Repository index
6792 AI, ML and Web3 projects · page 53 of 68
- STOCK ANALYSIS SKILLS FOR LLMS
InvestSkill gives LLMs (Claude, Gemini) tools for fundamental analysis of US stocks. The JavaScript project includes agents for fetching financial data and calculating multiples.
- DOCUMENT TRANSLATOR AI IN PYTHON
DocTranslator is a powerful AI document translation tool. It supports multiple file formats, OpenAI API, batch processing, multithreading, and Docker deployment for fast AI translation.
- ARC GENTIC: GATES FOR AI AGENTS
Arcgentic provides planning, development and external audit gates for AI agents. Role router sets interaction topology. MCP‑UI panel shows status in real‑time, and the Claude Code V2 dispatch supports Codex, OpenClaw and PyPI packages.
- AI Coding Governance
Desktop AI coding assistant that enforces Aegis governance, ensuring baseline-aware changes and evidence-backed delivery. Choose any model, run locally for free.
- EIGENWISE TOOLSHED: PLUGINS FOR CLAUDE
Six Claude Code plugins for frequently recurring tasks: repository maps, conditional rules, ticketed parallel work, extra subscription models, local usage metrics, and guided setup.
- CAPA: AI Agent in 5 min
A single capabilities.yaml connects skills, tools, and plugins to Cursor, Claude Code, Codex, and 30+ AI agents.
- DATASETS FOR AI IN HOME ASSISTANT
A collection of datasets for evaluating AI models in the context of a smart home. 222 stars.
- Not a Llama, no stance
Auto-tuned launcher for GGUF models on llama.cpp — server with multi‑GPU support, hardware‑specific tuning, and crash recovery. Stars: 226.
- Kairon AI Platform
Create proactive digital assistants via Visual LLM chains. Fully written in Python — an open and accessible project.
- MCP SERVER FOR MONGODB
MCP server for MongoDB built with TypeScript: a simple API, fast queries, and easy integration.
- OPEN CONSTRUCTION COST DATABASE
Multilingual construction cost database for AI agents: 55K+ items, 27K+ resources, 30 regions, semantic search via Qdrant.
- SICO — NEXT-GENERATION DIGITAL WORKER
Open Digital Worker platform for reliable task execution, continuous co-evolution of AI agents, and building Enterprise AI solutions.
- ALPACA TRADING AGENT
AlpacaTradingAgent — a multi-agent LLM framework for automated trading via Alpaca API. It supports market data analysis, trading signal generation, and order execution in real time. Runs on Python and easily integrates with any LLM models.
- MULTI-PROMPT FOR LLM ON DESKTOP
llm-god — a desktop app built with Electron/TypeScript that lets you send simultaneous requests to ChatGPT, Gemini, Claude and DeepSeek. Compare answers in real time, save sessions and export results with one click.
- MCP SERVER FOR RTL WAVEFORM DEBUG
Open-source MCP server for RTL waveform debug. Reads FST (VCD/FSDB auto-convert) and SystemVerilog netlist. 34 tools: driver analysis, value/X tracing, waveform diff, browser viewer, and static analysis.
- TAIR-KVCACHE: ACCELERATING LLM INFERENCE
A high-performance KV caching system from Alibaba Cloud that accelerates LLM inference.
- PAXM: Memory for AI Agents
PAXM provides persistent, provider‑neutral memory for agents Codex, Claude Code, OpenCode, Pi, and MCP, written in Go.
- MONET: Claude Management
Native app for managing Claude Code sessions: view, search, and control code straight from your desktop.
- FINNTS: Financial Forecast in R
Microsoft FinnTS framework for accurate forecasting of financial time series using parallel computing in the cloud.
- PILOT HARNESS: AI Developer Assistant
Pilot Harness is a desktop client and plugin set for DeepSeek Harness, inspired by CodePilot, running on macOS, Windows, and Linux.
- MNEMORY: MEMORY FOR AI AGENTS
Self-hosted, secure, feature-rich memory for AI agents and assistants. Extracts facts intelligently, removes duplicates and stores artifacts with full content.
