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
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.
agent0ai/agent-zero
Agent Zero is a dynamic, customizable AI framework that acts as a personal assistant capable of learning, creating tools, and cooperating with multiple agents to accomplish diverse tasks.
leon-ai/leon
Leon is an open-source personal AI assistant project undergoing a major architectural rewrite to enhance its capabilities with tools, context, memory, and agentic execution.
XiaomiMiMo/MiMo-Code
MiMoCode is a terminal-native AI coding assistant that helps developers read, write, and manage code, offering persistent memory, autonomous agents, and self-improvement capabilities.
cloudflare/moltworker
Moltworker is a proof-of-concept project that runs the OpenClaw personal AI assistant within Cloudflare Workers using sandbox containers, providing secure, multi-channel AI assistant deployment with persistent storage and managed infrastructure.
chuspeeism/dashi-ppt-skill
AI agent skill that turns documents into browser-editable HTML slide decks across 12 visual themes, with in-page editing controls and export to HTML, PDF and editable PPTX.
DearVa/Everywhere
Everywhere is a context-aware AI desktop assistant that integrates multiple large language models and tools to provide seamless, intelligent help directly on your screen without switching apps.
ghuntley/how-to-build-a-coding-agent
A step-by-step workshop to build an AI-powered coding assistant that evolves from a basic chatbot to a multi-functional developer tool using the Anthropic Claude API.
volcengine/MineContext
MineContext is a proactive context-aware AI partner that collects and processes multimodal digital context to deliver insights, summaries, and to-dos, enhancing productivity and creativity while prioritizing user privacy.
EvoScientist/EvoScientist
Self-evolving multi-agent research system built on DeepAgents, with six specialised sub-agents and a knowledge-graph memory, exposed through a web UI, a terminal interface and mobile.
eugeniughelbur/obsidian-second-brain
Cross-CLI skill package that turns an Obsidian vault into an AI-maintained second brain, with more than 40 slash commands for capture, recall, synthesis and scheduled vault upkeep.
nickjvandyke/opencode.nvim
opencode.nvim integrates the opencode AI assistant into Neovim to provide context-aware code research, reviews, and requests directly within the editor.
superagent-ai/grok-cli
Grok CLI is an open-source conversational AI command-line tool that integrates Grok AI to provide intelligent file operations, shell command execution, and extensible tool usage directly within the terminal.
Mirix-AI/MIRIX
Mirix is a multi-agent personal assistant that captures and consolidates on-screen activities into structured memories, providing intelligent, privacy-focused, and adaptive user interaction through advanced multi-modal data processing and search capabilities.
yilewang/llm-for-zotero
A Zotero plugin that puts an LLM research agent inside the reader, allowing grounded chat with PDFs, figure and screenshot analysis, cited answers and library-wide agent operations over the reference collection.
K-Dense-AI/claude-scientific-writer
Deep research and writing tool that searches literature in real time and produces publication-ready papers, reports, posters, grant proposals and reviews, usable as a Claude Code plugin, Python package or CLI.
MLSysOps/MLE-agent
MLE-Agent is an intelligent AI assistant designed to autonomously support machine learning engineers and researchers by building baselines, participating in Kaggle competitions, integrating research resources, and providing smart debugging and personalized project assistance.
PaperDebugger/paperdebugger
Chrome extension and Go backend that adds a multi-agent academic writing assistant to Overleaf, running research, critique and revision passes over a LaTeX project without modifying it.
SakanaAI/evolutionary-model-merge
A repository by SakanaAI for evolutionary optimization of model merging recipes, providing models, code, and resources to improve and evaluate merged language and vision-language models, particularly for Japanese tasks.
OpenRaiser/NanoResearch
End-to-end autonomous research engine that takes a topic through a nine-stage pipeline, runs real GPU training jobs locally or on SLURM, and emits a LaTeX paper backed by the measured results.
firecrawl/open-scouts
Next.js and Supabase application for creating scouts, scheduled AI agents that repeatedly search and scrape the web with Firecrawl and OpenAI and email the user when they find matching information.
