trendrepo.dev

Repositories taking off

Filters
?
Stars gained
New stars in the window. "all" means the repo is younger than the window, so the number is every star it has.
Today
Stars since midnight US Pacific time, so a partial day.
Above pace
How many more stars the repo got than its pace in the window before would predict. +500 means 500 more than usual.
Momentum
A daily score modeled on trendshift.io: 8 points per star and 2 per fork since midnight UTC, reduced for repos that are this busy every day.
Speed-up
Stars per day in the window divided by stars per day in the window before. "New" means the repo is younger than the window. "Under 14 days" (twice the window; "Under 2 years" for 1 year) means it is older than the window but too young for a full window before it to compare with.
Bars
Stars per day (per week for 90 days and 1 year). Bright bars are the selected window. Heights use a square-root scale, so quieter days stay visible next to a spike.

Updated 38 min ago

Columns
#Repository Stars Today 7d 30d Above pace ↑ Momentum Speed-up Daily stars
551

Dynamic Island for macOS

Swift · 23 months old

5,063+5+57+319-350960.5x, slowing
552

🔬 Harness Vibe Research with Self-evolving AI Scientists

Python · 8 months old

4,9170+14+83-35000.2x, slowing
553

Modular SenseNova skills for building AI-powered office assistants and productivity workflows

JavaScript · 6 months old

5,926+6+139+247-350670.4x, slowing
554

A powerful, all-in-one Discord assistant built for every server.

JavaScript · 8 months old

9,201+7+158+895-347640.7x, slowing
555

A next generation HTTP client for Python. 🦋

Python · 5 months old

1,588+3+30+101-345420.2x, slowing
556

Bootstrap Kubernetes the hard way. No scripts.

10 years old

50,473+7+54+319-344640.5x, slowing
557

A Claude skill that writes the accurate prompts for any AI tool. Zero tokens or credits wasted. Full context and memory retention

7 months old

15,096+18+446+1,480-3441730.8x, slowing
558

1,324-exercise fitness dataset — animation GIFs, 180×180 thumbnails, muscle-group & equipment data, and step-by-step instructions in 6 languages. The exercise data layer behind the LogPress app.

HTML · 7 months old

23,237+17+177+980-3441600.7x, slowing
559

Codex-native Academic Research Skills suite for human-in-the-loop academic research workflows

Python · 6 months old

13,538+41+358+1,881-3444530.8x, slowing
560

可私有部署的多租户知识智能体平台:统一 RAG、知识图谱、多智能体、MCP/Skills、沙盒与权限管理。Yuxi = Cloud Agents + Knowledge RAG, Self-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows.

Python · 2 years old

7,504+6+72+309-3431180.5x, slowing
561

An open-source, macOS text action popup for running custom scripts, AI actions, and extensible workflows on selected text.

Swift · 2 months old

712+1+18+175-343180.3x, slowing
562

Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.

Python · 2 months old

2,241+9+121+541-342630.6x, slowing
563

Browse media content with your own rules on Android TV

Java · 6 years old

35,567+19+390+1,475-3401700.8x, slowing
564

Turn long-horizon goals into verifiable results. A local-first semantic control plane and research workbench for long-running agent teams, across sessions and runtimes.

Python · 4 months old

6,436+8+66+450-3401120.6x, slowing
565

OpenWiki is a CLI that writes and maintains agent documentation for your codebase.

TypeScript · 4 months old

17,458+14+179+717-3404120.7x, slowing
566

:house_with_garden: Open source home automation that puts local control and privacy first.

Python · 13 years old

91,738+7+164+748-337810.7x, slowing
567

Summer 2027 software engineering, data science, AI, quant, product management, and hardware internship postings. Updated daily by Simplify and Pitt CSC.

Python · 6 years old

48,160+18+140+613-3372760.6x, slowing
568

Bento, the office suite that fits in a file

TypeScript · 3 months old

5,566+1+46+352-337240.5x, slowing
569

Know how much Claude Code, Codex, Cursor, Copilot and 70+ other AI coding tools you have left — a free, open-source macOS monitor on the edge of your screen.

Swift · 57 days old

599+2+22+126-33726Under 60 days
570

A community-supported supercharged document management system: scan, index and archive all your documents

Python · 4 years old

47,108+6+237+1,112-336580.8x, slowing
571

The ESP32-BlueJammer (Bluetooth jammer, BLE jammer, WiFi jammer, RC jammer) disrupts 2.4GHz communications. Using an ESP32 and nRF24 modules, it generates noise and unnecessary packets, causing interference between the devices communicating, making them unable to work as intended. Ideal for controlled disruption and security testing.

2 years old

8,730+5+49+294-336660.5x, slowing
572

CubePlex is a cloud-native platform for managed agents in team workspaces — skills, shared memory, MCP tools, persistent sandboxes, governed access, and self-hosted deploy on Docker Compose or Kubernetes.

Python · 7 months old

561+3+21+105-334320.2x, slowing
573

Open source evals for physical AI. Run any LLM/VLA on any arm/humanoid against any real/sim benchmark.

Python · 4 months old

7050+14+98-331100.2x, slowing
574

Weather, tides, the sun, the moon, maps, and a planetarium, in your terminal. The Old Farmer's Almanac meets Minitel.

