Signal SentrySearchUpdated Nov 20, 05:30 UTCAM Drop
Repos · climbing fastest

AI repos, ranked by star velocity.

Measured from our own snapshots of the GitHub API, so the numbers compare Drop to Drop.

Vet before you run. Trending doesn't mean safe. Read the code, check the maintainers, run it in a sandbox first, and never pipe an install script into your shell.

From the Drops

ReposFollowing since Nov 17, 2026in 5 Drops

rust-anything rewrites apps in Rust step by step, checked against originals; 5520 stars

On GitHub:Rewrite your whole app in Rust, one piece at a time, checked against the original's recorded behavior at every step…Rust

The MIT-licensed repo ports CLIs, HTTP servers and libraries from TypeScript, Python, C, Go, Ruby and Java to Rust, checking each step against recorded behavior. It gained 866 stars since our last check; created Nov 16.

Why it matters: Checking every step against recorded behavior is the safeguard to judge here. Try it on a small CLI before pointing it at a service you run.

  • 5,520★ total
  • +866★ since our last check (14 h)
  • License: MIT
  • Created Nov 16, 2026
  • Last push Nov 19, 2026
From Drop #097 · Fri, Nov 20, 2026 · Morning
Repos

inference-optimisation-skill lets an agent tune local LLM serving speed; 950 stars

On GitHub:Agent skill for hill-climbing local LLM serving speed (decode, speculative decoding, prefill, KV, startup, TTFT) on any…Python

An MIT-licensed skill that has an agent iteratively tune local LLM serving, covering decode, speculative decoding, prefill, KV cache, startup and time to first token. Created Nov 16; up 263 stars since our last check.

Why it matters: If you serve models on your own hardware, it is a quick way to let an agent search for faster settings. It is two days old, so review what it changes.

  • 950★ total
  • +263★ since our last check (12 h)
  • License: MIT
  • Created Nov 16, 2026
  • Last push Nov 16, 2026
From Drop #093 · Wed, Nov 18, 2026 · Morning
ReposFollowing since Nov 16, 2026in 3 Drops

blender-ai-mcp-addon adds an AI assistant and MCP server to Blender; 2261 stars

On GitHub:AI assistant and MCP server for Blender: visual chat, scene tools, multi-agent workflows. Works with ChatGPT/GPT…

The MIT-licensed repo, created Nov. 12, offers visual chat, scene tools and multi-agent workflows, and works with several model providers. It gained 140 stars since our last check.

Why it matters: Still the fastest climber in our repo data, a sign MCP is reaching creative tools. Review what scene and scripting access it grants before use.

  • 2,261★ total
  • +140★ since our last check (8 h)
  • License: MIT
  • Created Nov 12, 2026
  • Last push Nov 12, 2026
From Drop #091 · Tue, Nov 17, 2026 · Morning
Repos

agentes-chat runs a self-hosted Slack-style workspace for teams and AI agents; 1475 stars

On GitHub:Open-source, self-hosted Slack alternative where your team and AI agents work together in channels and DMs. Agents run…TypeScript

An AGPL-3.0 chat app where agents on Claude, ChatGPT/Codex, Gemini or Grok work in channels and DMs with MCP tools, memory and approvals. Created Nov. 9; up 64 stars since our last check.

Why it matters: A sign that teams want agents in shared chat with approval steps, not only in the IDE. Note the AGPL license before offering it to outside users.

  • 1,475★ total
  • +64★ since our last check (12 h)
  • License: AGPL-3.0
  • Created Nov 9, 2026
  • Last push Nov 15, 2026
From Drop #088 · Sun, Nov 15, 2026 · Evening
ReposFollowing since Nov 13, 2026in 2 Drops

yogurt takes private AI meeting notes on your own computer; 1512 stars

On GitHub:Private AI meeting notes that stay on your computer. A free, open-source alternative to Granola for Mac, Windows and…TypeScript

FrigadeHQ/yogurt, an MIT-licensed open-source alternative to Granola for Mac, Windows and Linux that keeps notes local, has 1512 stars, up 116 since our last check. It was created on 2026-11-10.

Why it matters: Teams wary of sending meetings to a cloud note-taker can trial a local one, but the repo is days old, so judge its maturity before relying on it.

  • 1,512★ total
  • +116★ since our last check (12 h)
  • License: MIT
  • Created Nov 10, 2026
  • Last push Nov 15, 2026
From Drop #087 · Sun, Nov 15, 2026 · Morning
Repos

agentes-chat runs a self-hosted Slack alternative for teams and AI agents; 942 stars

On GitHub:Open-source, self-hosted Slack alternative where your team and AI agents work together in channels and DMs. Agents run…TypeScript

An AGPL-3.0 project created November 9 where agents on Claude, ChatGPT/Codex, Gemini or Grok work in channels and DMs with MCP tools, memory and approvals. It gained 546 stars since our last check.

