A research lead finder, a vision results kit, and a context trimmer

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

   pewdiepie-archdaemon/odysseus : Bring AI chat, research and notes into one workspace

   Python

   A self-hosted workspace that brings AI chat, research, documents, notes and planning tools together. Useful for exploring whether keeping these activities in one application helps your daily workflow, with feature maturity checked against the tasks you need.

   +252
2. 2

   mvanhorn/last30days-skill : Find what people discussed in the last month

   Python

   A research skill for gathering recent discussion about a topic across web and community sources. Useful before writing about a fast-moving subject, with the collected posts serving as leads to verify rather than a complete or representative account of public opinion.

   +208
3. 3

   RyanCodrai/turbovec : Build a growing document search index with smaller vectors

   Python

   A vector index that uses quantization to reduce the memory needed for document embeddings. It supports adding vectors without a separate training pass, useful for experimenting with a local document search collection that keeps growing.

   +166
4. 4

   Leonxlnx/taste-skill : Show your AI the look you want before it builds the UI

   Shell

   A skill collection for improving the layout, typography and motion of AI-built interfaces. It also supports making visual references before coding, useful when a clear example would communicate your design intent better than another long prompt.

   +135
5. 5

   roboflow/supervision : Turn object detections into tracks, boxes and counts

   Python

   Python utilities for turning vision-model detections into useful results such as annotated images, object tracks and zone counts. Useful when the detector already works but you still need the surrounding code to inspect results or build a video-analysis workflow.

   +128
6. 6

   alibaba/open-code-review : Put AI review comments on the lines that need attention

   Go

   Reviews code changes with an AI model and places comments on the relevant lines. File selection and comment positioning are handled by ordinary program logic, useful when you want review suggestions that are easier to locate and check in a large diff.

   +120
7. 7

   chopratejas/headroom : Trim bulky tool output before it fills your AI's context

   Python

   Compresses material such as logs, tool outputs and retrieved documents before an agent sends it to a model. Useful when large, repetitive inputs consume the context window; test whether the compressed version preserves the details your task actually needs.

   +116
8. 8

   safishamsi/graphify : Map your code and docs, with inferred links marked

   Python

   Maps code and mixed project documents into a graph that you can browse and query. It labels connections as extracted or inferred, useful for investigating how two concepts relate while keeping source evidence separate from the tool's interpretation.

   +114
9. 9

   XingYu-Zhong/DeepSeek-GUI : Keep an eye on your coding agent's changes and checks

   TypeScript

   An AI coding workbench with desktop and terminal interfaces sharing the same tasks. Changes and test evidence stay attached to the work, useful if you want to switch interfaces while still being able to inspect what the agent did.

   +102
10. 10

    NousResearch/hermes-agent : An assistant that can turn past tasks into reusable skills

    Python

    A personal AI agent with persistent memory, accessible from a terminal or chat apps. It can save skills from completed tasks and search earlier conversations, making it interesting for recurring work that benefits from remembering previous attempts.

    +101