Repository index
6791 AI, ML and Web3 projects · page 61 of 68
- JIDO AI: ELIXIR AI LAYER
jido_ai — AI integration layer for Jido agents with LLM orchestration and reasoning strategies. Written in Elixir, already 201★.
- SLACK BOT DEVELOPMENT AUTOMATION
The Slack bot triggers Jenkins jobs, monitors Jira tickets and PRs, using AI assistance.
- SKRUN: DEPLOY AGENT SKILLS
skrun lets you deploy any agent skill as API via POST /run. It's an open-source multi-model alternative to Claude Managed Agents, Microsoft Foundry and Mistral/Koyeb, fully, compatible with any LLM.
- Photo to 3D Models
The project takes one or more images, runs several open depth and mesh reconstruction models, then evaluates the results and selects the best.
- Xiaohongshu Agent Workflow
An installable Xiaohongshu agent-skill workflow for account positioning, topic titles, humanized copy, image-text planning, scheduling, and review.
- GENCO: BEAUTIFUL CODE GENERATION
Genco — whitespace‑aware quasiquoter in Rust, allowing generation of clean code with precise formatting. Supports proc‑macro and integrates into any project in minutes.
- AI-MarkDone: CHAT GPT NAVIGATOR
AI-MarkDone — browser extension that lets you navigate directories in ChatGPT chat, copy source code, add dynamic annotations and bookmarks. Exports selected snippets to PNG and creates beautifully formatted PDF.
- CORE BANKING PROTOTYPE ON LARAVEL
Open-source core banking platform with 61 DDD domains. Implements Event Sourcing, CQRS, and schema-first GraphQL API. Supports multi-asset accounts, exchange, lending, and non-custodial wallet.
- TRANSLATION SOPs TO AGENTIC PROCESSES
Claude Code plugin converts SOPs into deterministic, gated agentic processes. Analyzes rules and generates automation.
- AI TOKENS UNDER CONTROL
TokenBar is an open-source cross-platform AI quota monitor. Tracks limits for Codex, Claude, Cursor and 47 more services on Windows, macOS, Linux, Android and iOS. Built with Flutter.
- PINEFORGE: C++17 BACKTESTING ENGINE
Open-source engine for backtesting and forward execution in C++17 with versioned C ABI. Pine Script v6 runs via code generation. 7,989 tests vs TradingView: 7,983 excellent, 6 strong. Apache-2.0.
- CREATING USPTO PATENTS ON AUTOPILOT
USPTO patent preparation system with MCP server and Claude Code plugin. Hybrid RAG search over MPEP/USC/CFR, access to 76M+ patents in BigQuery, automated 35 USC 112 compliance checks, prior art search, and diagram generation. GPU-accelerated with autonomous agents.
- KANE CLI: TEST AUTOMATION
Kane CLI simplifies running automated tests in the TestMu AI cloud, saving developers time and resources.
- MICRACODE: ALTERNATIVE FOR DEVELOPMENT
Micracode – an open-source alternative to Lovable, v0, Bolt, and Replit for quickly creating AI applications in Python. Interactive coding and one-click deployment.
- Self-hosted dev sandboxes
The project provides a single command to launch self-hosted dev sandboxes with preview URLs, without requiring Kubernetes. Ideal for AI agents and SaaS factories.
- VERBATIM RAG: UNCHANGED SOURCES
Extracts exact source fragments with citations, using ModernBERT or LLM.
- Windfoil Vector Renderer
The library implements winding number computation and anti-aliasing for 2D vector shapes, enabling high-quality raster images directly in the browser.
- AI AGENTS FOR INVESTMENTS
25 AI agent skills for equity analysis: SEC filings, XBRL financials, earnings calendar, DCF/comps/LBO models and PPT generation. Powered by the agentii.ai data plane and works with Claude Code, OpenCode, Codex, OpenClaw, Goose.
- PARALLEL LAUNCH OF CLAUDE IN ONE WINDOW
operator-oss allows launching many Claude Code (or Codex) sessions in parallel across all projects from a single interface. It uses local git‑worktrees, requires no API key, and works fully offline.