Why it matters: Another sign teams want agents inside shared chat with approvals; review the AGPL-3.0 terms before building on it.

  • 942★ total
  • +546★ since our last check (12 h)
  • License: AGPL-3.0
  • Created Nov 9, 2026
  • Last push Nov 12, 2026
From Drop #082 · Thu, Nov 12, 2026 · Evening
ReposFollowing since Nov 11, 2026in 2 Drops

lot-map shows Claude Code's tool calls and subagents live beside the chat; 427 stars

On GitHub:A live map beside the chat that shows what Claude Code is doing: tool calls, model steps, hooks, skills and subagents…TypeScript

The MIT-licensed lot-map, created Nov. 9, gained 173 stars since our last check. It lights up Claude Code's tool calls, model steps, hooks, skills and subagents as they happen, runs locally and comes in five languages.

Why it matters: A quick way to see what a coding agent does in a session, useful before granting it more access.

  • 427★ total
  • +173★ since our last check (12 h)
  • License: MIT
  • Created Nov 9, 2026
  • Last push Nov 12, 2026
From Drop #081 · Thu, Nov 12, 2026 · Morning
Repos

onlyread makes AI browser agents read-only by refusing writes; 86 stars

On GitHub:Make AI browser agents read-only: a Chrome extension that refuses writes (send, post, edit, delete) before they leave…TypeScript

onlyread is a Chrome extension that blocks sends, posts, edits and deletes before they leave the browser. Licensed AGPL-3.0 and created Nov. 5, it gained 31 stars since our last check.

Why it matters: A simple guard for trying browser agents on real accounts: let them look, but not act, until you trust them.

  • 86★ total
  • +31★ since our last check (12 h)
  • License: AGPL-3.0
  • Created Nov 5, 2026
  • Last push Nov 11, 2026
From Drop #081 · Thu, Nov 12, 2026 · Morning
Repos

solo-to-team-skills helps one person delegate to and verify AI agents; 642 stars

On GitHub:Skills for human-led AI teams: delegate tasks, verify evidence, explain steps clearly, and learn from real cases. 一个人统筹…

An MIT-licensed set of skills for human-led AI teams: delegating tasks, verifying evidence, explaining steps and reusing lessons from real cases. Created Nov 7, it gained 62 stars since our last check.

Why it matters: A sign builders want verification built into delegation; worth a look if you hand work to several agents at once.

  • 642★ total
  • +62★ since our last check (12 h)
  • License: MIT
  • Created Nov 7, 2026
  • Last push Nov 7, 2026
From Drop #080 · Wed, Nov 11, 2026 · Evening
Repos

ste80-humanizer rewrites text toward Simplified Technical English; 266 stars

On GitHub:STE80 Humanizer: agent skill that removes AI tells and rewrites text 80% of the way to ASD-STE100 (Simplified Technical…Python

An MIT-licensed agent skill, created 2026-11-09, that removes AI tells and rewrites text toward ASD-STE100. It gained 126 stars since our last check.

Why it matters: A small skill to try if you want plainer agent-written docs; it is a day old, so review it before relying on it.

  • 266★ total
  • +126★ since our last check (12 h)
  • License: MIT
  • Created Nov 9, 2026
  • Last push Nov 10, 2026
From Drop #078 · Tue, Nov 10, 2026 · Evening
Repos

poki lets AI agents operate a real iPhone with no jailbreak; 704 stars

On GitHub:Let AI agents operate a real iPhone. Local MCP server and agent, no jailbreak, no extra hardware.Swift

JosssphZhou/poki is a local MCP server and agent for driving a real iPhone without a jailbreak or extra hardware. It gained 87 stars since our last check; AGPL-3.0, created Nov. 5.

Why it matters: Phone control is a new agent surface. An agent tapping through apps can act as whatever accounts the phone is signed into, so try it on a spare device first.

  • 704★ total
  • +87★ since our last check (12 h)
  • License: AGPL-3.0
  • Created Nov 5, 2026
  • Last push Nov 9, 2026
From Drop #076 · Mon, Nov 9, 2026 · Evening
Repos

agent-autoloop runs CLI agents in the background, asking only when unsure; 4259 stars

On GitHub:让你的命令行 Agent 在后台自己接活、自己跟进到底;平时不烦你,遇到拿不准的事才发卡片找你拍板。TypeScript

KKKKhazix/agent-autoloop, described in Chinese, lets a command-line agent take on and follow through on work in the background, sending a card for a human decision only when unsure. Up 106 stars since our last check; MIT.

Why it matters: It puts the act-or-ask choice in the harness. Check what the tool counts as unsure before trusting it with anything you can't undo.