Python · 7 months old

644+1+10+94-329160.2x, slowing
575

Open-source auth gateway connecting 1500+ SaaS providers to AI agents through SDK, CLI, MCP, HTTP, and OpenAPI.

TypeScript · 3 months old

6,093+1+50+223-32970.4x, slowing
576

BigBanana AI Director是一个工业级一站式 AI 短剧,AI 漫剧,AI 导演平台,面向创作者,实现从灵感到成片的高效生产。 它摇弃了传统的“抽卡式”生成,采用 "Script-to-Asset-to-Keyframe" 的工业化工作流。实现 “一句话生成完整短剧,从剧本到成片全自动化”,同时精准控制角色一致性、场景连续性与镜头运动。

8 months old

2,377+1+26+161-32800.3x, slowing
577

Autonomous game development with Claude Code and Codex

Python · 8 months old

7,217+3+50+241-328580.4x, slowing
578

The batteries-included agent harness.

Python · 14 months old

30,607+16+182+874-3272310.7x, slowing
579

OpenLake is a high performance storage engine for efficient LLM inference and GPU Training

Rust · 5 months old

2,6370+1+10-32700.0x, slowing
580

GVS5H: Five Qwen3.8-27B Models Match Claude Fable 5 on LiveCodeBench Hard | Fable 5 Level Coding for a Fifth the Price - or on a Single GPU

Python · 1 months old

1,035+28+283+347-3274940.5x, slowing
581

Ask the oracle when you're stuck. Invoke GPT-5 Pro with a custom context and files.

TypeScript · 11 months old

4,0600+1+47-32600.1x, slowing
582

The missing integration layer for AI agents. Let them call any OpenAPI / MCP / GraphQL / custom js functions in secure environment.

TypeScript · 8 months old

4,270+4+52+294-326500.5x, slowing
583

ProxCenter is an alternative to VMware vCenter for Proxmox environments. It provides a modern, intuitive web interface to manage multiple Proxmox VE clusters and Proxmox Backup Server instances from a single pane of glass.

TypeScript · 8 months old

1,741+1+14+68-32480.2x, slowing
584

A curated list of public-source, research, and commercial tools for AI security and AI-assisted cybersecurity — autotriage, agent security, AI/ML supply chain, pentest agents, AI SAST, LLM-driven fuzzing, threat intelligence, SOC/SIEM triage, reverse engineering, LLM red-teaming, and more.

Python · 4 months old

1,684+1+17+139-323120.3x, slowing
585

把书、长视频、播客等高价值内容蒸馏成可执行的 Agent Skills(Distill high-value content from books, long-form videos, podcasts, and more into executable Agent Skills)

Python · 6 months old

11,763+25+277+1,186-3222720.8x, slowing
586

美股指南

4 months old

7,797+5+65+555-322640.6x, slowing
587

AI-guided editable scientific figures with Codex and local Origin/OriginPro

Python · 3 months old

1,010+4+43+238-321560.4x, slowing
588

Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.

Rust · 7 months old

3,324-1+4+49-32000.1x, slowing
589

Frontier-class open models on a free Kaggle TPU v5e-8: GLM-5.3-Flash 320B MoE (~165 tok/s, our own JAX engine) and Qwen3.8-27B bf16 (~130 tok/s), 262k context, prefix caching. Works with Claude Code, Codex, opencode and pi.

Python · 55 days old

732+4+40+200-32040Under 60 days
590

A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent

Python · 19 months old

30,731+12+335+1,003-3191050.8x, slowing
591

Just a VLM Agent Can Play Robots

Python · 49 days old

587+1+17+129-31916Under 60 days
592

Skills for Design Engineers

TypeScript · 9 months old

10,209+18+334+1,100-3181520.8x, slowing
593

基于 Rust 的低风控、高性能、自托管多账号透明代理网关

Rust · 4 months old

961+6+81+314-318900.5x, slowing
594

Browser automation CLI for AI agents

Rust · 9 months old

44,623+23+330+1,518-3172390.8x, slowing
595

CLI runbook for agent long run.

Python · 4 months old

1,493+2+66+277-317390.5x, slowing
596

Annotate terminal text, review documents and agent replies in Herdr, and send the feedback straight back to the agent.

Rust · 2 months old

700+1+26+132-316160.3x, slowing
597

Give your AI a full stack: memory, voice, face, and hands. This is the "I want an AI agent" shortcut. It sets up the entire jaredrhod stack for you with an installation wizard. Select which pieces you want or do it all!

Batchfile · 2 months old

1,171+2+45+208-316180.4x, slowing
598

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

LLVM · 9 years old

41,200+1+93+515-315290.6x, slowing
599

35 production-grade agentic AI architectures (Reflexion, LATS, GraphRAG, MemGPT, Voyager, BrowserAgent, ...) — a Python library and runnable textbook with multi-provider LLM support and a 17-task benchmark leaderboard.

Jupyter Notebook · 13 months old

4,634+1+17+90-315100.2x, slowing
600

A lightweight, lightning-fast, in-process vector database

C++ · 10 months old

16,151+1+28+181-315160.4x, slowing

Today counts stars since midnight US Pacific time, so it is a partial day.