Repository index
6792 AI, ML and Web3 projects · page 37 of 68
- MASFactory Vibration Multi-Agent
MASFactory is a Python framework for orchestrating multi-agent systems using a graph-centric approach and vibrational modeling.
- TEXT TO GAME WITH AI
GodotMaker — an autonomous pipeline that turns a text description into a ready-made Godot game. 296 stars, runs on Python.
- RATEL SMART MEMORY FOR AGENTS
Ratel is a Rust framework for AI‑agent context engineering: it cuts token usage by ~80% and provides in‑process BM25 plus semantic search without a vector DB.
- LOCKKNIFE ULTIMATE TOOL
LockKnife combines TUI and headless CLI for deep Android research. Powered by Python orchestration and Rust core, it works with AI agents, credential cracking, APK analysis and runtime inspection.
- ORIVEO MULTIMODEL CHAT
Open-source chat client with BYOK for iOS, Android and web. Supports OpenAI, Anthropic, Gemini and other compatible providers, including Ollama, LM Studio, llama.cpp, vLLM. Local-first, self-hosted, no account, AGPL-3.0.
- FINENVS: RL-ENVIRONMENTS OF THE NEXT GENERATION
FineEnvs — Python library for creating and scaling reinforcement learning environments with LLM capabilities. It simplifies LLM-agent integration, supports training via GRPO and PPO, and is compatible with Hugging Face and OpenEnv.
- PIXEL-ART OFFICE FOR AI AGENTS
Pixtuoid — a terminal application in Rust that turns AI-agent work into a pixel‑art office. Integrates with Claude Code and Codex, allowing agents to write and test code directly in a virtual workspace.
- Auto Identity Remove
Automatic removal of personal data from 30+ people-search sites on a schedule.
- WEAVE - FUTURE PLATFORM
Weave is a high-performance platform for building applications with deep AI integration: LLMs, chatbots, RAG, and autonomous agents.
- BUG HUNTER AI AGENT
An autonomous agent searches for vulnerabilities and bugs in the code, then fixes them in a safe branch.
- SpringNote: Light Notes with AI
SpringNote is a tool for quick notes where AI automatically collects and organizes your thoughts.
- AINL TURNS AI INTO A WORKER
AINL turns a regular chatbot into a structured AI worker, enabling multi-step workflows with memory, tools, and validation.
- VMLX - NEXT-GEN MLX MODELS
Ultra-fast compressed MLX models with two-level cache, hybrid scheduler, and continuous batching.
- MisakaNet: AI Agent Library
Python micro-lessons library for AI agents: exchange proven debugging experience via git. No dependencies, stdlib only.
- PAXML - AMAZING JAX FRAMEWORK
Pax is a JAX framework for training large-scale models with high FLOP utilization and flexible parallelization.
- LLM-API-KEY-PROXY - UNIVERSAL LLM GATEWAY
A unified API for accessing any LLM with OpenAI/Anthropic compatibility, load balancing, and request translation.
- AGENTIC AI LANDSCAPE - AGENT MAP
Data and insights on agentic AI systems from Ant Open Source and inclusionAI. 499 stars on GitHub!
- AUTOLITH — SELF‑MODIFYING AI AGENT
Autolith — self‑rewriting AI agent in Common Lisp, changing its code at runtime. It interacts with LLM via API, generates and improves programs, works as a CLI agent and extends via ordinary Lisp libraries.
- REPOSITORY-HARNESS: REPO FOR AGENTS
Turns any repository into a workspace for Claude Code, Codex, Cursor and other AI agents. 559 ⭐
- GISSELLE: AI APP BUILDER OPEN
Create AI applications without code: Giselle is an open TypeScript framework for rapid prototyping.
- Awesome LLM Resources List
A curated list of the best articles, tutorials, and tools for hands-on work with large language models.
- CAURA Shared AI Memory
Caura provides managed shared memory for AI agent fleets with multi‑tenant support, trust policies, and an audit trail.
- LOCAL-FIRST INBOX FOR AI AGENTS
pizza-bot is a local-first inbox for long-running AI agents on DeepAgents and LangGraph. Supports human-in-the-loop and runs via Electron. 319 stars on GitHub.
- NIETZSCHEAN DEBUGGER: HEALS YOU
Python CLI tool powered by Claude that doesn't fix bugs but makes you think. Returns a question instead of an answer, developing critical thinking during debugging. 386 stars on GitHub.
- OPEN-SOURCE TASK MANAGER FOR SELF-HOSTING
OpenTodo is an open-source task manager that runs on your own server. Works offline on all devices, supports encryption and import from popular services.