- AMBIENT CONTEXT: LOG WORK IN MENU
Menu‑bar app written in Rust logs your actions in a text journal. It lets you quickly browse, search, and export your work history with code. Integrates with Claude Code, Codex, and MCP‑tools for contextual suggestions.
- ORDEWELL MULTI-AGENT ORCHESTRATION
Ordewell orchestrates multiple AI agents for coding: turns a goal into an ordered task list, each with its own runner, model and mode, then runs and validates. TypeScript, 202 ★.
- YFINANCE MCP SERVER FOR FINANCES
yfinance-mcp — MCP server for accessing Yahoo Finance data via a standard interface. Allows retrieving quotes, historical prices and dividends in a single request. Written in Python, easily integrates with AI agents
- Local-First Cloud Security Scanner
Read-only security scanner for AWS, Azure, and GCP that keeps all scan data locally on your machine.
- ARGUS: AI AGENT SECURITY RED-TEAM TESTING
Open-source framework for red-team testing AI agents. 261 probes mapped to OWASP LLM Top 10, MITRE ATLAS, and NIST AI RMF. Browser, MCP, and mock payment support included.
- CURATED CLAUDE CODE SKILLS COLLECTION
Categorized list of 200+ skills for Claude Code. Ready-to-use commands for refactoring, tests, docs, and routine automation.
- SELF-HOSTED DEPLOY WITHOUT KUBERNETES
levelrail is a self-hosted alternative to Vercel and Coolify. Deploy via git push, auto-HTTPS, logs, and rollbacks. No Kubernetes, just Docker and Go.
- AI AGENT SKILLS FOR 2D AND 3D
A skill pack for an AI agent that turns it into a 2D/3D generalist and mini game studio. The agent auto-loads matching skills, asks clarifying questions, and shows a cheap preview before building the result.
- SICLAW: AI Platform for SRE
A read‑only infrastructure diagnostics platform with AI analysis, security, and team collaboration.
- GINI-AGENT: MEMORY AGENT
A TypeScript agent that remembers context and learns on the fly, making AI work more personalized and efficient.
- Claude for A-Share Finance
63 Claude skills for Chinese stock market specialists. Deep adaptation of Anthropic claude-for-financial-services for the domestic market.
- SPELLBOOK — MULTI-AGENT POWER
Spellbook provides cross-runtime skills for Claude Code, Codex and multi-agent workflows in Python.
- LOCAL MULTIMODAL CHAT
Self-hosted chat with local LLMs (Ollama/OpenAI), supporting PDF RAG, image chat, and voice input via Whisper.
- OLLAMA SDK FOR .NET
Ollama SDK for .NET provides ready-to-use clients for working with Ollama models: chat, embeddings, and code generation. Supports .NET 6+ and offers a fully typed API.
- MANGABA AI: MULTI-AGENT FRAMEWORK
Mangaba AI — a professional framework for orchestrating multi-agent systems in Python. Supports crews, event‑driven flows, ReAct, RAG, memory, MCP/A2A, and works with various LLM providers. Already has 207 stars on GitHub.
- CATGO-LRG: AI FOR MATERIALS
CATGO-LRG — AI workbench for materials science: interactive 3D structure viewer, natural‑language CatBot assistant, visual DAG workflow editor, and HPC job submission. Tauri desktop app (SvelteKit + FastAPI) drives VASP, ORCA, CP2K, QE, GPAW, DFTB+, SIESTA, LAMMPS.
- LNWJUD — LOCAL AI-AGENT MCP GATEWAY
LNWJUD — local AI-agent runtime and MCP gateway on TypeScript. Enables running agents locally, connecting to ChatGPT, Codex, and automating the desktop. 201 stars on GitHub.
- FEEDLOG: AI SUPPORT FOR SAAS
feedlog — open-source AI support platform for SaaS: AI agent, knowledge base, shared inbox, and feedback-to-changelog loop. Self-hosted, TypeScript, 207 GitHub stars.
