Github Trends®
893 findingsmedian surprise 0.00048window 180 days
UNIT / TREND-MONITOR · REV 2.6
[ 180 days window ]
SOURCE: gharchive
Star-event source (GH Archive) degraded in Feb 2026 — this window still runs on it while data migrates to our own daily snapshots. Rankings may undercount.
EXPORT · CSV ↧
REPOSITORY / FINDING
LANG
SURPRISE SCORE
TREND
S · E · D · F
01
sanhaji182/gateway_realtime[BOT]
[ TYPESCRIPT ]
<0.000001
448
02
openai/math[BOT]
[ LEAN ]
<0.000001
15,132
03
sitimas9/ghsibudi
utility scripts
[ PYTHON ]
<0.000001
448
04
anthropics/fermats-last-theorem[BOT]
[ LEAN ]
<0.000001
1,282
05
repowahyuillahi/clock-update-windows-startup
Utility Windows untuk memperbaiki dan menyinkronkan jam otomatis saat PC menyala. Dibuat untuk memudahkan para IT support solo player di luar sana, supaya tidak selalu diganggu di pagi hari hanya karena jam PC user melenceng.
[ C# ]
<0.000001
449
06
deepseek-ai/awesome-deepseek-agent[BOT]
[ — ]
<0.000001
6,236
07
anthropics/financial-services[BOT]
[ PYTHON ]
<0.000001
40,226
08
microsoft/CUAWright
A simple SWE-style browser+desktop agent framework that achieves SOTA results on long-horizon CUA tasks
[ PYTHON ]
<0.000001
6,064
09
microsoft/playwright-cli
CLI for common Playwright actions. Record and generate Playwright code, inspect selectors and take screenshots.
[ JAVASCRIPT ]
<0.000001
14,320
10
microsoft/AI-Engineering-Coach
better agentic engineering
[ TYPESCRIPT ]
<0.000001
4,340
11
microsoft/TRELLIS.2
Native and Compact Structured Latents for 3D Generation
[ PYTHON ]
<0.000001
12,133
12
unicitynetwork/whitepaper[BOT]
[ TEX ]
<0.000001
20,097
13
google/eng-practices
Google's Engineering Practices documentation
[ — ]
<0.000001
23,285
14
microsoft/ML-For-Beginners
12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all
[ JUPYTER NOTEBOOK ]
<0.000001
91,570
15
microsoft/AI-For-Beginners
12 Weeks, 24 Lessons, AI for All!
[ JUPYTER NOTEBOOK ]
<0.000001
69,936
16
cursor/cookbook[BOT]
[ TYPESCRIPT ]
<0.000001
4,125
17
microsoft/qlib
Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, including supervised learning, market dynamics modeling, and RL, and is now equipped with https://github.com/microsoft/RD-Agent to automate R&D process.
[ PYTHON ]
<0.000001
49,467
18
ultraworkers/claw-code⚠[BOT]
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
[ RUST ]
<0.000001
194,916
19
microsoft/playwright-mcp
Playwright MCP server
[ TYPESCRIPT ]
<0.000001
38,314
20
microsoft/SkillOpt
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
[ PYTHON ]
<0.000001
18,519
21
microsoft/generative-ai-for-beginners
21 Lessons, Get Started Building with Generative AI
[ JUPYTER NOTEBOOK ]
<0.000001
121,554
22
openai/plugins
OpenAI Plugins
[ JAVASCRIPT ]
<0.000001
7,483
23
google/agents-cli
The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud.
[ PYTHON ]
0.00000101
6,099
24
google/ax
Google's open agentic orchestration runtime
[ GO ]
0.00000105
13,917
25
anthropics/defending-code-reference-harness
Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize
[ PYTHON ]
0.00000109
7,599
26
openai/whisper
Robust Speech Recognition via Large-Scale Weak Supervision
[ PYTHON ]
0.00000118
110,791
27
microsoft/playwright
Playwright is a framework for Web Testing and Automation. It allows testing Chromium, Firefox and WebKit with a single API.