Xiangyue-Zhang/auto-deep-researcher-24x7
Autonomous research agent that plans, launches and monitors deep learning experiments around the clock using a leader-worker loop, a persistent experiment ledger and safety gates.
KwaiKEG/KwaiAgents
KwaiAgents is an open-source generalized information-seeking agent system leveraging Large Language Models with enhanced agent capabilities, datasets, benchmarks, and deployment tools.
Spark-To-Paper-Skills/paperjury
PaperJury is a Claude Code skill that stress-tests a research paper before submission through a review, verdict, revision and verification loop, with deterministic code controlling state, voting and patch application.
microsoft/ToRA
ToRA is a series of tool-integrated reasoning agents developed by Microsoft that combine large language models with external computational tools to solve challenging mathematical reasoning problems with high accuracy.
vakovalskii/sgr-deep-research
Open-source Python framework for Schema-Guided Reasoning research agents, shipping deep-research implementations, an OpenAI-compatible REST API, streaming and CLI tooling.
principia-ai/WriteHERE
WriteHERE is an open-source AI writing framework that uses recursive planning, heterogeneous task integration, and dynamic adaptation to enhance long-form writing for fiction and technical reports.
kardolus/chatgpt-cli
Multi-provider command line client for LLMs written in Go, offering threaded chat, prompt files, image and audio input, MCP tool calls and an experimental ReAct and Plan/Execute agent mode with budget and policy limits.
ur-whitelab/chemcrow-public
ChemCrow is an open-source package that integrates large language models with specialized chemical tools and databases to solve complex chemistry tasks such as retrosynthesis, reaction prediction, and molecular property analysis.
zamalali/DeepGit
DeepGit is a LangGraph deep research agent that searches, filters and ranks GitHub repositories for a natural language query using ColBERT retrieval, cross-encoder reranking and hardware-aware filtering.
Melmaphother/Science-Star
Science-Star is an open Python platform for building and experimenting with scientific AI agents, built on a ReAct loop with planning, memory and reflection plus HLE and GAIA benchmark harnesses.
existence-master/Sentient
Sentient is a proactive and personalized AI companion that integrates with multiple platforms to provide context-aware assistance, voice interaction, and autonomous task execution while prioritizing user privacy and transparency.
infiolab/infio-copilot
Infio-Copilot is a Cursor-inspired AI assistant plugin for Obsidian offering autocomplete, inline editing, semantic vault search, custom agent modes and MCP integrations over a user's notes.
Azzedde/brainstormers
Next.js web application that runs six structured brainstorming methods as multi-step LLM prompting pipelines over OpenAI models, returning streamed, organised idea trees.
renee-jia/scholar-loop
ScholarLoop is an autonomous multi-agent research loop that reads arXiv and OpenAlex literature, proposes experiments, runs real PyTorch training runs against a frozen metric, distills lessons and drafts a peer-reviewed write-up.
gaotiexinqu/OneResearchClaw
Autonomous research pipeline that turns meeting recordings, documents, spreadsheets, slides, mixed archives and arXiv or video links into structured research reports through grounding, literature search and review loops.
Azure-Samples/contoso-creative-writer
Contoso Creative Writer is a multi-agent AI solution using Azure OpenAI and related Azure services to help users write well-researched, product-specific articles based on user topics and instructions.
ScarletPan/awesome-autonomous-gpt
A curated repository compiling outstanding projects, tools, applications, benchmarks, and research related to autonomous AI agents based on GPT and large language models, serving as a comprehensive resource for the AI community.
tsinghua-fib-lab/AgentSquare
AgentSquare is a research project providing an automatic search platform for designing modular large language model agents, supporting multiple tasks and encouraging community contributions.
chadbrewbaker/ChadGPT
ChadGPT is a comprehensive project focused on understanding, self-hosting, and applying large language models using open-source tools and exploring future AI and Linux system integrations.