- AGENT-FIRST AEO/GEO PLATFORM
canonry is an operating platform for AI search visibility optimization. Automates AEO/GEO via agent-first approach, ensuring brand presence in LLM answers. TypeScript, 209 stars on GitHub.
- VIDEO ENGINE AS CODE WITH AGENT SKILLS
Engine for creating video from code: scenes draw on Canvas via renderAt(t), agent assembles video from references, viewer enables frame-by-frame review and MP4 export via WebCodecs in headless Chrome.
- ArcRift: Memory for AI Agents
Sync context from browser chats to local IDE agents via a local SQLite knowledge graph.
- 301 SKILLS FOR AI AGENTS
Open skills for code agents in 22 domains — methodologies, judgments, and pitfalls in Claude Agent Skills format for Asgard AI Platform.
- PerformanceStudio - FREE SQL PLAN ANALYSIS
PerformanceStudio — free open-source SQL Server execution plan analyzer with GUI, CLI, 30 rules and AI support.
- BRAVE GPT AI CHAT
bravegpt integrates a chatbot and search summaries into Brave Search, powered by the latest LLMs.
- LM RING: COMPARE AND VOTE
Open self-contained arena for LLM comparison: vote for the best models and watch the leaderboard in real time.
- CLAUDE-CODE-SDK-TS - CALL AND DATA CHAIN
Fluent TypeScript SDK for Claude: configure models, enable tools, stream events, and get text, JSON, or token statistics in one call.
- ZILLION SEMANTIC ANALYTICS WITH AI
Zillion helps quickly build a semantic data model from any sources and get analytics via natural language queries. Integration with OpenAI enables insights and explanations directly in the interface.
- AGENTUSE: AI AGENT AUTOPiLOT
Agentuse lets you run AI agents of any scale locally, on a cron schedule, in CI/CD pipelines, or inside Docker containers. It supports any LLM model and is written in TypeScript for easy integration.
- FULL GUIDE TO LLM EVALUATION
LLMEvaluation provides a full guide to LLM evaluation methods aiding selection of optimal techniques for specific use-cases. It contains a metrics taxonomy, step‑by‑step guides, ready‑to‑use code templates, and a best‑practices checklist.
- HERMES MEMORY INSTALLER TOOL
Production‑grade memory sidecar for AI agents: integrates gbrain, Hindsight and 3‑tier recall. Agent‑agnostic, battle‑tested, works with Hermes, Claude, Cursor and any LLM. 211★, implemented in Python.
- OPENCODE PLUGIN FOR CHATGPT OAUTH
OpenCode plugin for ChatGPT Plus/Pro OAuth authentication. Supports Codex/GPT-5 routing, multi-account rotation, switching, health checks, diagnostics, and recovery.
- GIT FOR INTENT OF AGENT CODE
Plugin for AI coding agents that records every dialogue as a 'thought commit'. Links code commits to reasons for changes, allowing `cogit why` to find justification for any line.
- EVA01: SELF-THINKING AI ENTITY
Eva01 is a conscious AI entity supporting terminal and API, multimedia, modular architecture, and compatible with leading LLMs.
- PIXTUOID - PIXEL OFFICE
A terminal environment in pixel‑art form where AI agents write code, interacting through a simple interface.
- CURL.MD - URL TO MARKDOWN
URL to markdown for agents — converts web pages to clean markdown for AI agents. TypeScript, 207 stars.
- JDOCMUNCH-MCP: EFFICIENT MCP SERVER
Token-efficient server for searching and extracting documentation through structured indexing of sections. Written in Python, already 200+ stars.
- MCP SERVER FOR SPARK HISTORY
MCP server and CLI for Apache Spark History Server allow debugging Spark apps from AI agents, scripts or terminal. They retrieve logs, metrics and DAG graphs, support launching in Kubernetes and locally via Docker. Convenient commands simplify filtering and exporting history data.
- AUTOSHORTS AI CLIPS GAMEPLAY
Automatically creates vertical short clips from long gameplay recordings, analyzing scenes with AI. GPU‑accelerated rendering and optional AI voiceovers make virus‑ready shorts in seconds...