  • 4,259★ total
  • +106★ since our last check (12 h)
  • License: MIT
  • Created Nov 3, 2026
  • Last push Nov 9, 2026
From Drop #076 · Mon, Nov 9, 2026 · Evening
Repos

openai/codex is a lightweight coding agent for the terminal; 133914 stars

On GitHub:Lightweight coding agent that runs in your terminalRust

OpenAI's Codex repo gained 164 stars since our last check, the most of any repo we track this run. Apache-2.0 license, created in April 2025.

Why it matters: Interest keeps climbing in vendor-built open-source agent harnesses; teams standardizing on one can inspect and fork this one under Apache-2.0.

  • 133,914★ total
  • +164★ since our last check (12 h)
  • License: Apache-2.0
  • Created Apr 13, 2025
  • Last push Nov 9, 2026
From Drop #075 · Mon, Nov 9, 2026 · Morning
Repos

solo-to-team-skills packages skills for one person leading AI agents; 301 stars

On GitHub:Skills for human-led AI teams: delegate tasks, verify evidence, explain steps clearly, and learn from real cases. 一个人统筹…

Skills to delegate tasks, verify evidence, explain steps and reuse lessons from real cases. Up 63 stars since our last check; MIT license, created Nov 7.

Why it matters: Builders want delegation and verification habits packaged, not just more agents. The repo is days old: read the skills before adding them to an agent.

  • 301★ total
  • +63★ since our last check (12 h)
  • License: MIT
  • Created Nov 7, 2026
  • Last push Nov 7, 2026
From Drop #075 · Mon, Nov 9, 2026 · Morning
Repos

sand3d does 3D modeling in Python, built for LLMs; 1305 stars

On GitHub:3D modeling in Python, built for LLMs.HTML

Sandflow-ai/sand3d, an Apache-2.0 library for 3D modeling in Python aimed at LLMs, gained 223 stars since our last check. It was created on Nov 3.

Why it matters: Code-first 3D lets an agent build and edit models as text it can diff. Worth a look if you are wiring agents into design or game pipelines.

  • 1,305★ total
  • +223★ since our last check (12 h)
  • License: Apache-2.0
  • Created Nov 3, 2026
  • Last push Nov 6, 2026
From Drop #074 · Sun, Nov 8, 2026 · Evening
Repos

sandbox-mcp spins up throwaway Windows Sandbox machines through MCP; 280 stars

On GitHub:Fresh, throwaway Windows machines for testing your apps: an MCP server and CLI that automate Windows SandboxJavaScript

shanselman/sandbox-mcp is an MCP server and CLI that automates Windows Sandbox to give fresh, disposable Windows machines for app testing. MIT licensed, created Nov 6, up 98 stars since our last check.

Why it matters: Agents testing Windows apps can work in a disposable machine instead of on your desktop. Review what the server exposes before granting it access.

  • 280★ total
  • +98★ since our last check (12 h)
  • License: MIT
  • Created Nov 6, 2026
  • Last push Nov 7, 2026
From Drop #073 · Sun, Nov 8, 2026 · Morning
Repos

vork is a headless 3D and VFX engine for agents; 723 stars

On GitHub:Headless 3D and VFX engine for agents. Research preview.Rust

voyager-so/vork, a research preview created Nov 5, gained 305 stars since our last check. It has no license listed.

Why it matters: Agents that build 3D scenes or effects need an engine with no screen attached. With no license listed, check its terms before building on it.

  • 723★ total
  • +305★ since our last check (12 h)
  • Created Nov 5, 2026
  • Last push Nov 7, 2026
  • No license

Flags are signals, not verdicts.

From Drop #072 · Sat, Nov 7, 2026 · Evening
Repos

agent-autoloop runs a CLI agent in the background, asking only when unsure; 3736 stars

On GitHub:让你的命令行 Agent 在后台自己接活、自己跟进到底;平时不烦你,遇到拿不准的事才发卡片找你拍板。TypeScript

Its description says it lets a command-line agent pick up and follow through on work in the background, sending a card for your decision when it is unsure. MIT license, created Nov 3, up 148 stars since our last check.

Why it matters: A small example of the ask-only-when-unsure pattern; if you try it, decide up front which actions must always come back to you.

  • 3,736★ total
  • +148★ since our last check (12 h)
  • License: MIT
  • Created Nov 3, 2026
  • Last push Nov 7, 2026
From Drop #071 · Sat, Nov 7, 2026 · Morning
Repos

poki lets AI agents operate a real iPhone via a local MCP server; 363 stars

On GitHub:Let AI agents operate a real iPhone. Local MCP server and agent, no jailbreak, no extra hardware.JavaScript

The repo describes a local MCP server and agent that drive a real iPhone with no jailbreak and no extra hardware. It gained 96 stars since our last check; AGPL-3.0, created Nov 5.

Why it matters: An agent driving a real phone can reach whatever apps are signed in on it. If you try it, use a test device rather than your own.

