Repository index
6791 AI, ML and Web3 projects · page 57 of 68
- SKILLS FOR ROS 2 DEVELOPMENT
Agent skill for productive ROS 2 development: step‑by‑step SKILL.md guide covering workspace, nodes, executors, QoS, ros2_control, Nav2, MoveIt 2, real‑time, and deployment. Compatible with Claude Code, Codex, Cursor and Gemini CLI.
- AI Router & Token-Saving Gateway
Single-binary Go router directing Claude Code, Cursor, and Codex across 155 providers with 20-40% token savings.
- PgGraph — Graph DB for Postgres
An open graph database on top of your existing Postgres. Written in Rust.
- HERMES CN DESKTOP AI AGENT
Desktop Hermes Agent CN app built for Windows‑first using Tauri, TypeScript, and Rust. Its isolated core provides secure LLM interaction.
- AI AGENTS IN KUBERNETES
Agyn — an open-source runtime that moves AI agents into company infrastructure with corporate controls.
- K8SSANDRA OPERATOR – EASY INTEGRATION
Simplifies managing Cassandra in Kubernetes, providing automatic installation, configuration, and updates. Developed in Go.
- MEDICAL_IMAGE_ANALYSIS - AI ANALYSIS OF MEDICAL IMAGES
The project uses foundation models for medical image analysis, providing high accuracy and speed of diagnosis.
- codex-bridge - Generate Images and Agents
Generate images via GPT‑Image‑2 and launch GPT‑5 sub‑agents in Claude Code, using only the Codex CLI login — no OpenAI key needed.
- TS-BENCH: AI AGENTS BENCHMARK
CLI tool for comparing the performance of AI agents in TypeScript tasks.
- COLLECTION OF CSS SKILLS FOR AGENTS
cc-skills is a collection of ready-made CSS components implementing agentic skills for working with Claude Code and other LLMs. The project simplifies creating interactive agent interfaces, ensuring compatibility with the antigravity framework and fast hot-reload.
- DOBERMAN-CORE — PROTECTION FOR AI AGENTS
Doberman-Core intercepts every input, output, and tool call during AI-agent operation, blocking unsafe actions. It works as middleware, checking authorization and applying guardrails without modifying agent code.
- PLATE AI TEMPLATE FOR EDITOR
Plate AI editor template on React 19, Next.js 16, Tailwind 4 and MCP. Includes TypeScript, ready integration of shadcn-ui and Radix UI for quick start. Allows customizing the toolbar and saving content to any storage.
- MANAGE AI AGENTS IN TMUX
ccmux lets you run all your AI‑coding agents inside tmux, quickly switch to the one that needs you and move work between them. Create separate worktree sessions for each agent and pass tasks without extra switching.
- VIBEX — AGENTS FOR YOUR CODE
Vibex is a desktop and mobile workspace for AI agents. Supports Codex, Claude Code, OpenCode and dozens more via ACP. Full control from prompt to commit in Rust/GPUI.
- SAVE TOKENS IN CLI
Local CLI optimaizr finds wasted tokens in Claude Code, Codex, opencode and your API calls. Analyzes spending and shows where money is lost. Supports TypeScript projects and works offline.
- JAT: FIRST AGENT IDE
The first agent IDE with a visual panel: live sessions, tasks, code editor, and terminal. Parallel workflows and auto-rules.
- CLI-Anything-WEB: CLI From Any Site
Claude Code plugin that generates production-ready Python CLI for any web app. Already 20+ ready-made tools.
- HUMAN AND AI: COLLABORATIVE SYSTEMS
Overview of LLM‑supported human‑agent interaction systems. Complete list of resources and practical guides.
- SCALABLE VECTOR SEARCH
C++ library for fast and scalable search over high‑dimensional vectors. Supports approximate search with configurable metrics.
- PORTAINER MCP — OFFICIAL PYTHON SERVER
Official Portainer MCP server in Python — simplifies container management and orchestration via MCP API.
- J-WASH: LLM TOOL
Tool for manual alignment of large language models using Jacobian Lens, with results exported.
- SELF-HOSTED CODEX GATEWAY FOR TEAMS
codex-pooler is a self‑hosted Codex gateway built with Elixir that lets you run your own AI agent for code completion. It integrates with Aider, Cline, Continue and Cursor through a single API gateway.
- VSCODE FOR 1C: PLATFORM TOOLS
Extension for VS Code (Cursor, Windsurf, VSCodium) supports configuration projects, 1C:EDT and OneScript, metadata work, vanessa‑runner commands, tests and debugging, and also integrates MCP for AI agents.
- LIGHTWEIGHT MCP SERVER FOR MACOS
Lightweight MCP server in Python that lets you control macOS applications and GUI via the Model Control Protocol. Minimal dependencies, fast startup, and support for automation scripts.
