Repository index
6792 AI, ML and Web3 projects · page 15 of 68
- Multi-agent CLI bridge
CLI command to manage multi-agent work teams based on Claude, Codex, Gemini, and other AI models with project memory and tmux oversight.
- MAESTRO - Simplifying Model Fine-tuning
The project simplifies fine-tuning of multimodal models PaliGemma 2, Florence‑2, and Qwen2.5‑VL, saving developers time and resources.
- MCP Server for arXiv
Model Context Protocol server for searching and analyzing scientific articles from arXiv.
- Claude Code Framework
Claude Code Framework saves time by eliminating constant requests like 'please act like a senior engineer'.
- Serenity – Simplicity of Business Apps
ASP.NET Core MVC + TypeScript – a framework for quickly creating scalable business applications without unnecessary complexity.
- E-book Translation with Fast Results
A Calibre plugin translates e-books into the selected language, preserving formatting and structure.
- TanStack AI SDK
🤖 Type-safe AI SDK for TypeScript supporting streaming chat, tool calls, agents, and multimodal applications with OpenAI, Anthropic, Gemini, React, Vue, Svelte, and Solid.
- XTRUING: PERSONALIZE YOUR LLM
xTuring simplifies creating and personalizing your own LLMs: from data preparation to fine‑tuning. The tool supports adapters, ready‑made pipelines and model export. Join our Discord: https://discord.gg/TgHXuSJEk6
- Personal AI Agent in Rust
Moltis is a secure personal agent server in Rust, running as a single binary. It provides isolated execution, supports multiple LLM providers, voice, memory, and integrations with Telegram, WhatsApp, Discord, Teams, and other MCP tools.
- COMMAND CENTER FOR AI CODING
CodeNomad is a desktop app for managing AI agents. Unifies context, tools, and LLMs in one interface. 2657 stars on GitHub.
- Generative AI Roadmap Projects
A collection of generative AI resources: roadmap, projects, interview and coding preparation.
- OMAGENT: THE MULTIMODAL AGENT
OmAgent — Python framework for multimodal agents on Gemini, GPT-4 and other LLMs. Enables rapid prototyping and deployment via Gradio, supports RAG and rapid chatbot templates.
- Pixel to Motion
The project uses AI to convert raster logos into smooth SVG animations, creating HTML demos, GIF and video previews, and performing motion-quality assessment.
- Flutter LLM Chat Client
A mobile and desktop client for communicating with LLMs. Supports platforms, focused on flexibility and cross-platform compatibility.
- OMNIGRAPH GRAPH FOR LAKEHOUSE
Omnigraph is a native graph engine for lakehouse that lets you work with data like a Git repository, supporting branching, merging, and change history.
- GENTLE SHELL AI ARCHITECT
Gentle‑shell turns Raspberry Pi into a powerful harness for senior architects: SDD/OpenSpec, subagents, strict TDD evidence, and review guardrails. It automatically discovers agent skills and ensures repeatable code quality.
- DeepSeek GUI Workspace
Development environment for AI agents for DeepSeek models with Code and Claw modes, allowing you to write, debug, and visually assemble workflows.
- Reversible Agent Runtime Substrate
Turns agent execution into reversible Git-like traces enabling meta-agents to observe, fork, replay, and revert runs with 5x faster copy-on-write forks and 95% KV-cache reuse.
- Voice Agent Platform
Open Source Voice Agent Platform
- SLACKDUMP - SAVE YOUR SLACK CHATS
Export private and public messages, threads, files, and Slack users without admin rights.
- Local AI Novel Writer
Free, open-source novel writing app with AI-assisted outlining, drafting, and editing. Runs locally with user-configured models.
- AutoCLI: Universal CLI Parser
AutoCLI is a fast and secure command-line tool for retrieving data from more than 55 sites, including social networks and platforms, as well as managing Electron applications and integrating local CLI utilities.
- AI Video Editing Agent
FireRed-OpenStoryline is an AI agent that turns manual video editing into a natural‑language‑driven director. It uses an LLM to plan and coordinate editing tools, enabling transparent human‑AI collaboration.
- OPEN .NET FOR OPENAI
Official .NET library for the OpenAI API: easy integration of GPT models into your apps.
- NotFair: Claude Code Ads SEO
Open library of Claude Code skills for SEO, GEO, Google Ads and Meta Ads — tools for automating digital marketing with open source.