- DEER-WORKFLOW — GRAPH WORKFLOW IN TYPESCRIPT
Open runtime for graph engineering: orchestration in TypeScript, with semantic work delegated to replaceable Agent runtimes.
- CONTROL AI AGENTS FROM YOUR PHONE
omg.dev — remote control for Claude, Codex, Cursor, OpenCode and other AI agents. iOS app lets you launch tasks, read logs and intervene in agent work remotely. 551 stars on GitHub.
- MCO — Multi-Agent Orchestration
A neutral orchestration layer for Claude Code, Codex CLI, Gemini CLI, and other AI agents. 375 stars on GitHub.
- Jarvis Voice Assistant
Local French voice assistant that works with Claude or Ollama models without an internet connection. It controls Hue lighting, OBS, calendar, and browser, makes Twilio calls, and provides an extensible MCP server for adding skills.
- YOUR AI AGENTS IN MESSENGERS
abacusai-bot — 100% free open-source framework for running personal AI agents in Telegram, WhatsApp, and CLI. Written in TypeScript, supports tools, code, and integrations. 253 stars on GitHub.
- AI GAME BREAKDOWN IN C
decomp.wtf - AI agent decompiles your games into C code, byte‑for‑byte identical to the original. Runs locally, without sending data to the network. Uses Claude Code for matching‑decompilation.
- YOUR TEAM OF AI BOTS IN ONE BINARY
Self-hosted solution for AI agent team: spaces, all accounts in one place, task handoffs, approvals and routines. Written in Rust + React. Alternative to Grok Bot, Claude Duet and OpenAI dots.
- VIBECODING WITH CLAUDE CODE
A toolkit for AI development based on PDCA methodology. 555⭐ on GitHub!
- Java AI Resources and Materials
Open repository with materials on Java backend, AI agents, system design, and algorithmic interview preparation.
- CORALLINE — STATUS BAR
Powerlevel10k style for Claude Code: insert one prompt — and the AI will set everything up. 287 ⭐
- TDA: Java Thread Analysis
Analyze Java thread dumps via a convenient GUI or use as an MCP server for integration.
- AMADEUS: AI AGENT FOR DESKTOP
Amadeus is a real‑time multimedia desktop agent built on Python, using CUDA, Electron and GPT‑SoVITS. The project is evolving toward a persistent AI OS interface and already has 203 stars.
- NEW PROJECT TASTECODE
Tastecode — a unified desktop client for coding‑agents, made for creative work. Early beta already available for Windows and macOS.
- CREATE A GAME IN ONE MINUTE WITH AI
Describe an idea in one phrase — the DeepSeek Harness plugin generates code, adds AI art, and deploys to GitHub Pages or Cloudflare in one click. 433 stars on GitHub.
- BELUGA: AI IDE FOR MACOS
Beluga — native AI IDE for macOS with P2P connections. Integrates Claude Code and git worktree for parallel agentic development. TypeScript, 500+ stars on GitHub.
- HERMES PLUGINS: GOAL MANAGEMENT
A set of custom plugins for hermes-agent: goal management, inter-agent bridge, model selection, and cost control.
- MANTIC.SH - AI CODE SEARCH
Structural code search engine tuned for AI agents. TypeScript, 550 stars!
- SDK FOR JAVASCRIPT CHAT PLATFORM
SDK monorepo for integrating AI‑focused messaging: free cloud server, enterprise support, and AI agents.
- CLOUD OPS: AUTONOMOUS BUSINESS OS
Claude‑Ops — a business operating system for Claude Code: 57 skills, 21 agents and a smart daemon. It unifies WhatsApp, Email, Slack, Telegram in a single inbox, performs autonomous PR merges and monitors AWS, Stripe, Shopify, etc.
- SECOND BRAIN - YOUR DIGITAL OS
An agent framework that automates tasks using LLM and file intelligence — 552 stars, Python. Excellent DevTools for cross‑platform automation!
- VSCODE EXTENSION WITH LLM
Connect Claude, Gemini, ChatGPT and other LLMs to GitHub Copilot Chat VS Code via plugin. Quick setup and free models!
- macOS OCR CLI in Swift
A macOS command-line tool that uses Apple Vision for text recognition and creating searchable PDF files. Supports batch image processing and export to various formats.
- LEAN LSP MCP: PROOF REVOLUTION
The project integrates the Lean Theorem Prover with the Language Server Protocol via MCP, providing code completion, proof checking, and interactive code editing.
- CAD2DATA: AUTOMATION OF CONVERSION OF FILES.
The project provides a workflow for AI agents that automates CAD file conversion (.rvt, .ifc, .dwg) using command‑line tools on Windows locally. It enables integrating conversion into LLM and RAG pipelines without manual intervention.