  • 363★ total
  • +96★ since our last check (12 h)
  • License: AGPL-3.0
  • Created Nov 5, 2026
  • Last push Nov 6, 2026
From Drop #070 · Fri, Nov 6, 2026 · Evening
Repos

sand3d does 3D modeling in Python, built for LLMs; 359 stars

On GitHub:3D modeling in Python, built for LLMs.HTML

Sandflow-ai/sand3d, a Python library for 3D modeling designed for LLMs, gained 247 stars since our last check to reach 359. Apache-2.0 license; created November 3.

Why it matters: Code-first 3D lets agents produce and revise models as scripts. The repo is days old, so check its maturity before relying on it.

  • 359★ total
  • +247★ since our last check (12 h)
  • License: Apache-2.0
  • Created Nov 3, 2026
  • Last push Nov 5, 2026
From Drop #069 · Fri, Nov 6, 2026 · Morning
Repos

uncut runs a headless coding-agent harness from one 7 MB binary; 604 stars

On GitHub:The lossless, headless coding agent harness. One 7 MB static binary, four tools, plain stdin/stdout, no silent cuts.Go

The repo describes a lossless, headless coding agent harness: one static binary, four tools, plain stdin/stdout. It gained 2 stars since our last check; MIT license, created Nov 1.

Why it matters: A minimal harness is easier to audit than a full framework; worth a look if you want to see every step an agent takes.

  • 604★ total
  • +2★ since our last check (6 h)
  • License: MIT
  • Created Nov 1, 2026
  • Last push Nov 2, 2026
From Drop #068 · Thu, Nov 5, 2026 · Evening
Repos

sapper-v2 runs an autonomous pentest swarm led by an AI commander; 1110 stars

On GitHub:Autonomous pentest legion — AI commander + worker swarm + layered fact-intent graph. 3rd Tencent Intelligent…Python

The repo describes an AI commander directing a worker swarm with a layered fact-intent graph, and says it won a Tencent attack-defense contest. It gained 379 stars since our last check; MIT license, created Oct 30.

Why it matters: Unattended offensive agents are getting easy to pick up. Security teams should assume attackers can run them and test their own exposure the same way.

  • 1,110★ total
  • +379★ since our last check (18 h)
  • License: MIT
  • Created Oct 30, 2026
  • Last push Nov 3, 2026
From Drop #067 · Thu, Nov 5, 2026 · Morning
ReposFollowing since the Morning Dropin 2 Drops

agent-autoloop runs CLI agents in the background, pinging you when unsure; 2262 stars

On GitHub:让你的命令行 Agent 在后台自己接活、自己跟进到底;平时不烦你,遇到拿不准的事才发卡片找你拍板。TypeScript

The MIT-licensed repo, created Nov 3, says it lets a command-line agent pick up and follow through work in the background, sending you a card only when it needs a decision. It gained 1337 stars since our last check.

Why it matters: Background agents that ask only when unsure move review to moments they choose. Before trying it, check what the agent may do without asking.

  • 2,262★ total
  • +1,337★ since our last check (12 h)
  • License: MIT
  • Created Nov 3, 2026
  • Last push Nov 4, 2026
From Drop #066 · Wed, Nov 4, 2026 · Evening
ReposFollowing since Oct 30, 2026in 9 Drops

Mika runs an on-device Android agent that operates apps and the web; 6159 stars

On GitHub:An on-device AI agent for Android that operates apps and the web to get things done for you.Kotlin

An Apache-2.0 repo created Oct 29 for an on-device Android agent that works apps and the web for you. It gained 193 stars since our last check.

Why it matters: Interest in phone agents that act inside apps keeps climbing. Check what permissions it needs before putting it on a device with work accounts.

  • 6,159★ total
  • +193★ since our last check (12 h)
  • License: Apache-2.0
  • Created Oct 29, 2026
  • Last push Nov 3, 2026
From Drop #065 · Wed, Nov 4, 2026 · Morning
Repos

skein runs fail-closed swarm orchestration with epoch-fenced work; 259 stars

On GitHub:Fail-closed swarm orchestration with epoch-fenced work and late-completion rejection.Go

Balanov/skein describes fail-closed agent swarm orchestration that fences work by epoch and rejects late completions. MIT license, created Nov 2, up 2 stars since our last check.

Why it matters: If parallel agents in your stack can deliver stale work after a task has moved on, this repo's design is a short read on one way to refuse it.

  • 259★ total
  • +2★ since our last check (3 h)
  • License: MIT
  • Created Nov 2, 2026
  • Last push Nov 3, 2026
From Drop #064 · Tue, Nov 3, 2026 · Evening
Repos

AnyModelBot runs local-first personal AI bots on 70+ models via one key; 2172 stars

On GitHub:🤖 Open-source, local-first alternative to Grok Bot, OpenAI dots and Claude Duet. Your own AI bots on any model: GPT…Python

An MIT-licensed repo created Oct 27 that pitches itself as an open-source alternative to Grok Bot, OpenAI dots and Claude Duet, reaching many models through one Modelflare key; up 880 stars since our last check.