- DELEGATE SKILLS: SEAMLESS INTEGRATOR
Tool that turns OpenAI Codex CLI into a background executor: plan, check diff, commit autonomously.
- French Bureaucracy with AI
Python library with skills for AI agents: accounting, notary, and more. Simplifying French bureaucracy.
- AI-native state store for agents
The AI-native state store for agents. MySQL-compatible, embedded or server, hybrid vector + full-text search, COW sandboxes (FORK/MERGE).
- AUTOMATED LIST OF JEV PROJECTS
List of open projects, integrations, and discussions built on Jev — the type‑safe AI model for reliable decisions. 202★, Python, tags awesome, jev, llm.
- GRIPTAPE — AI AGENTS ON PYTHON
Modular framework for creating AI agents and workflows with chain-of-thought reasoning, tools, and memory.
- OPEN SPEC FOR OPENAI API
OpenAPI specification enabling easy integration and documentation of OpenAI model calls.
- MOBILE-USE: AI AGENTS CONTROL APPS
The mobile-use project allows AI agents to interact with real Android and iOS applications like a human.
- CODEISLAND - AI IN MAC NOTCH
Quick AI status panel in real time on MacBook notch with support for 13 tools and Companion for iPhone & Apple Watch.
- Local Claude Code
Run Claude Code entirely on-device with Apple Silicon using an MLX-native server compatible with the Anthropic API. Supports local Qwen 3.5 122B, Llama 3.3 70B, and Gemma 4 31B models without network access.
- HCAPTCHA-CHALLANGER - BYPASSING HCAPTCHA WITH AI
The project uses a multimodal LLM to automatically solve hCaptcha challenges, bypassing protection without manual intervention.
- DOCMD — DOCUMENTATION IN SECONDS
Create production-ready documentation from Markdown in seconds. No React, no extra — just content.
- NITROSTACK: FULL AI STACK
A full-featured TypeScript framework for creating, testing, and deploying MCP servers and AI applications.
- DATA TRANSMISSION BRIDGE
Proxy server connecting Streamable HTTP and stdio MCP transports. Simplifies data exchange protocol integration.
- OpenUsage — Subscription Management
Track your subscriptions for free and without tracking. A simple tool for expense control.
- Accelerate Deep Analysis
The project provides a structured deep research skill for Claude Code, Open Code, and Codex with human-in-the-loop control.
- Warp streaming output
Warp enables inference of the Kimi K3 model with 2.78 trillion parameters, streaming activated weights directly from NVMe, bypassing RAM limitations. The engine is written in pure C without external dependencies and easily embeds into projects.
- Claude Code for Terminal
An AI agent in the terminal that understands your code, accelerates development by automating routine tasks, explaining complex sections, and managing Git operations through natural language.
- AWESOME SEEDANCE: PROMPT-LIBRARY AI‑VIDEO
Seedance 2.5/2.0 prompt library with 463 verified cases, links to posts and 264 cross‑model retest runs. Includes 25 ready‑to‑use templates and 60 installable AI‑video Skills for start generation.
- RIPWIRE: CODE MAP FOR AI
ripwire — zero‑dependency C++23 CLI + MCP server that in seconds builds a deterministic ranked map of repo code, computes blast radius and suggests the set of tests affected by changes. It also shows quality deltas of complexity and coverage between commits, saving ~5% of tokens compared to grep‑reading.
- Orca — IDE for agents
The idea of parallel AI agents: control a fleet of any agents with a subscription. Available on desktop and mobile devices.
- HOLMESGPT: AI AGENT FOR SRE
SRE agent on Python for automating monitoring, log analysis, and fast incident response.
- OSSINSIGHT: OVER 10B DATA POINTS
Analysis, comparison, and trends of open source projects using natural language. Powered by LLM.
- NODTERM - Multiple Nodes in Terminal
Manage AI agents in tmux-supported terminals and parallel sessions as draggable nodes on an infinite canvas.
- SHIPPIE — CODE REVIEW AGENT 🚢
Extensible AI agent for code review and QA in TypeScript. 2377 stars on GitHub!
- WORKFLOW SDK: DURABLE TYPESCRIPT FUNCTIONS
SDK for building durable TypeScript functions with persistence, retries, and observability. Runs locally and on Vercel without infrastructure management.