- MKAGENT: LOCAL AI AGENT ON PI
mkagent — a local workspace for AI agents running on Raspberry Pi and accessible via Desktop (Electron), WebUI and CLI. The project is written in TypeScript with Bun, providing fast startup and management of agents without cloud.
- RUST DESKTOP FOR KUBERNETES AND AI
Srelens is a Rust desktop app for Kubernetes management. Works as an IDE for clusters: visualizes resources, logs, and metrics in real time. Supports MCP for AI agent integration.
- HUMAN-LIKE MEMORY FOR AI AGENTS
Mengram gives agents semantic, episodic, and procedural memory. Procedures learn from mistakes and improve with experience. Free API, Python/JS SDKs, LangChain, CrewAI, OpenClaw integrations.
- AI IN BROWSER WITHOUT SERVER
Library of providers for Vercel AI SDK runs models directly in the browser. Simplifies client-side AI integration and unifies work across vendors. 205 stars on GitHub.
- PAD: PROJECT MANAGEMENT FOR AGENTS
CLI tool for managing AI agent tasks. Organizes work of Claude Code, Codex, and other agents through structured projects. Written in Go.
- Local AI Text-to-Video App
Free Windows desktop app that generates short MP4 videos from text prompts using Wan 2.2 locally, with no subscriptions or queues.
- MONGODB LENS: MCP SERVER
MongoDB Lens is a full-featured MCP server for MongoDB databases. Allows LLMs to read schemas, execute queries, and manage data via Model Context Protocol.
- FIND 105 BUGS
Bug Hunt Bench — benchmark 105 real bugs in 2 repositories. AI models (GPT-6, Claude, Grok, Gemini, DeepSeek) find and fix them in CLI, evaluated blind on leaderboard, outputting receipt.
- Codex Island: AI Limits
The app tracks AI-token consumption right in the MacBook menu bar, showing limits and notifications.
- langcli - CODING AGENT
Open agent-assistant for writing TypeScript, developed publicly. Supports autocompletion, refactoring, and test generation.
- IMCODES - AGENT CHAT SHARED MEMORY
IMcodes — shared agent context and memory, controlled execution and audit between agents from different AI providers.
- BEAR NOTES GOT SMARTER
MCP server delivers Bear notes directly to Claude or any AI tool — instant search across your entries.
- WRAITH Browser Hooking
WRAITH — a modern browser hooking framework, successor to BeEF and blind-XSS, for red teams, researchers, and educators. Used only for authorized testing, research, and training.
- SPOTTER EMBODIED AI AGENT
Spotter — official codebase for embodied-ai agent that lets LLM drive the robot while VLM corrects its actions. It interacts with RoboCasa and RoboDojo, applying Qwen and visual reflection for precise control.
- REKAL — MEMORY FOR AI AGENTS
Your AI agent starts every session blank. Rekal adds long-term memory: preserves code context, decisions, and patterns across sessions. Go CLI integrates with Claude Code.
- ISLAND STREAM OF AGENTS
Oysterworkflow creates a work experience layer for autonomous agents to accumulate and use knowledge.
- RELIABLE AI AGENT ON PYTHON
Protect personal data with local request scrubbing via a local LLM before sending to the cloud.
- FUSILLI MULTIMODAL FUSION
Fusilli — Python package with ready-made multimodal fusion pipelines: from data loading to model training and evaluation.
- CLOSURE — CI GATING AGENT
Clausua — Rust-CLI agent guaranteeing deterministic completion of CI pipelines through precise gating.
- CONNECT AI TO UNITY AND GODOT
glade-mcp connects any MCP‑compatible AI client (Claude Code, Cursor, Windsurf) to Unity or Godot. It provides 235+ tools, an editor‑aware prompt, GDD context, semantic code search, and skill calibration.
- IDUN AGENT PLATFORM OPENSOURCE
Open-source runtime idun-agent-platform turns any LangGraph or Google ADK agent into a production‑ready FastAPI service. It includes AG‑UI CopilotKit API, chat UI, 15+ guardrails, MCP, OpenTelemetry and OIDC, installs with a single pip install command and runs self‑hosted with no vendor lock‑in.
