DietrichGebert/ponytail
Ponytail enables AI agents to generate more concise, efficient, and cost-effective code by enforcing a "lazy senior dev" methodology, prioritizing existing solutions and minimal implementation.
Awesome AI Agents › AI Assistants
gaotiexinqu/OneResearchClaw
OneResearchClaw is a Python pipeline that takes real working materials in many formats and produces finished research reports without manual handoffs between stages. Accepted inputs include meeting audio and video, documents, tables, PowerPoint files, ZIP archives holding mixed material, and links to arXiv papers, YouTube videos or Bilibili videos, which the system downloads locally before starting. Once material is ingested the pipeline structures it, extracts keywords, grounds the content, runs literature research around the extracted topics, synthesises the findings and exports the result in several document formats. Several controls shape a run. Research depth is selectable as simple, medium or complex, which trades report thoroughness against time and token spend. Multi-topic execution detects that a single meeting covers several distinct subjects and generates an independent report for each one in parallel, so dense group discussions are not flattened into one summary. A review stage sends the draft through a bounded review and rewrite loop driven by more than one model, so obvious quality problems are caught before delivery. The skill-driven design keeps the researcher behaviour in a catalogue of skills rather than in one monolithic prompt, and a skill evolution feature records user feedback as derived, selectable versions of a skill so the pipeline gradually adapts to how a particular user works. The repository documents the framework, ships a showcase of five worked cases spanning meetings, documents, mixed archives, links and review workflows, and provides a project page and quick start. It requires Python 3.10 or newer and is released under the MIT licence, with English and Chinese documentation. The intended users are researchers, analysts and knowledge workers who regularly need a written report drawn from scattered source material and want the collection, research and writing steps automated end to end.
https://github.com/gaotiexinqu/OneResearchClaw
Also in AI Assistants
HKUDS/DeepTutor
DeepTutor is an AI-powered personalized learning assistant that offers interactive knowledge Q&A, visualization, practice generation, and deep research capabilities to enhance education through a comprehensive and adaptive platform.
agentscope-ai/QwenPaw
QwenPaw is a personal AI assistant framework that provides local or cloud deployment, multi-channel connectivity, skill extensibility, and multi-agent collaboration for enhanced productivity and cr...
mukul975/Anthropic-Cybersecurity-Skills
A comprehensive, open-source library of 754 structured cybersecurity skills for AI agents, mapped across five prominent industry frameworks.
googleworkspace/cli
gws is a command-line tool that dynamically interfaces with Google Workspace APIs (Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin) and includes AI agent skills for automation.
nanocoai/nanoclaw
NanoClaw is a lightweight, secure AI assistant platform that runs agents in isolated containers, providing a customizable alternative to OpenClaw with native Anthropic Claude Code integration and m...
assafelovic/gpt-researcher
GPT Researcher is an autonomous AI agent that conducts deep web and local research to generate detailed, unbiased research reports with citations.
screenpipe/screenpipe
Screenpipe transforms your computer into a personal, local, and private AI that records, searches, and automates based on all your digital activities.