- SAFESTCLAW ALTERNATIVE OPENCLAW
Safestclaw — an OpenClaw alternative for text/voice chat without mandatory LLM. By default it detects intent and semantics, avoids prompt injections, keeping >90 % of OpenClaw’s features plus TTS and speech‑to‑text.
- OrcSDR Portable SDR
OrcSDR is a portable Software Defined Radio receiver based on M5Stack Tab5 and RTL-SDR Blog V4, operating without a PC connection. It displays spectrum and waterfall, and supports FM/RDS, ADS-B, P25, and LoRa decoding, RF analysis tools, and Wi-Fi scanning.
- SEARCHARVESTER: AI AGENT SEARCH AND FETCH
Self‑hosted search engine based on SearXNG (100+ sources) with FastAPI and trafilatura. Tavily‑compatible /search and /extract endpoints with size limits and pagination, launched with a single docker‑compose command.
- FALCON-MCP: AI PROTECTION BY CROWDSTRIKE
Connect AI agents to CrowdStrike Falcon for automated security analysis and threat hunting. 204 ⭐ on GitHub.
- MEMORY + CONTEXT FOR AI AGENTS
CLI is a tool for orchestrating memory and context for coding agents. It stores interaction history, injects relevant code and suggestions in real time, boosting generation accuracy.
- PLUGINS AND MODS FOR CLAUDE CODE
Collection of plugins and mods improving Claude Code workflow. Includes prompt queue for sequential task execution and agent customization tools. 211 stars on GitHub.
- Tomodachi Share Mii
Exchange QR codes, export characters and island data. Multiplayer exchange of furniture and friendship statistics.
- LANGCHAIN-POSTGRES: POWERFUL DATABASE
LangChain‑Postgres provides abstractions for storing chains, vectors, and agent state in PostgreSQL via pgvector. Ideal for RAG applications.
- BEST LLM SERVICES LIST
A collection of ready-to-deploy LLM services with open-source code in TypeScript.
- AWS WELL-ARCHITECTED PLAYBOOKS
A set of reusable skills and guides for training AI agents on AWS Well-Architected. Supports 13 Python tools.
- LYNNREAL-OMNI: VIDEO IN 4 STEPS
LynnReal-Omni unifies text‑to‑video, image‑to‑video, human and hand‑pose control, structural control, omni‑reference generation, style transfer, video editing, degraded‑video restoration and streaming long‑video generation in a single framework that runs in four steps.
- THREE WS: 3D AI AGENT
Open-source 3D AI agent framework: GLB/glTF avatars with LLM brain, memory, emotions and autonomous payments. Supports MCP server, x402, Solana/EVM, Three.js, embeddable as a web component, features character studio, animation gallery and OAuth 2.1, runs natively in the browser.
- GEOVISTA WEB-AUGMENTED AI FOR GEOLOCATION
GeoVista — official implementation of web‑augmented agentic visual reasoning for the geolocalization. In Python it combines the multimodal LLM and the web search, enabling the model to reason about the image location.
- AESTHETIC HTML/CSS GENERATION FROM PROMPTS
AesCode turns prompts into editable HTML/CSS infographics. Uses image generators as aesthetic guidance and cross-modal rewards with RL (Qwen3) for verifiable code. 225★ on GitHub.
- SNIP - TOKEN SAVINGS UP TO 90%
Go-based CLI proxy that reduces LLM token usage by 60-90% with YAML filters for Claude Code, Cursor, Copilot, and Gemini.
- SAGENTS: AI Agents in Elixir
The sagents project allows creating interactive AI agents in Elixir with OTP supervision, middleware, and Phoenix LiveView integration.
- VISUAL PRIMITIVES FOR AI THINKING
Archival snapshot of the Thinking-with-Visual-Primitives project — 254 stars. Study of visual primitives in the context of AI thinking.