- KOHAKUTERRARIUM AGENT FRAMEWORK
KohakuTerrarium is a framework for creating autonomous AI agents and teams with built-in tools, TUI, and a web interface.
- HAYSTACK COOKBOOK: READY-TO-USE NOTEBOOKS
Jupyter notebook examples with Haystack: RAG, search, and LLM. Ready to use and customize.
- Video Templates for AI Agents
Create reusable Remotion video templates and share them across 25+ coding agents like Claude Code and Codex.
- VESTIGE - COGNITIVE MEMORY FOR AI
Vestige is a cognitive memory for AI agents: FSRS‑6, 29 brain modules, a 3D dashboard, and an MCP server for popular IDEs.
- AI CONTROLS n8n VIA MCP
Integrate AI assistants (Claude, ChatGPT) with n8n via MCP. Control automation using natural language.
- WDOC - SMART DOCUMENT SEARCH
Summarization and search across heterogeneous documents with support for any LLM providers, file types, and advanced RAG.
- BOOST MAKE AGENTS SMARTER
A minimalist tool for speeding up and improving AI‑agent work.
- HEYGEN SKILLS: AVATARS AND VIDEO
The skills project provides scripts for creating avatars and videos via HeyGen v3 Video Agent. Implemented in Shell, already 355★ on GitHub.
- AUDITOR - NEW RELEASE FOR CODE
Auditor project release channel: automatic code audit, reports, and integrations to improve development quality.
- EMILIA PROTOCOL ACTION GUARDIAN
EMILIA Gate verifies authority before changing money, code, permissions, and infrastructure, providing independently verifiable proof.
- TALWELL: LONG-TERM MEMORY
TALWELL — plugin‑oriented long-term memory for AI‑agent platforms, implementation of the AMP protocol. Written in JavaScript, it has 549 ★ and supports auto‑dream and LLM integration.
- ASKIMO: AI CHAT CLIENT
askimo is a universal AI client in Kotlin with support for chat, RAG, plans, and agents through multiple model providers.
- Genblaze: AI Media Pipelines
Genblaze — open-source Python SDK for orchestrating generative media pipelines (video, audio, image) with built-in provenance for every output.
- CREATE YOUR AI SOUL
The soul.md project helps create a personality for your agent by loading data into Claude Code or OpenClaw and forming a unique AI soul.
- ECHO: AI Where the User Pays
SDK where AI costs fall on the user, not the developer.
- OSINT MCP SERVERS FOR RECON
A curated list of the best MCP servers for OSINT investigations. An open project with 285 stars — PRs welcome!
- UNITY MCP SERVER – GAME REVOLUTION
Connect Claude, Cursor, or any MCP client to Unity and get 268 tools for AI game development.
- MOBIUS: RUST FRAMEWORK FOR AGENTS
Möbius is a compact Rust framework for building code-writing agents. Frontend-agnostic and works with any LLM. Already gained 300 GitHub stars.
- Codex Mobile on any OS
Run Codex Mobile on Linux, Windows, and Termux on Android without restrictions.
- AGENT SELF-SEARCH NET
Self-contained search skill for AI agents: SearXNG, anti-detect browser, and hallucination protection. Free, no limits.
- Pure C# PP-OCRv6 OCR
Pure C# PP-OCRv6 OCR library with SIMD kernels and GEMM for fast, low‑memory text detection/recognition. Includes a managed ONNX interpreter, needing no Paddle, ONNX Runtime, or OpenCV native libs.
- SECURE SANDBOX FOR AI AGENTS
Box isolates AI agents, using OS isolation and default‑deny Dogwood policies. It injects credentials from a secure store without exposing them to the agent, and restricts files, network and code execution.
- PaperOrchestra AI Scientific Writer
Automatic AI author of scientific articles based on the Google PaperOrchestra implementation. Works with any code agent without API keys or LLM SDK.
- OPEN-AGENTRL - UNIVERSAL AGENT RL
Open-AgentRL offers RLAnything and DemyAgent — general and scalable agent RL algorithms for terminal, GUI, SWE, and tool use.
- Survive LLM Chaos
Open-source Go tool for fine-tuning, building, and deploying LLMs with a single command.
- REMOVES ADS BEFORE PLAYBACK
MinusPod — a self-hosted Python server that intercepts media streams and removes ads before playback using LLM Claude. Users get clean content without interruptions, without needing extra plugins.
- RESTORING VISUAL CONSISTENCY
Project deepseek-whalechan ensures high consistency of Whale‑chan's character design in every generation. It includes a high-consistency specification, a visual asset library, and a toolkit for creating agents.