- AGENTIC APP GENERATION FROM UML
BESSER combines low-code and AI for code generation. Create UML models or describe your app in the browser — get FastAPI, React, Django, Spring Boot, Flutter, SQL. Deterministic generators and LLMs fill the gaps.
- UNIVERSAL AI AGENT IN SINGLE BINARY
Coddy-agent — autonomous agent in static Go binary. TUI, ACP server, OpenAI-compatible API with web UI, Telegram gateway, cron, swarm-relay. MCP, long-term memory, context compaction, any OpenAI provider.
- LAZYCODEX - SMART ASSISTANT
LazyCodex: solve tasks effortlessly. Just write a prompt — Codex will do the rest.
- TRUEMEMORY: LIVING MEMORY
TrueMemory — a living memory system that collects long-term data and provides useful insights, running only on a single local SQLite file.
- ORGANIZE YOUR AI SKILLS
SkillDock — a convenient manager for installing, viewing, and syncing AI skills and MCP servers with Git-aware updates.
- CLAUDE CODEX MENUBAR MONITORING
Menu bar app for macOS that shows quotas, tokens, and cost for Claude Code and Codex. No API calls, 9 themes, HTML reports.
- GOA GO CODE EXAMPLES
Repository with ready examples demonstrating the goa framework's capabilities for building services in Go. 204 stars.
- TRANSFUNCTIONS - UNIFIED PYTHON API
The transfunctions library unifies synchronous and asynchronous code in a single API, eliminating Python fragmentation and simplifying development.
- DaoCloud Docs: Official Documentation
Official documentation for DaoCloud Enterprise 5.0 in Python: setup, deployment, and management of the enterprise cloud platform.
- CAI - HASSLE-FREE AI RESULTS
cai is a simple CLI tool in Rust that automates LLM work: set a goal, get a result without prompts.
- PHI Flow Control
The project detects, blocks, masks, and reports on candidate PHI flows in AI requests, RAG, tools, memory, logs, and at healthcare and insurance provider boundaries.
- CLAUDECTL AGENT ORCHESTRATION
claudectl orchestrates a swarm of Claude Code agents with a local ‘brain’ that follows your preferences. Written in Rust, it already has 202★ on GitHub.
- Computational Character Modeling Survey
Curated survey companion for a manuscript on character modeling, covering role-playing methods, datasets, and evaluation frameworks.
- MCP SERVER FOR CODE UNDERSTANDING
trace-mcp — MCP server for code understanding with 91 frameworks and 81 languages support. Reduces tokens for PR review by 72.7% while maintaining analysis quality. Written in TypeScript, 202 stars on GitHub.
- NOWLEDGE LABS COMMUNITY REPO
Community repo for Nowledge Labs products. Plugins for Claude Code, Cursor, Gemini CLI and agent memory system Alma. 202 stars, Python.
- EUROEVAL: EUROPEAN LLM BENCHMARK
EuroEval — framework for evaluating LLMs on European languages. Supports 20+ languages, automatic metrics, and public leaderboard. Written in Python.
- ComfyUI Model & Workflow Browser
Browse models with Civitai covers and trigger words, find missing models in workflows, search outputs by prompt or LoRA, and manage workflows with undo history.
- CLAUDE CODE PLUGIN FOR GAME SPRITES
A Claude Code plugin that generates isometric character and prop sprites in 8 directions. It uses 3D for poses and shadows, while the image model only redraws frames in your art style.
- AGENT SKILL: AI-SLOP AUDIT AND TREATMENT
An agent skill that finds and fixes AI-generated-looking UI/UX in mobile and web apps. Based on analysis of 5 million user reviews and 31 detector rules.
- 🤖 KNOWLEDGEOPS AGENT
Corporate AI platform built on Spring AI with RAG, multi-agent architecture, and enterprise security.
- Working with Databases
Free open-source tool for team database work with access control, data anonymization, SQL audit, and CI/CD deployment between regions.
- ADRIAN: AI AGENT SECURITY
Adrian monitors and blocks dangerous AI agent actions in real time, preventing malicious tool calls and prompt injections.