- ONE API FOR 100+ MODELS
Linten is an open-source AI gateway with a single OpenAI-compatible API for 100+ models. Supports virtual keys, spend tracking, routing, and guardrails. Self-hosted deployment.
- ENVOY: Joint Data Storage
A distributed state store for AI agents, sessions, machines, and organizations in a single location.
- LPM - Quick Start AI Workspaces
Start, stop, and duplicate dev projects with one click. Perfect for Claude Code, Codex, and other AI agents. ⭐ 241
- LUCARNA MANAGE CODE ANYWHERE
Receive notifications, approve changes, and keep working with Codex, Pi, or Claude anywhere — via Telegram, WeChat, or 飞书, without a single hook.
- CONTRIB AI: AUTONOMOUS AGENT
An autonomous AI agent written in Rust searches repositories, analyzes code, generates fixes, and submits PRs.
- Cognitive runtime for AI agents
Recursive evidence-gated runtime for memory-native AI agents with hybrid search, temporal reasoning, and asynchronous learning.
- Local AI roleplay app
Open Dungeon lets you generate stories and inline images entirely on your computer, using Gemma 4 QAT via Ollama (and others) + FLUX, with no accounts or API keys.
- AI BUILDS AUTOMATION
MCP server for creating n8n workflows in natural language via Claude AI and Cursor IDE. 17 tools, multi-instance support.
- DSPY.RB: Ruby for AI
dspy.rb is a Ruby framework that lets you program language models instead of writing prompts. It simplifies creating AI agents and integrating with LLMs.
- LOGICRAG: INDUSTRIAL AI
The open-source LogicRAG project presented at AAAI'26 implements an advanced RAG approach in Python.
- PHAROS: LOCAL AI RAG
Local agentic RAG system for ingesting documents of multiple formats, hybrid search, and corporate access control.
- Doubao Work Guide
Practical guide to using Doubao: step‑by‑step tutorials, real‑world tasks, skill set, connectors, automation, and multi‑agent workflows.
- PRECISE GATEWAY FOR AI TOOLS
Local MCP gateway provides a single port for all tools and AI clients. It enables lazy discovery with ~90% token savings, verifies tool integrity and quarantines suspicious ones, and stores secrets in the system keychain.
- ZJT AI DRAMA GENERATOR
ZJT is an open-source platform on Python that uses AI to automatically create short dramas. From script and storyboard to video synthesis — the entire process is hands-free. It supports Docker and a multi-agent architecture.
- REGEXPU: UNICODE TRANSPILER
Regexpu converts modern Unicode regular expressions ES2015 into ES5‑compatible code. It allows using Unicode properties \p{...} in old browsers without polyfills. Generated code preserves semantics and works everywhere.
- HERMES LIFE OS AGENT
Personal OS agent studies you, detects life patterns and gets smarter daily thanks to memory, cron‑scheduler and RL Atropos. Written in Python, uses Claude and Anthropic, supports CLI and tracks habits and health.
- GOOGLE NOTEBOOKLM OVER MCP + API
Wrapper for Google NotebookLM via MCP with local REST API. Citation-backed answers, audio/video/content generation, multi-account rotation. Integrates with Claude Code, Cursor, n8n, Zapier.
- FREE CODING MODELS WITHOUT KEYS
bansos-router unites free coding models in one local endpoint. No API keys — just connect and let neural nets write code.
- Inference Engine for Cybersecurity
High-performance inference engine in Rust with safe memory handling for cybersecurity tasks.
- YourMemory - AI Memory with Forgetting
Agentic AI memory accounting for Ebbinghaus forgetting curve. On LoCoMo it gives +16pp better recall than Mem0.
- QVAC Local AI SDK
QVAC lets you run LLM, speech recognition, and translation locally on all platforms — from PC to smartphone.
- AGENT-PULSE AI TRENDS REAL TIME
Agent‑Pulse gathers evidence‑based data on the AI industry: daily trend updates, source updates, and weekly briefs for decisions.
- CLAUDE CODE GPT-5 CODING PROXY
Run the Anthropic Claude Code CLI via a local LiteLLM proxy, using GPT-5 and other OpenAI models.
- MAUI LABS: NEW TOOLS
Experimental toolkits for .NET MAUI that accelerate cross‑platform app development.
- CURATOR LIST OF AI AGENTS
Collection of resources on AI agent evolution, their memory, multi-agent architectures, and self-improvement. Includes links to frameworks, protocols, and JavaScript code examples. 201 stars on GitHub.