Why it matters: Worth a look if you want a self-hosted assistant across many models, but traffic goes through one third-party key, so check what that service can see.

  • 2,172★ total
  • +880★ since our last check (21 h)
  • License: MIT
  • Created Oct 27, 2026
  • Last push Nov 3, 2026
From Drop #063 · Tue, Nov 3, 2026 · Morning
Repos

uncut is a headless coding agent harness in one 7 MB binary; 566 stars

On GitHub:The lossless, headless coding agent harness. One 7 MB static binary, four tools, plain stdin/stdout, no silent cuts.Go

uncut, MIT-licensed and created November 1, describes itself as a lossless, headless coding agent harness with four tools and plain stdin/stdout. It gained 255 stars since our last check.

Why it matters: Small, scriptable harnesses let teams wrap a model in a pipeline they can inspect. It is a day old, so treat it as an experiment, not a dependency.

  • 566★ total
  • +255★ since our last check (12 h)
  • License: MIT
  • Created Nov 1, 2026
  • Last push Nov 2, 2026
From Drop #062 · Mon, Nov 2, 2026 · Evening
Repos

kanzo runs a self-hosted kanban board for humans and agents; 422 stars

On GitHub:Self-hosted kanban for humans and agents. One 4 MB binary, starts in 2 ms, zero setup.Rust

kanzo, AGPL-3.0 and created Oct 25, describes itself as one 4 MB binary that starts in 2 ms with zero setup. It gained 195 stars since our last check.

Why it matters: If you run several coding agents, a shared board is one way to see their work next to people's; check the AGPL license before embedding it.

  • 422★ total
  • +195★ since our last check (12 h)
  • License: AGPL-3.0
  • Created Oct 25, 2026
  • Last push Nov 1, 2026
From Drop #060 · Sun, Nov 1, 2026 · Evening
Repos

dsh-Go runs DeepSeek Harness on your phone and can control your PC; 3410 stars

On GitHub:dsh-go — DeepSeek Harness 装进口袋:手机本机运行,也能遥控你的电脑。Dart

Per its description, dsh-go runs DeepSeek Harness locally on a phone and can also remotely control a computer. AGPL-3.0, created October 25; up 694 stars since our last check.

Why it matters: A phone agent that can reach your PC widens what a lost or compromised phone can touch; check what access it holds before you try it.

  • 3,410★ total
  • +694★ since our last check (12 h)
  • License: AGPL-3.0
  • Created Oct 25, 2026
  • Last push Oct 31, 2026
From Drop #058 · Sat, Oct 31, 2026 · Evening
Repos

grim-prompter has coding agents build a threat model of your repo; 292 stars

On GitHub:Threat modeling for AI coding agents: point Claude Code, Codex or any agent at your repo and get an evidence-traced…

Per its description, it points Claude Code, Codex or another agent at a repo to produce an evidence-traced threat model, covering 36 architectures and 29 methods. MIT, created October 28; up 30 stars since our last check.

Why it matters: A low-cost first pass at threat modeling agent-heavy code; treat its output as a starting point for a person's review, not a verdict.

  • 292★ total
  • +30★ since our last check (12 h)
  • License: MIT
  • Created Oct 28, 2026
  • Last push Oct 29, 2026
From Drop #058 · Sat, Oct 31, 2026 · Evening
Repos

sapper-v2 runs an autonomous AI pentest swarm under a commander agent; 178 stars

On GitHub:Autonomous pentest legion — AI commander + worker swarm + layered fact-intent graph. 3rd Tencent Intelligent…Python

An MIT-licensed autonomous pentest tool, created 2026-10-30, pairing an AI commander with a worker swarm. Its description claims a win in a Tencent attack-defense contest of 634 teams, run 8 hours unattended.

Why it matters: Autonomous offensive tooling is now open source; run it only against systems you are authorized to test.

  • 178★ total
  • License: MIT
  • Created Oct 30, 2026
  • Last push Oct 30, 2026
From Drop #057 · Sat, Oct 31, 2026 · Morning
ReposFollowing since Oct 29, 2026in 3 Drops

BLA tries to shield apps from AI reverse-engineering agents; 1268 stars

On GitHub:🛡 BLA (Blind LLM Agents) — Adversarial defense shield that protects binaries, Electron apps, JS bundles, Python, and…TypeScript

qybaihe/bla describes an adversarial shield for binaries, Electron apps, JS bundles, Python and WebAssembly against AI reverse-engineering agents. It gained 357 stars since our last check; MIT, created 2026-10-25.

