This week: taming agent output, routing free model quotas, and agents that research for real

Fastest-growing this period

Counts come from GitHub's official stargazers/history endpoint: the stars gained on each day of the window. Project briefs and the reading notes below are editorial additions.

1. 1

   ayghri/i-have-adhd : Stop your coding agent from burying the answer

   Python

   Installs as a skill for Claude Code and similar assistants and changes how they reply: the answer comes first, multi-step tasks are numbered, and every reply ends with one concrete next step. Useful when long agent responses make you hunt for the actual fix; its rule file is plain text, so you can tune the behavior yourself.

   +16,980
2. 2

   bilawalsidhu/gods-eye-view : Follow flights and ships around an interactive 3D Earth

   JavaScript

   A browser-based 3D globe that combines public feeds such as aircraft, ships and earthquakes. Following an aircraft across the terrain is an engaging way to explore geographic data; its visual sensor effects should not be confused with actual sensor imagery.

   +13,398
3. 3

   tt-a1i/archify : Show your team exactly what changed in the architecture

   JavaScript

   Turns an agent's structured description of a system into interactive HTML and SVG architecture diagrams. It can compare diagram snapshots, useful for showing a team which components and connections changed between two versions of a design.

   +9,548
4. 4

   deepseek-ai/deepseek-harness : Explore DeepSeek's building blocks for an extensible agent

   TypeScript

   DeepSeek's agent runtime built around replaceable plugins, with a web interface for running it. Useful for developers exploring how to compose an agent's capabilities; it is a developer preview, so expect interfaces to change as you experiment.

   +8,535
5. 5

   DietrichGebert/ponytail : Stop your AI turning a small fix into a new framework

   JavaScript

   A set of instructions that asks AI coding agents to reuse existing code and question whether a new abstraction is needed. Its rules also explicitly retain validation and error handling, useful when your agent keeps making a small task unnecessarily complicated.

   +7,635
6. 6

   debpalash/VoiceStudio : Try voice design, transcription and dubbing in one workspace

   Python

   A local audio workspace for voice design, transcription, dubbing and longer narrated projects. Useful for trying several speech workflows with your own material in one application, with engine choice and hardware determining the supported languages and output quality.

   +6,872
7. 7

   cathrynlavery/diagram-design : Make your diagrams match the article around them

   HTML

   A coding-agent skill for turning an explanation or existing diagram source into HTML and SVG diagrams. It can incorporate a publication's colors and fonts, useful when a diagram needs to fit an article or presentation rather than look like a separate tool's default export.

   +6,555
8. 8

   mattpocock/skills : Make your AI ask the right questions before it writes code

   Shell

   Give your coding assistant a skill that asks detailed questions before implementation. Use it to clarify vague requirements before the agent builds the wrong thing.

   +6,344
9. 9

   affaan-m/ECC : Give your coding agent a plan, tests and a memory

   JavaScript

   A collection of coding-agent workflows for planning, tests, review and remembering useful context. If your assistant jumps straight into edits or forgets earlier decisions, this gives you reusable routines to adapt to your project.

   +6,240
10. 10

    heygen-com/hyperframes : Write HTML and let an agent render it as video

    TypeScript

    Turns HTML, CSS and seekable animations into deterministic MP4 videos. You can drive it from a local CLI or hand its skills to an AI coding agent, which plans the video, writes valid markup, lints, previews and renders. A practical route to product intros or animated explainers without learning a timeline editor. Requires Node.js 22 or newer.

    +5,155
11. 11

    stablyai/orca : Compare several coding agents in separate workspaces

    TypeScript

    A desktop interface for running terminal coding agents in separate Git worktrees. You can compare attempts at the same task and inspect their changes, useful when juggling several experiments would otherwise mean managing many terminals and directories.

    +4,983
12. 12

    microsoft/markitdown : Turn a pile of mixed documents into Markdown

    Python

    Converts documents such as PDFs and Office files into Markdown for text-processing tools. Useful when you want to feed a folder of mixed documents into search or an AI workflow while retaining headings, lists and other readable structure where supported.

    +4,708
13. 13

    google/artemis : Let an AI assistant drive a real Android phone for tests

    Python

    A Google open-source tool that lets AI assistants and test suites operate a real Android phone or emulator from natural-language instructions. It plugs into coding assistants through MCP, so the assistant can drive the device and pull back screenshots and Logcat logs, while a browser view mirrors the screen live.