- MULTIMODAL RAG SURVEY
Comprehensive survey of multimodal RAG methods: from retriever architectures to generation strategies. 545 stars on GitHub. Perfect for topic entry.
- SCARF — Native AI Agent (macOS, iOS)
Native app for Hermes AI agent with support for local and remote servers, multiple windows, and powerful tools.
- ANYTYPE-MCP - Manage Objects with AI
The MCP server enables AI assistants to create and edit objects and lists in Anytype's encrypted wiki using natural language.
- AWS CDK FOR GENERATIVE AI
AWS CDK construct library for building generative AI solutions. Ready-made patterns for quick start.
- MCP-SECURITY: AI-AGENTS FOR SOC
MCP-Security is an open Python framework for integrating AI agents into SOC/SIEM/SOAR. Automates threat analysis and incident response using LLM.
- Hermes Voice Gadget SDK
Firmware, simulator, and plugin for building ESP32 push‑to‑talk voice gadgets that work with a Hermes Agent.
- MOSHIX EXTENDS JSON CAPABILITIES
A set of extensions for Moshi: IR plugins, sealed class support, and utilities to simplify JSON serialization in Kotlin.
- REMOTE SSH VIA AI AGENTS
MCP server with 37 tools for managing SSH servers. DevOps automation, backups, monitoring, and database work via Claude Code and OpenAI Codex.
- FREE RUNS-ON.DEV SUBDOMAINS FOREVER
Get your own runs-on.dev subdomain free forever. Runs on Cloudflare Workers with instant DNS. Perfect for projects and testing.
- AGENTS IN SANDBOXES
Self-hosted platform for running code agents in isolated environments with a vault proxy.
- STS2MCP: AGENT LAUNCH STS2
The STS2MCP mod exposes the internal state of Slay the Spire 2 and provides an MCP server for full‑featured agent runs of the game.
- VICOA: AGENT IDE FOR CODE
Vicoa — agent IDE that lets you control a team of coding agents from any device: desktop PC, smartphone, or VPS. The project is open source, self-hostable, and written in Python.
- ARL-NEXT: ASYNCHRONOUS RECON
ARL-NEXT — a contemporary attack-surface reconnaissance and asset monitoring platform. Rewritten in Python with asynchronous scheduling, enterprise-level asset correlation and native MCP support. Ready to run in Docker.
- VIDEO STORYBOARD IN ONE IMAGE
dsh-video-storyboard creates a scene-aware storyboard for DeepSeek Harness: 9-16 cells with timestamps, transcript, and audio envelope in one image (384 tokens). Two tools: video_storyboard and video_zoom.
- Intelligent Search
Knowledge engine for AI agents with MCP support: document indexing, wiki organization, and instant search across PDF, DOCX, PPTX, and Markdown.
- HEVY-MCP: YOUR WORKOUTS ON GITHUB
Manage workouts, programs, and exercises in Hevy via the MCP server. Create sessions faster, organize plans, and always stay up to date with changes.
- 230+ SEMANTIC ANCHORS
Catalog of 230+ verified terms like arc42, TDD London School, tracer bullet. Activate deep LLM knowledge. Insert into prompts and agent instructions instead of manual method descriptions.
- SIMPLEMIND: LIGHTWEIGHT AI API CLIENT
Python client for Anthropic, Gemini, and other LLMs. Replaces LangChain and LangGraph for common tasks — no extra abstractions or complexity.
- Native Desktop Applications
Agent Skill for creating cross-platform desktop applications with native UI. Based on analysis of Raycast 2.0.
- Firefox Automation on Python
An advanced Python framework with WebDriver BiDi support for Firefox automation, efficiently bypassing detection and protection systems.
- BYTESDESK AI CHAT FOR TEAMS
Open IM service with AI chat, email, tickets and omni‑channel support — an alternative to Slack, Zendesk and Intercom.
- R2AI: AI REVERSING
r2ai — plugin for radare2 that uses LLM for automatic analysis and reversing of code. Integrates directly into the radare2 interface, providing hints and generating pseudocode. Supports OpenAI models and local LLMs via API.
- DISLLM INFERENCE ON MOJO
Runs diffusion LLMs (LLaDA, Dream) locally on CPU without GPU. Written in Mojo with GGUF format support. 289 stars on GitHub.
- SELF-HOSTED SEARCH FOR AI AGENTS
ask-search — CLI and MCP server over SearxNG for searching Google, Bing, DuckDuckGo, Brave without API keys. Works with Claude Code, OpenClaw and any shell. Optional Tavily backend included.