- PENECHO: AI Canvas for Creativity
Penecho is a collaborative canvas for hand‑drawing, equations, and diagrams, enhanced with AI for spatial reasoning.
- WANWU - AI Agents Platform
Wanwu platform from China Unicom is an enterprise solution for creating AI agents, workflows, and RAG with model management.
- COLLAB-PUB: BUILD WITH AGENTS
Platform for collaborative project creation with AI agents in TypeScript. Already 2.5k stars on GitHub!
- oooSplat: 3D Splats
A local desktop TypeScript app that converts images and videos into 3D Gaussian Splats with a single click. Supports instant preview and export to popular formats.
- HAMILTON - MODULAR DATAFLOW
Apache Hamilton simplifies creating testable, self-documenting data pipelines with lineage tracking.
- OPENLIT AI FUTURE PLATFORM
Open source platform for AI Engineering: OpenTelemetry LLM, GPU monitoring, guardrails and prompt management. Integration with 50+ providers.
- WEBCODEX: AI AGENTS ON YOUR OWN MACHINES
Give cloud AI agents a real development environment on your own machines. Code execution, file system, terminal — all in your environment.
- GOOGLE WORKSPACE UNDER AI CONTROL
Manage Gmail, Calendar, Docs, Sheets, Drive and other Google Workspace services with AI. ⭐2507 stars!
- PANWATCH: AI AGENT FOR STOCK
PanWatch - self-hosted AI platform for monitoring A-share, HK and US stocks with TradingAgents.On Python 1.8k ★
- Unified Research Workspace
A unified workspace for human-AI research collaboration featuring PDF Q&A with citations, knowledge vault, and writing tools.
- RL FOR LARGE MODELS
Overview of modern reinforcement learning methods for large reasoning models, including theories and practical approaches.
- AGENT-SKILLS: LIBRARY OF SKILLS FOR APIFY
The agent-skills library offers ready-made skills for creating agents on Apify Actor using Python. With over 2.3k stars, MCP integration, and code examples, it simplifies AI-agent development.
- Visualize Tech Stacks from Text
Describe your tech stack in natural language and instantly get a polished architecture diagram using official service logos.
- Smart Code Analyzer
Giancarloerra/SocratiCode provides enterprise-grade codebase analysis with zero configuration, delivering hybrid semantic search, polyglot dependency graphs, and symbol-level impact analysis.
- AGENT-SCAN AI Security Scanner
A security scanner for AI agents, MCP servers, and agent skills. An open-source Python tool.
- AI-Generated Code Films
An AI agent writes scripts, renders frames programmatically, designs audio, and outputs complete MP4 videos.
- AI GENEALOGY EX-USSR ARCHIVES
Skill for AI agents (Codex, Claude Code) for evidence-first genealogy of the former USSR. Processes church books, civil, military, deportation and repression records. Replies in your language.
- Brutal Game Framework
A free, open‑source C# framework that lets developers build games or custom engines with direct Vulkan and native API access, powering Kitten Space Agency and RimWorld’s Waylith engine.
- ChatGPT2API — Compatible Proxy API
Reverse implementation of the ChatGPT protocol, emulating OpenAI API. Supports image generation and working with text models through a unified interface.
- Graphene Anime Layers
Decomposition of anime character images into layers using AI. Accepted to SIGGRAPH 2026.
- Co-creation with AI Agents
Collaborator — a platform for co-creation with AI agents. Turn ideas into reality together with intelligent assistants.
- Story to Handdrawn Video
The project converts Chinese text or a sequence of images into an animated comic‑diary as a silent MP4 file that mimics hand‑drawn drawing.
- Medical AI Skills Library
An open collection of ready-to-use models and tools for applying AI in medicine within the OpenClaw framework. Enables rapid integration of diagnosis, image analysis, and clinical text processing.
- NATIVE LLM SERVER FOR MAC
LLM server compatible with OpenAI+Anthropic, no Python required. Includes MLX Core macOS: chat, agent, and tool calling.
- AWESOME MODEL QUANTIZATION RESOURCES
A curated list of articles, benchmarks, surveys, and tools for neural network quantization. Covers low-bit networks, LLMs, multimodal and generative models, vector and lattice quantization. Supports efficient model deployment.
- WHISPERJAV NOISE-FREE SUBTITLES
Subtitle generator for video based on Qwen3‑ASR, Whisper, and local LLM, noise-resistant and ideal for JAV content.