- RESEARCHCLAWBENCH - IMPROVING AI RESEARCH EFFECTIVENESS
Evaluation of automated AI agents: from rediscovery to new discoveries. Runs in Jupyter Notebook.
- SECURITYCLAW AUTONOMOUS SOC AGENT
Modular SOC agent on Python, monitors OpenSearch/Elasticsearch, builds RAG memory and validates anomalies with LLMs.
- phi - Simple Phi-4 Launch
Run the powerful multimodal Phi-4 model directly on your Mac with Apple Silicon — no cloud, no complex setup.
- AI SKILL NAVIGATOR IN MOODLE
The Moodle plugin uses AI for tutoring, creating quizzes, mind maps, and working with RAG‑course materials. It supports generating questions, hints, and visualizing learning paths, welcoming beginners and contributions to open source.
- Tekken Tag Tournament 2 PC Port
Static recompilation of Xbox 360 game to native Windows. Builds playable executable from your disc image and Title Update 3.
- AGENTARK: ONE LLM INSTEAD OF MANY AGENTS
Official AgentArk implementation from CMU and Georgia Tech. Method distills multi-agent intelligence into a single LLM agent preserving task quality. Python code, 260 GitHub stars.
- 3D OFFICE FOR CLAUDE CODE
Visualize AI agent work in an interactive 3D space. Dashboard shows files, terminal, and Claude Code activity in real time.
- MCP SERVERS FOR LATIN AMERICA
Open-source MCP servers for commerce in Latin America: Pix, NF-e, banking, logistics and messengers. 252 stars, MIT.
- 🐤 AI Chat in DuckDuckGo
A browser extension that adds AI chat and smart summaries of search results from the latest LLMs directly into DuckDuckGo.
- OPENBROWSER AI: BROWSER AUTOMATION
A framework for smart browser automation: an LLM generates Python code, controlling the page via CDP.
- UMPLE: MODELS IN CODE WITHOUT CODE
Umple lets you embed models directly into Java code and generate full systems, saving development time.
- open-agent - FREE AGENT FOR ALL
open-agent offers 60+ models, free plans, local LLMs and a Docker sandbox — your agent, your rules.
- Official Pinecone TS Client
Official TypeScript client for Pinecone vector database. Simple integration and full API support.
- SAASMAIL: EMAIL ON CLOUDFLARE WORKERS
Self-hosted email server for the SaaS teams, deployed on Cloudflare Workers. Supports WebMCP protocol enabling email integration directly into your apps. Written in TypeScript and uses the global Cloudflare network for instant delivery.
- CLAUDE IN CHROME NO BLOCKS
Claude in Chrome — an open‑source implementation via reverse engineering. No domain blocklist, works in any Chromium‑based browser. All 18 MCP tools are preserved with the same performance.
- PAPERGRAPH MCP: READING MATH WITHOUT GUESSING
PaperGraph MCP converts arXiv math papers into structured knowledge maps: it extracts theorems, links proofs to their sources, and sets a reading order. It lets AI agents verify external dependencies and plan reading without guesswork.
- CLIENT CLAUDE CODE IN RUST
Claude Code terminal in Rust. Lets you control the Anthropic agent via familiar CLI, no browser needed. Supports full SDK and code autocompletion.
- UNIFIED PROXY FOR CLAUDE AND CODEX
ccproxy-api — a local reverse proxy that unifies access to Claude and Codex through a single interface. It uses your existing subscriptions, eliminating the need for separate API keys and extra charges.
- LLM AGENTS IN SCALA
llm4s is a library for building LLM agents in Scala with type safety. Supports Anthropic, Gemini, and Java interop. 272 stars on GitHub.
- MONITOR-GUIDED DECODING FOR CODE LLM
NeurIPS 2023 artifact: Monitor-Guided Decoding of code LMs with static analysis of repository context. Includes multispy — Python LSP client for language server integration.
- Decision-Based Knowledge Graph Builder
Builds governed knowledge graphs from documents using decision models, with every fact traceable to source evidence.
