+10
Tue, Oct 13, 2026+0+00
Wed, Oct 14, 2026+0+01
Thu, Oct 15, 2026+4+01
Fri, Oct 16, 2026+1+00
Sat, Oct 17, 2026+1+12
Sun, Oct 18, 2026+1+01
Mon, Oct 19, 2026+1+00
Tue, Oct 20, 2026+0+00
Wed, Oct 21, 2026+0+00
Thu, Oct 22, 2026+0+00
Total+115+865
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Social mentions

Recent discussions about this repository across the web
  1. Oct 81 post

    • The trick: we trained our own Jevs on the agent’s own traces step Jev: grades every search the agent makes final Jev: reads the whole trace and predicts if the answer is right (AUC 0.92) We also…

      Read full on X, posted by @llmluthor

      @llmluthor · x.com

  2. 8 days earlier
  3. Sep 301 post

    • It wins across every domain we tested web research: 77.5% customer service: 80.3% function calling: 81.3% multi-hop QA: 72.4% Jev was behind in every single one

      Read full on X, posted by @llmluthor

      @llmluthor · x.com

You might also like

Repositories close to bandr-ai/bandits
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Enterprise AI Gateway Built For Scale: Route, Govern, and Secure All Your AI Traffic

Busbar

Control what AI can do before it acts

ClawBench

a benchmark for personal agents

TeichAI/teich

Python

Generate, format and mask agent traces with ease.

14819

google-deepmind/envlogger

Python

A tool for recording RL trajectories.

13621

jinzijian/EvoTrace

Python

Compile real-world Claude Code and Codex trajectories into verified, tradable post-training assets.

28129

combined-ai/isplay

TypeScript

Understand your agent's decisions

156

JudgmentLabs/judgeval

Python

The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.

1.1k106

Continuum-AI-Corp/OrcaReplay

TypeScript

OrcaReplay — Time travel for AI agents. Record, replay, fork, and debug any agent run with any model. Built by the OrcaRouter.ai team.

28174

browser-use/rl-env-use

HTML

Build RL environments for any domain from real cases that Browser Use agents mine from the web

1457

kargarisaac/lerim

Python

Compiles AI agent traces and truns them into reusable context.

1007

traceroot-ai/traceroot

TypeScript

TraceRoot - Open Source AI Agent Improvement Platform YC S25

873308