- BETTER HARNES - MANAGE CODE SCIENTIFICALLY
Boosts the efficiency of agent-based development: best metric, deep analysis, and continuous project improvement.
- Conduit – Mobile AI Window
Native iOS/Android client for Open WebUI with direct connections to OpenAI, Ollama, and OpenRouter, featuring local chats and self‑sufficient Hermes agents.
- AI GENERATES 3D AND VIDEO ON YOUR GPU
Raea is an engine for rendering video, 3D, and games via AI agents. Write tasks in React/TypeScript, your GPU computes. Built with Rust + Bevy.
- BOOTCAMP: MULTIMODAL DATA
The bootcamp project brings together tools for working with unstructured data: reverse image, audio, video, molecular search, and NLP tasks.
- LEADS FROM GOOGLE MAPS NO API
Script extracts leads from Google Maps phones, emails, websites and socials into clean CSV. Runs locally via Claude, no API-key, on your machine.
- YEK - Fast Code Serialization for LLM
Rust utility that turns repository files into text for LLM input. Lightning-fast speed and simplicity.
- OTERM – TERMINAL FOR LLM Cass
Simple LLM client in the terminal: quickly process queries and scripts. In Python, without extra interfaces.
- IMAGE GENERATION REVIEW
A large-scale review of text-to-image generation methods: architectures, models, and approaches — all collected in one repository.
- 12306 MCP: Smart Ticket Search
A server for searching 12306 tickets built on the Model Context Protocol provides fast and accurate train search.
- FULLING: AI Developer Agent
Fulling — AI agent for full-stack development on Next.js, Claude, and shadcn/ui with PostgreSQL DB and deployment to Kubernetes.
- REAGENT: AI RECONSTRUCTS CODE
Reagent uses AI to reconstruct and validate C/C++ code from the binaries. Supports analysis of autonomous agents and integration with Claude, Codex.
- PENTESTAGENT: AI AGENT FOR TESTS
PentestAgent is an AI‑agent framework for black‑box security testing: it supports bug bounty, red‑team, and pentest workflows.
- Claude AI Tracker
A native macOS menu bar app for tracking Claude AI usage limits in real time. Built with Swift and SwiftUI.
- BRIGHTDATA-MCP: SINGLE SOLUTION FOR WEB
Model Context Protocol server for accessing public web data without complex setup.
- AI Agent Session Manager
Unified TUI interface for managing Claude, Gemini, OpenCode, Codex and other AI agent sessions directly from the terminal.
- OPEN LIST OF RESOURCES FOR WHISPER
Awesome-whisper — articles, tutorials, models and tools for OpenAI Whisper. Contains links to models, fine‑tuning guides and integration examples in Python, JS and other stacks. Allows quick finding resources for speech‑to‑text projects.
- AGENTUNIVERSE - MULTI-AGENT FRAMEWORK
Framework for creating multi-agent systems on LLM, written in Python. Simplifies orchestration and extensibility of agents.
- Kritt AI: Vulnerability Detection
Open-source tool for self-hosting that uses AI agents to automatically detect and confirm vulnerabilities in source code.
- UNITING LLM IN LARAVEL..
Prism — a unified facade for working with any LLMs in Laravel. It joins calls to OpenAI, Anthropic Claude and other providers, offering streaming generation, tool use and token caching via simple service.
- AGENT OF EMPIRES — PHONE CONTROL
Control a swarm of code agents via a web interface straight from your phone. tmux + git worktrees out of the box.
- MAI-UI: GUI Agents 2B‑235B
MAI-UI provides fundamental GUI agents ranging from 2 to 235 billion parameters in Jupyter Notebook format for rapid experimentation.
- LCU: CODE FOR ANY HARNESS
LCU extracts Codex Computer Use functionality from the app, enabling integration with any automation system. The Python library supports browser interaction, accessibility, and agent skills.
- Awesome-GraphRAG: Best RAG Resources
A collection of materials on graph RAG: articles, surveys, benchmarks, and open-source projects.
- VIBE-CODING TOOLKIT: AI AGENTS
vibe-coding-toolkit — a battle‑tested set of AI‑coding tools from production: Claude Code plugins, sub‑agent orchestration, quality gates, and ready‑to‑copy prompts. 409 ★, JavaScript.