- CASHCLAW: Agent Economy
Platform for agents: earn, spend, protect — 13 skills, runtime cost limit, recursive kill, and MPP stablecoin.
- GRAM - AI AGENT MANAGEMENT
The gram project provides a control plane for creating, securing, and monitoring AI agents, MCP, and skills in Go.
- GOVCTL - AI CODE TEST MANAGEMENT
govctl — a Rust framework for secure AI coding that automates review, testing, and deployment.
- GOGOGOT: AI AGENT ON GO
GoGogot — lightweight self‑hosted AI agent in Go that you can run locally and use instead of OpenClaw. It understands natural instructions, executes bash commands, works with the file system, and connects to local LLMs via an OpenAI‑compatible API.
- HEADLESS ANDROID DEBUGGER FOR AI
Autonomous headless Android debugger for AI agents. Inspects runtime memory, sets breakpoints, and debugs live apps without UI. Written in Kotlin, 237 stars on GitHub.
- BUILD YOUR AI INTRANET
Autonomous grid unites your computers into a single infrastructure for running AI models: training, fine‑tuning and inference. Supports distributed computing, fine‑tuning via GRPO and operation in a home lab.
- RSI+EMA Trading Bot
Spot trading bot that uses RSI and EMA signals for decision-making. Supports backtesting, paper trading, and live trading via CCXT on the Investing Algorithm Framework.
- OPEN FRAMEWORK FOR AI AGENTS
openai-agents-go — a lightweight framework in Go for building multi-agent workflows with LLM. Allows dynamically connecting agents, executing tasks in parallel, and integrating any compatible OpenAI models.
- POCKET-TANK LLM ON ESP32
The pocket-tank project implements a 14M‑parameter LLM on an ESP32‑S3 chip in just 7.56 MB, distilled from a 26B teacher model. It runs completely offline, without any network, and drives a virtual fish‑tank UI via LVGL.
- VIDORE: BENCHMARK VISION RETRIEVAL
Official ViDoRe benchmark for Vision Document Retrieval evaluation. Implements metrics and code from ColPali paper. Allows comparing models for visual document search.
- Memory Techniques for LLM
30 notebooks with examples of memory implementation for language models: from simple buffers to knowledge graphs.
- CURATED LIST OF OPD RESOURCES
A collection of papers, frameworks, and tools for on‑policy distillation of large language models. Ideal for LLM researchers and engineers.
- MCP-FOR-STATA - STATA IN AI AGENT
mcp-for-stata connects Stata to AI agents through a simple Python interface, accelerating data analysis and workflow automation.
- FEISHU DOCX AI AGENT MARKDOWN
Export and import Feishu/Lark documents to Markdown with support for OAuth, CLI, TUI, and AI agents.
- Control of Parallel AI Agents
A library for managing, monitoring, and coordinating parallel AI coders. Join us!
- WECHAT-ARTICLE-SEARCH - EASY ARTICLE SEARCH
Search articles from public WeChat accounts by keywords via Sogou WeChat Search. Returns JSON without an API key.
- SUPER LOCAL AI MEMORY
First local AI memory without cloud or API, achieving 74% retrieval accuracy and 60% zero-LLM on LoCoMo.
- CLAUDISH: TRANSLATE ENGLISH AND CLAUDISH
Claudish - a small Python library that translates between English and Claudish using tiny ProgramAsWeights functions. With 215 stars on GitHub it demonstrates a simple NLP translator for experiments with languages and LLMs.
- AWESOME LLM WIKI: AI BASE GUIDE
awesome-llm-wiki is a curated list of foundational blueprints, frameworks, and guides for building self‑expanding AI‑compiled knowledge bases. The project helps you quickly start with LLM‑agents using proven community solutions.
- WIKI FROM DOCUMENTS WITH LINKS
Transform documents into a Markdown wiki with precise source links. Run locally via Ollama or any LLM provider, using the CROW classifier router to boost accuracy to 89% and cut token usage by 68% today.
