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
OpenRaiser/NanoResearch
NanoResearch is a Python system that automates the full research cycle from a topic statement to a finished LaTeX paper. Its distinguishing claim is that it actually executes computational experiments rather than only generating text: the pipeline writes runnable experiment code, submits training jobs to a local GPU or a SLURM cluster, collects the resulting logs and metrics, and builds every table and figure in the paper from those measured numbers instead of letting the language model invent them. The pipeline has nine stages. IDEATION searches academic literature through OpenAlex and Semantic Scholar, identifies gaps, forms hypotheses and gathers citations. PLANNING converts the idea into a detailed experimental blueprint covering datasets, baselines, metrics and ablations. SETUP prepares the repository, dependencies, models and data. CODING generates a complete experiment project with training scripts, data processing and model definitions. EXECUTION runs the training with automatic retry and debugging. ANALYSIS parses training logs into structured evidence. FIGURE_GEN produces architecture, comparison and ablation figures. WRITING composes the LaTeX manuscript from the evidence and citations, and REVIEW audits each section and revises it. The run can be resumed from any stage after an interruption, and different models can be routed to different stages. Outputs include the compiled PDF, the LaTeX source, a BibTeX file, figures, code and data in a traceable workspace. The command line interface offers both a classic streaming log mode suited to redirection and scripting and a full-screen TUI panel for interactive monitoring, and additional entry points exist for Claude Code and a Feishu bot. There is also an Evo self-evolution pipeline. Documented use cases are rapid prototyping of research ideas, autonomous experimentation, batch benchmark generation, paper drafting and auditing of the research process. Requires Python 3.10 or later.
https://github.com/OpenRaiser/NanoResearch
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.