Why it matters: Interest in defending code from AI-driven analysis keeps climbing; treat its protection claims as the repo's own until tested.

  • 1,268★ total
  • +357★ since our last check (12 h)
  • License: MIT
  • Created Oct 25, 2026
  • Last push Oct 29, 2026
From Drop #056 · Fri, Oct 30, 2026 · Evening
Repos

DeepseekHarness-Android runs DeepSeek Harness on a phone without root; 282 stars

On GitHub:免 ROOT 免 Termux,一个 APK 在安卓手机上跑 DeepSeek Harness。引擎内嵌 App 进程 · 读屏操作 App · 改系统设置 · 定时/条件自动化 · 可选 ShizukuKotlin

Its description says one APK runs the harness with no root or Termux, reads the screen to operate apps, changes system settings and runs scheduled automations. Apache-2.0; up 149 since our last check.

Why it matters: Agents that tap through apps and change settings on a personal phone deserve the same scrutiny as desktop agents with broad access.

  • 282★ total
  • +149★ since our last check (12 h)
  • License: Apache-2.0
  • Created Oct 27, 2026
  • Last push Oct 29, 2026
From Drop #055 · Fri, Oct 30, 2026 · Morning
Repos

agent-office-3d shows your AI coding agents' live status in a 3D office; 86 stars

On GitHub:A low-poly 3D office that shows your AI coding agents' live status — idle agents sneak off to play Minecraft (no tokens…JavaScript

The MIT-licensed project renders a low-poly office where idle coding agents sneak off to play Minecraft, using no tokens. It was created October 29.

Why it matters: A light way to see at a glance which of several agents is busy and which is idle.

  • 86★ total
  • License: MIT
  • Created Oct 29, 2026
  • Last push Oct 29, 2026
From Drop #055 · Fri, Oct 30, 2026 · Morning
ReposFollowing since Oct 27, 2026in 4 Drops

BAMA gives agents skills to build native macOS apps; 725 stars

On GitHub:BAMA: Build Any Mac App. Agent skills to research, clone, design, build, optimize, and test native macOS apps with…Swift

BAMA offers agent skills to research, clone, design, build, optimize and test native macOS apps with Swift and SwiftUI. MIT licensed, created October 24, up 112 stars since our last check.

Why it matters: Packaged skills let coding agents handle a full native app workflow rather than one-off prompts.

  • 725★ total
  • +112★ since our last check (12 h)
  • License: MIT
  • Created Oct 24, 2026
  • Last push Oct 29, 2026
From Drop #054 · Thu, Oct 29, 2026 · Evening
Repos

agentring lets your AI agents call your phone over VoIP; 139 stars

On GitHub:Let your AI agents call your phone over VoIP, and call them back. Your phone rings like a real call, even locked; a…Kotlin

agentring rings your phone like a real call, even when locked; a voice AI talks it through and returns the transcript. Self-hosted, Apache-2.0, created October 23, up 75 stars since our last check.

Why it matters: A way for long-running agents to reach a person for a decision without a phone number or Twilio, per its description.

  • 139★ total
  • +75★ since our last check (12 h)
  • License: Apache-2.0
  • Created Oct 23, 2026
  • Last push Oct 28, 2026
From Drop #054 · Thu, Oct 29, 2026 · Evening
Repos

grim-prompter has AI coding agents threat-model your repo; 87 stars

On GitHub:Threat modeling for AI coding agents: point Claude Code, Codex or any agent at your repo and get an evidence-traced…

Point Claude Code, Codex or any agent at a repo to get an evidence-traced threat model; the repo lists 36 architectures and 29 methods. MIT license; created October 28.

Why it matters: A security review aid for teams already running coding agents. It is a day old, so judge its maturity accordingly.

  • 87★ total
  • License: MIT
  • Created Oct 28, 2026
  • Last push Oct 28, 2026
From Drop #053 · Thu, Oct 29, 2026 · Morning
Repos

Capri runs an Edgerunners-inspired AI agent on your desktop; 379 stars

On GitHub:🌃 Capri — Edgerunners-inspired AI agent for your desktop. Works with Claude Code, Codex, Antigravity & more.

The repo, created October 27 with no license, says it works with Claude Code, Codex, Antigravity and more. It gained 209 stars since our last check.

Why it matters: The fastest climber in our repo tracking this run; with no license listed, reuse rights are unclear.

  • 379★ total
  • +209★ since our last check (7 h)
  • Created Oct 27, 2026
  • Last push Oct 27, 2026
  • No license

Flags are signals, not verdicts.

From Drop #052 · Wed, Oct 28, 2026 · Evening
Repos

kanzo is a self-hosted kanban board for humans and agents; 104 stars

On GitHub:Self-hosted kanban for humans and agents. One 4 MB binary, starts in 2 ms, zero setup.Rust

emanuele-em/kanzo ships as one 4 MB binary that starts in 2 ms with zero setup, per its description. It gained 43 stars since our last check. AGPL-3.0 license, created Oct 25.