- GUIDE TO AI ARCHITECTURE
awesome-ai-architect — curated guide list blending AI engineering with solution architecture. Speeds junior‑to‑senior AI‑architect growth via clear roadmaps, templates, interview prep. 200+ stars validate its utility.
- AI STORYBOOK STORY GENERATOR
Story-ui is an AI‑powered story generator for Storybook that works with any framework, design system and LLM provider. Written in TypeScript, it instantly creates ready‑to‑use MDX files for components.
- MINIMAL BOX FOR AGENTS
Run the AI agent in an isolated Minimal box on your PC. Build and execute code without risk to the system.
- AGENTIC AI SEARCH PLATFORM
ansvisor — open-source platform for agentic AI search. Tracks visibility across ChatGPT, Claude, Gemini, Perplexity and Copilot. Agents turn signals into prioritized actions and drafted fixes.
- PIE — MODEL SERVING ON RUST
Programmable engine for high-performance LLM and diffusion model serving. Written in Rust, supports batching, KV caching, and dynamic adapter loading.
- AI PET ON YOUR SCREEN
Roamies are desktop pets with AI living on your screen. They remember promises, remind you of tasks, and point at important things. Work on macOS and Windows with any AI provider.
- AGENT SKILL FOR COMPOSING MUSIC NOTE BY NOTE
A skill for AI agents that writes original instrumental music note by note, then performs, mixes, and masters it on free sampled instruments and synthesizers. Outputs audio, MIDI, stems, and a project file for editing.
- OPUS Quality, SONNET Price
A project to directly build a cost-effective AI operations model with Claude Code. It achieves premium quality at low cost.
- BITROUTER - ACCELERATE AGENT LOOPS
BitRouter is an open gateway and router for LLM agents in Rust, optimizing any workflows and compatible with any models.
- AI AGENT CODE TEMPLATE
TypeScript template for Claude Code with sub-agent workflow and automatic quality checks.
- UNIVERSAL MCP SERVER FOR THE UNSPLASH
MCP server for searching Unsplash images via a simple HTTP API(REST). Supports filtering by image keywords, orientation, and result count, returning URLs and metadata in JSON format.
- GO AI SDK: UNIFIED API
Go AI SDK provides a unified interface for over 21 LLM providers, including OpenAI, Anthropic, and Azure. It supports streaming generation, structured JSON output, and Model Context Protocol, using only the Go standard library.
- AI READY CODE: AGENT SKILL
The ai-ready project analyzes your repository and generates the configuration needed for AI agents: AGENTS.md, Copilot instructions, CI‑pipeline, and issue templates. Supports Claude Code, GitHub Copilot, Codex, and Cursor.
- ZOTSEEK AI SEARCH IN ZOTERO
ZotSeek adds semantic search to your Zotero library using vector embeddings. The built-in MCP server lets you connect Claude Code and Codex as AI agents for meaning‑based queries. Everything runs completely locally, with no data sent over the network.
- FIRSTCODER: LOCAL AI AGENT FOR CODE
FirstCoder — open-source local coding agent in Python. Useful enough to run, small enough to read end to end, and structured enough to learn from. A practical reference when building your own agent.
- SELF-EVOLVING INFRASTRUCTURE FOR PHYSICAL AI
rosclaw — runtime for embedding AI agents into robot bodies. Supports e-URDF, safety sandbox, capability routing, praxis capture, physical memory, and skill evolution. 202 stars on GitHub.
- LLM Bug-Sweeping Benchmark
A Python benchmark that measures how many bugs LLMs can detect and fix across large codebases.
- AI-powered reverse engineering harness
BINNY lets you run any LLM or local model as an agent for binary analysis, providing a Go‑based harness to automate reverse‑engineering tasks.
- CATALOG OF MCP SERVERS FOR 1C
List of ready MCP servers simplifying AI integration with 1C:Enterprise. Enables quick model connection to configurations via standard API. Supports BSL extensions and usage examples.
- RED-TEAMING AI AGENTS IN PYTHON
Humanbound — adversarial testing engine, SDK, and CLI for AI agents. Runs locally or via Humanbound Platform. 218 stars on GitHub.
- YOUR FINANCIAL TRACKER MCP
Self-hosted budget tracker with bank sync, multi-currency, and investments. Built-in MCP server lets you manage finances via Claude and ChatGPT. Full data control without clouds.
- NON-LINEAR AI AGENT
PiX creates a non-linear AI agent workflow. Session as a tree: branch anytime, context follows the branch.
- ADHD — Skill for Coding Agents
Tree of thoughts with dead‑end branch pruning. Parallel reasoning in multiple cognitive frameworks built on Claude Agent SDK.
- AnyKB: Private RAG Agent
AnyKB is a private knowledge base with Retrieval‑Augmented Generation support and a transparent agent that explains each step of its reasoning.