    +4,488
14. 14

    webadderallorg/Recordly : Record polished demo videos without touching a timeline editor

    TypeScript

    An open-source desktop app that records your screen and turns the raw footage into a presentable demo: automatic zoom suggestions, smoothed cursor movement, styled frames and a webcam bubble you can pin anywhere. A drag-and-drop timeline covers trims, speed changes and annotations, and projects save as files you can reopen later.

    +4,263
15. 15

    obra/superpowers : Give a multi-step coding task checkpoints you can inspect

    Shell

    A skill collection that guides a coding assistant through requirements, planning, implementation, tests and review. Useful for longer features where you want explicit checkpoints before the agent moves from an idea to a large set of code changes.

    +3,946
16. 16

    THU-MAIC/OpenMAIC : Turn your study material into a class you can question

    TypeScript

    Turns a topic or document into an interactive classroom with teaching material, quizzes and AI participants. Useful when you want to study by asking questions and discussing examples rather than only reading an automatically generated summary.

    +3,944
17. 17

    liquidslr/system-design-notes : Review one system design problem at a time

    Chapter-by-chapter notes based on the System Design Interview books by Alex Xu, covering classic problems like rate limiters, consistent hashing, URL shorteners and payment systems. Each chapter is a folder, so you can work through one design at a time instead of rereading the whole book before an interview.

    +3,880
18. 18

    diegosouzapw/OmniRoute : Hundreds of AI providers behind one endpoint, zero keys to start

    TypeScript

    A self-hosted AI gateway that puts hundreds of model providers behind one OpenAI-compatible endpoint. On a fresh install you can send a request with the model set to auto and no keys at all, and its fallback chain moves to another provider when one runs out of quota, handy for experiments you would rather not put on a credit card.

    +3,720
19. 19

    Tencent/teamai-cli : Share skills, rules and MCP config across your whole team

    TypeScript

    A CLI that keeps a team's agent setup in one git repo. Admins publish skills, rules, hooks and MCP servers there, and each member runs a single init command so every Claude Code, Codex or Cursor session pulls the latest setup automatically. Useful when you want every teammate's assistant to follow the same conventions instead of passing files around by hand.

    +3,584
20. 20

    public-apis/public-apis : Find an API for the data your prototype is missing

    Python

    A categorized directory of public APIs with information about authentication and browser access. Useful for finding a data source for a prototype, then checking the chosen provider's current availability and terms before integrating it.

    +3,351
21. 21

    freestylefly/awesome-gpt-image-2 : Start an image prompt from a visual example you like

    JavaScript

    A collection of image-generation prompts and examples for formats such as posters, product shots and interface mockups. Useful for finding a visual starting point and adapting its composition or style to your own subject instead of describing everything from a blank page.

    +3,343
22. 22

    vastsa/PI-Desktop : A desktop home for your AI coding agent, no vendor lock-in

    TypeScript

    A desktop workspace that gives AI coding agents a home outside any single editor or model vendor. Projects, sessions, diffs and reviews stay on your machine, you choose the provider, and three working modes let you trade speed for control, from supervised edits to a goal the agent pursues on its own.

    +3,253
23. 23

    blader/humanizer : Find the phrases that make your draft sound like AI

    Python

    An editing skill that looks for repetitive, inflated and formulaic AI writing and proposes rewrites. Useful for getting a second pass over a draft, especially when you supply an example of the voice you actually want to keep.

    +3,169
24. 24

    JustVugg/colibri : Run 700-billion-parameter MoE models on hardware you already own

    C

    A pure C inference engine with zero dependencies that streams the experts of giant mixture-of-experts models from disk, treating VRAM, RAM and storage as a single memory hierarchy. It runs models from 744B up to 2.8T parameters on consumer hardware, and a built-in web dashboard shows which expert tiers are active while you chat.

    +2,969
25. 25

    EvoMap/AutoResearch : From research idea to paper-ready evidence with cross-model review

    Python

    An open-source agent workflow that turns a research idea into an evidence package ready for paper writing. It can propose directions from recent papers and community signals, has at least three different models cross-check each idea, and writes plans, code, logs and reviews to disk so a long run can be inspected, resumed or stopped at any point.

    +2,947

Ranking window: 2026-09-07 to 2026-09-13 UTC.