Why it matters: A shared task board is a simple way to hand work between people and agents and see who picked up what.

  • 104★ total
  • +43★ since our last check (17 h)
  • License: AGPL-3.0
  • Created Oct 25, 2026
  • Last push Oct 27, 2026
From Drop #051 · Wed, Oct 28, 2026 · Morning
Repos

Codex runs a lightweight coding agent in your terminal; 131252 stars

On GitHub:Lightweight coding agent that runs in your terminalRust

openai/codex gained 197 stars since our last check, the most of any repo on our list. Apache-2.0, created April 2025.

Why it matters: The top gainer this run is a terminal coding agent, a sign of where developer attention sits.

  • 131,252★ total
  • +197★ since our last check (12 h)
  • License: Apache-2.0
  • Created Apr 13, 2025
  • Last push Oct 27, 2026
From Drop #050 · Tue, Oct 27, 2026 · Evening
ReposFollowing since Oct 26, 2026in 3 Drops

CVEngine runs AI-first external attack surface assessments; 387 stars

On GitHub:AI-first external attack surface assessment with continuous discovery, evidence-based vulnerability validation, and…Python

A GPL-3.0 repo created Oct 24 for continuous discovery, evidence-based vulnerability validation and developer-agent MCP integration. Up 63 stars since our last check.

Why it matters: A fast-growing security tool built for agents. Point it only at assets you're authorized to test.

  • 387★ total
  • +63★ since our last check (12 h)
  • License: GPL-3.0
  • Created Oct 24, 2026
  • Last push Oct 27, 2026
From Drop #049 · Tue, Oct 27, 2026 · Morning
Repos

flecha-browser is an open-source Arc alternative with a built-in MCP server; 90 stars

On GitHub:Open-source Arc alternative for macOS: a Chromium browser for developers with Spaces, a dev command bar and a built-in…TypeScript

An MIT-licensed Chromium browser for macOS developers, created Oct 22, with Spaces, a dev command bar and an MCP server for coding agents. It averages 20 stars a day.

Why it matters: A browser that exposes an MCP server lets coding agents act inside it. Limit what it can reach.

  • 90★ total
  • License: MIT
  • Created Oct 22, 2026
  • Last push Oct 25, 2026
From Drop #049 · Tue, Oct 27, 2026 · Morning
Repos

canvas-mcp connects Claude, ChatGPT and other assistants to Canvas LMS; 115 stars

On GitHub:Read-only MCP server that connects Claude, ChatGPT and other AI assistants to Canvas LMS.JavaScript

A read-only MCP server for the Canvas learning management system, MIT-licensed and created October 25. It is new to our watch, so there is no change since our last check yet.

Why it matters: Its read-only design limits what an assistant can change in a school's LMS. It is gaining about 139 stars a day.

  • 115★ total
  • License: MIT
  • Created Oct 25, 2026
  • Last push Oct 26, 2026
From Drop #048 · Mon, Oct 26, 2026 · Evening
ReposFollowing since Oct 25, 2026in 2 Drops

vllm serves LLMs with high throughput and memory efficiency; 95521 stars

On GitHub:A high-throughput and memory-efficient inference and serving engine for LLMsPython

The Apache-2.0 inference and serving engine gained 68 stars since our last check, the most of any tracked repo, at about 136 a day.

Why it matters: Interest in self-hosted serving keeps climbing as open-weight models multiply.

  • 95,521★ total
  • +68★ since our last check (12 h)
  • License: Apache-2.0
  • Created Feb 9, 2023
  • Last push Oct 26, 2026
From Drop #047 · Mon, Oct 26, 2026 · Morning
Repos

Lampline builds AI phone agents locally and tests them with an AI caller; 286 stars

On GitHub:Build AI phone agents on your own computer and test every change with an AI caller. Open source, runs free with no API…Python

C4rohan/Lampline, Apache-2.0 and created Oct 19, builds AI phone agents on your own computer and tests every change with an AI caller; it imports Dialogflow CX. Up 101 stars since our last check.

Why it matters: Voice agents are hard to test before launch. Its description says it runs free with no API keys, or for cents per call with your own keys.

  • 286★ total
  • +101★ since our last check (10 h)
  • License: Apache-2.0
  • Created Oct 19, 2026
  • Last push Oct 24, 2026
From Drop #046 · Sun, Oct 25, 2026 · Evening
Repos

McShake turns McDonald's official MCP into a pixel-art slot machine; 122 stars

On GitHub:麦当劳官方 MCP 驱动的像素风老虎机:营养账本 + 凑单优化 + 1+1 随心配JavaScript

gundamli/McShake, MIT and created Oct 21, wraps McDonald's official MCP in a pixel-style slot machine with a nutrition ledger and order-combining optimization. Up 60 stars since our last check.