- AI ADVISOR FOR TRADERS
Claude-powered system for advising options traders. 238⭐ on GitHub.
- AI Team for Code Review
Multi-agent AI system simulating an engineering team for automated code review with agent discussions.
- GPT-ALL-STAR — AI TEAM WRITES CODE
AI tool for generating web applications from scratch. Multiple autonomous agents work together like a development team.
- BEACON-SKILL: AGENT PINGS
Library for exchanging messages between AI agents with support for RTC values and UDP bus. Easy integration into multi-agent systems.
- SERVICENOW MCP: AI TOOL
An open TypeScript server with 450+ tools and 26 AI capabilities for Claude, ChatGPT, and others, supporting stdio, SSE, HTTP, and A2A.
- PULSAR — ULTRAFAST MOE INFERENCE
Pulsar — an SSD-streaming engine for giant MoE models on Rust+CUDA.
- Mobile Dev Codex Plugin
Adds Codex integration for Android and iOS development, providing code generation, refactoring, and debugging assistance within IDEs.
- AMD Strix Halo Inference Engine
Kyojin runs ExLlamaV3 on AMD Strix Halo (ROCm gfx1151) to execute 300B‑parameter Mixture‑of‑Experts models on a single 128 GB mini PC.
- Anima Reference Image Adapter
ComfyUI node for character and style transfer from reference images to Anima using offset-RoPE and LoRA.
- AI CODING ON ANDROID NO PC
and-code is a native Android app for running AI coding agents locally on device. Works without terminal or PC, supports Claude Code and other agents.
- Light fine-tuning of LLM assistants
Zero-friction fine-tuning of any LLMs for Claude Code, Gemini CLI, and ACP agents: from environment setup to training (LoRA, SFT, DPO, GRPO) with NVIDIA and Apple Silicon support.
- TERRAPOD: FREE TERRAFORM ALTERNATIVE
Terrapod is an open-source replacement for Terraform Enterprise written in Python, enabling infrastructure-as-code management without licenses.
- theDAW: AI Music Studio
theDAW combines generation, editing, mixing, and live visuals in a unified environment for creating music with AI. The project is designed for producers, DJs, and visual artists.
- MAESTRO: Agent Audit for Code
Unified task system and decision log for Claude Code, Codex, and CI. Full traceability of agent work.
- PERSISTENT MEMORY FOR AI
Project persistent-ai-memory creates a local embedding store for AI assistants, LLMs, and GitHub Copilot inside VS Code. It retains context between sessions, enabling the model to recall past dialogues and code.
- CONNECT CLAUDE AND CHATGPT TO CURSOR
The ungate project lets you connect your Claude and ChatGPT subscriptions to the Cursor editor, eliminating the need to buy separate API‑tokens. The extension works with TypeScript and already has 204 stars on GitHub.
- MCP SERVER FOR APPLE
MCP server provides native macOS integration with Apple Reminders and Calendar via EventKit. It lets you create, read, and update reminders and events directly from the model context without extra dependencies.
- AI Marketing Agent Skills
Bilingual prompt library for AI assistants covering Meta, Google, TikTok ads, UGC analysis, cold outreach, and email marketing campaigns.
- UNBIASEDSTRATA — CLEAN STRATA WITHOUT BLOAT
Simplified Strata fork for LLM. Clone, rsync to prod, compile — done. No extra dependencies or configs.
- CODEINDEX DEPENDENCY ANALYSIS
Dependency analyzer with blast-radius assessment to accelerate AI development.
- Tessera Organize AI Sessions
Tessera combines projects, tabs, panels, and Git worktrees into a single environment for AI coding. Manage sessions without unnecessary switching.
- LLAMA_CPP.RB Ruby Bindings
Ruby wrapper for llama.cpp, allowing you to run large language models directly from Ruby code.
- arksim - DETECT AGENT ERRORS
arksim helps developers find errors in AI agents before they reach real users, saving time and improving reliability.
- TRANSFORMER-TRICKS - ACCELERATING TRANSFORMERS
A collection of techniques and utilities for accelerating transformers: attention optimization, quantization, and caching of computations.
- MEDUSA AGENT: BEST PRACTICES
A set of skills and commands for the Medusa agent that helps follow best practices and simplify development.
- QUANTIFIED-SELF - UNITE SPORT DATA
The quantified-self project collects data from Garmin, Suunto, and Coros into a single TypeScript app for convenient analysis of your workouts.
- HOMELAB MONITOR DASHBOARD
Plug‑and‑play dashboard for homelab in a single container: monitoring GPU, local‑AI VRAM, Docker, systemd and host health. Built‑in read‑only MCP server gives AI agents access to metrics.