[ TYPESCRIPT ]
0.00000122
97,970
28
microsoft/VibeVoice
Open-Source Frontier Voice AI
[ PYTHON ]
0.00000132
54,861
29
anthropics/commerce-agents
Reference blueprint for building shopping and merchant agents with Claude. Examples in retail, commerce, telecom, and entertainment included.
[ PYTHON ]
0.00000134
3,265
30
openai/skills
Skills Catalog for Codex
[ PYTHON ]
0.00000148
28,138
31
facebookresearch/vggt-omega
[CVPR 2026 Oral] VGGT Omega
[ PYTHON ]
0.00000149
4,663
32
microsoft/PowerToys
Microsoft PowerToys is a collection of utilities that supercharge productivity and customization on Windows
[ C ]
0.00000151
139,444
33
umarhadi/fly-hermes[BOT]
[ PYTHON ]
0.00000157
449
34
openai/codex-plugin-cc⚠
Use Codex from Claude Code to review code or delegate tasks.
[ JAVASCRIPT ]
0.00000168
34,350
35
vuejs/vue
This is the repo for Vue 2. For Vue 3, go to https://github.com/vuejs/core
[ TYPESCRIPT ]
0.00000177
212,622
36
img2threejs/img2threejsC⚠[BOT]
Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.
[ PYTHON ]
0.00000191
18,331
37
microsoft/ai-agents-for-beginners
18 Lessons to Get Started Building AI Agents
[ JUPYTER NOTEBOOK ]
0.00000221
77,383
38
pathwaycom/arc-task-gen
Generates original ARC-AGI-1-style tasks distribution-matched to the public eval set.
[ PYTHON ]
0.00000234
11,006
39
anthropics/claude-cookbooks
A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.
[ JUPYTER NOTEBOOK ]
0.00000234
53,539
40
openai/symphony
Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.
[ ELIXIR ]
0.00000236
27,727
41
capncodes69/myfreebuff[BOT]
[ POWERSHELL ]
0.0000027
458
42
genlayerlabs/genlayer-project-boilerplate[BOT]
[ TYPESCRIPT ]
0.00000277
18,817
43
anthropics/claude-for-legal
A suite of plugins for legal workflows
[ PYTHON ]
0.00000292
9,725
44
microsoft/vscode
Visual Studio Code
[ TYPESCRIPT ]
0.00000295
193,798
45
google/artemis
ARTEMIS turns natural-language instructions into reliable Android automation. It automates end-to-end workflows, captures logs, and integrates seamlessly with AI coding assistants such as Antigravity, Codex, and Claude Code. It also achieves 99%+ success rate on AndroidWorld Benchmark.
[ PYTHON ]
0.000003
12,229
46
openai/openai-agents-python
A lightweight, powerful framework for multi-agent workflows
[ PYTHON ]
0.00000308
30,110
47
NVIDIA/Personal-AI-Router
Router that virtually distributes inference across connected devices in the home.
[ GO ]
0.0000031
1,633
48
Tencent/BrowserSkill
Let AI agents use your real, logged-in browser without interrupting your work. CLI + extension for browser automation across any shell-capable AI agent.
[ TYPESCRIPT ]
0.00000327
9,137
49
browser-act/skills[BOT]
Browser automation CLI built for AI agents. Break through anti-bot walls, hand off to humans across platforms when stuck. Parallel multi-task execution, independent multi-session operation, isolated multi-account browsing.
[ PYTHON ]
0.00000353
6,157
50
NVIDIA/cuda-rust
NVIDIA's CUDA platform for Rust. Host runtime crates plus Tile (cutile-rs) and SIMT (cuda-oxide) kernel programming models in idiomatic Rust.
[ RUST ]
0.00000391
3,733
SHOWING 50 OF 893 (TOTAL 893) · CLICK ANY ROW ▸ · PAGE 1/18