Why it matters: It is one of nine McDonald's MCP repos on our list this run, a sign of how quickly a brand's public MCP server draws builders.

  • 122★ total
  • +60★ since our last check (10 h)
  • License: MIT
  • Created Oct 21, 2026
  • Last push Oct 22, 2026
From Drop #046 · Sun, Oct 25, 2026 · Evening
Repos

sglang is a high-performance serving framework for LLMs; 38056 stars

On GitHub:SGLang is a high-performance serving framework for large language models and multimodal models.Python

SGLang serves large language and multimodal models. It gained 356 stars since our last check, the most of any repo we track this run. Apache-2.0, created January 2024.

Why it matters: Serving engines keep drawing attention as open-weight demand grows; vllm, another serving engine, added 84 stars since our last check.

  • 38,056★ total
  • +356★ since our last check (15 h)
  • License: Apache-2.0
  • Created Jan 8, 2024
  • Last push Oct 25, 2026
From Drop #045 · Sun, Oct 25, 2026 · Morning
Repos

mcd-self-butler plans McDonald's orders through McDonald's MCP; 168 stars

On GitHub:麦当劳自助管家 McButler — 基于麦当劳 MCP 的点单参谋:每日推荐 / 套餐健康体检 / 门店全成本比价 / 团餐智能配餐 / 麦险分信用评级 / 麦门小剧场。麦当劳 1024 程序员节参赛作品。Python

A Chinese-language skill built on McDonald's MCP for daily picks, meal health checks and store price comparison, entered in a 1024 Programmer's Day contest. It gained 91 stars since our last check. MIT, created Oct 24.

Why it matters: A cluster of new repos, including mcd-saver-checkup and mcd-meal-mate, also builds on McDonald's MCP, each pitched as a skill for AI agents.

  • 168★ total
  • +91★ since our last check (15 h)
  • License: MIT
  • Created Oct 24, 2026
  • Last push Oct 24, 2026
From Drop #045 · Sun, Oct 25, 2026 · Morning
Repos

ollama gets you running Kimi, DeepSeek, Qwen and other models; 184621 stars

On GitHub:Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.Go

ollama/ollama, MIT-licensed and created in 2023, gets you up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. It gained 118 stars since our last check.

Why it matters: It had the largest star gain of any repo we track this run, as open-weight releases keep coming.

  • 184,621★ total
  • +118★ since our last check (12 h)
  • License: MIT
  • Created Jun 26, 2023
  • Last push Oct 23, 2026
From Drop #044 · Sat, Oct 24, 2026 · Evening
Repos

whatsmyagentdoing shows your Claude Code and Codex agents at work, live; 106 stars

On GitHub:See what every Claude Code and Codex agent on your machine is doing — live, in a little office.JavaScript

Charonyuu/whatsmyagentdoing, MIT-licensed and created Oct 23, shows what every Claude Code and Codex agent on your machine is doing, live. It has 106 stars; it is too new for a change since our last check.

Why it matters: As people run several coding agents at once, simple tools for seeing what each one is doing are drawing interest.

  • 106★ total
  • License: MIT
  • Created Oct 23, 2026
  • Last push Oct 24, 2026
From Drop #044 · Sat, Oct 24, 2026 · Evening

Showing the newest 50 of 104. Older ones stay on their Drop's page in the archive.

Star velocity

Stars gained between our checks

Over 14 h, between our checks at Nov 19, 16:00 UTC and Nov 20, 06:00 UTC. Names only: these repos were measured, not vetted, so we don't link them.

Repos ranked by stars gained since our previous check
RepoStars gainedTotalFlags
erkamyaman/rust-anythingRewrite your whole app in Rust, one piece at a time, checked against the original's recorded behavior at every step…Rust · MIT+8665,520None
ggml-org/llama.cppLLM inference in C/C++C++ · MIT+80135,786None
ollama/ollamaGet up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.Go · MIT+69187,690None
anthropics/claude-codeClaude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster…TypeScript+66156,359
  • No license
sybil-solutions/inference-optimisation-skillAgent skill for hill-climbing local LLM serving speed (decode, speculative decoding, prefill, KV, startup, TTFT) on any…Python · MIT+601,272None
openai/codexLightweight coding agent that runs in your terminalRust · Apache-2.0+44135,920None
huggingface/transformers🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio…Python · Apache-2.0+42169,304None
langchain-ai/langchainThe agent engineering platform.Python · MIT+36149,942None
vllm-project/vllmA high-throughput and memory-efficient inference and serving engine for LLMsPython · Apache-2.0+2597,240None
boringmarketer/boring-marketing-skills32 free marketing skills for your AI agent: research, positioning, copy, pages, SEO, AI search, ads, email and content…Python · MIT+24723None

Flags are signals, not verdicts.