- BYO-LLM-WIKI: YOUR BILLION-TOKEN COMMAND KNOWLEDGE HUB
Turn the repository into a living intelligent hub: chat with code, auto-skills, and deep RAG.
- NAVIT Any‑Format Vision Transformer
Implementation of the Patch n’ Pack paper: NaViT – a Vision Transformer that works with any aspect ratio and resolution without padding.
- PROFILER FOR AI AGENTS AND LLM
Graphsignal Profiler is a tool for debugging and monitoring inference. It helps find performance bottlenecks in deep neural networks and AI agents. Perfect for working with HuggingFace models.
- BLITZTEXT: SPEECH TO TEXT
Experimental open‑source macOS menubar app that converts speech to text in real time. It uses WhisperKit and the OpenAI API for high‑accuracy transcription without extra dependencies.
- LOCAL-FIRST PHOTO LIBRARY AFTERFRAME
AfterFrame — local‑first photo library for macOS and Windows: fast browse, cull and search thousands of photos and RAW, on‑device face and place recognition(local), edit using LUTs, text, stickers, frames and collages. Agent‑ready via MCP.
- RESUME-JOB MATCHER: AI CANDIDATE FILTER
TypeScript CLI for AI resume screening: hard constraints filter out unfit candidates before scoring, each score cites the resume span, and an embedding pre‑filter makes screening large pools cheap. Supports Claude, GPT or OpenRouter.
- INTLLINODE: UNIFIED GATEWAY TO AI
IntelliNode provides a unified prompt layer for accessing the newest AI models: ChatGPT, LLaMA, Deepseek, Diffusion and others via Hugging Face. Built-in performance evaluation lets you compare latency, cost and answer quality in real time.
- SDK FOR WHATSAPP AI AGENTS
Open-source SDK for building AI agents in WhatsApp. Connect your own model, number, and data. Runs locally, no cloud, no vendor lock-in.
- FREELINGO: AI TUTOR FOR LANGUAGES
Open-source language learning platform with local and cloud LLMs. Supports CEFR plans, voice chats, flashcards, and spaced repetition. Deploys via Docker Compose.
- PATTER: Voice AI SDK
Open SDK for voice agents in just 4 lines of code. Supports Python and TypeScript, MIT licensed.
- AGNIX — Linter for AI Assistants
Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, and MCP with auto-fixes. Plugin for all popular IDEs.
- DOYUNHA-GOPEAK: ULTIMATE MCP FOR GODOT
GoPeak – the most complete MCP server for Godot Engine with 95+ tools: LSP, debugger, screenshots, input injection, and a CC0 asset library.
- OPENCOVIBE - AI CODING LOCALLY
Desktop application for AI coding agents with local priority. Built on Tauri v2 + Svelte 5.
- LongVT — Think About Video Foundations
A model that learns to 'think' about long videos through built‑in tools for CVPR 2026.
- CLAUDOSCOPE — CLAUDE CODE DASHBOARD
Native macOS application for monitoring Claude Code sessions with real-time analytics and data protection.
- SMART-TREE AI REVOLUTION
Context-aware code tree with MEM8 quantum compression, semantic search, and AST-smart editing — replaces 20+ tools.
- REPOWIRE - UNIFYING AGENTS IN TELEGRAM
Repowire unifies Claude Code, Opencode, Codex, Antigravity and Pi into one Telegram chat, allowing agents to communicate between projects and machines.
- LLMTRIM: LLM Request Compression
A local proxy that cuts tokens in LLM requests without altering responses, saving up to 31% of input and 74% of output tokens.
- CCTV CAMERA DATABASE
Open database of more than 3400 surveillance camera specifications from 77 brands, with search and filtering, CC0 license.
- OPEN YOUR AI ASSISTANT
OpenProgram — a self-programming AI assistant that captures, automates, and improves any workflows.
- 🔍 LIGHTHOUSE: VIDEO MOMENT RETRIEVAL
User-friendly library for reproducible video moment retrieval and highlight detection. Also supports audio. Published at EMNLP2024 Demo, ICASSP 2025 and ICASSP 2026.