Develop and deploy smart contracts using natural language.
- ai-web3
- web3-agents
- web3-ai
- agents-web3
99,825 visible repositories in the index
1,969–1,992 of 2,152 · Most stars
Develop and deploy smart contracts using natural language.
Set up Claude Code once. Your whole company gets it. Self-hosted Claude Code and Codex with your company files, team skills, MCP and per-person folder permissions.
Write like anyone famous. 65+ famous voices and styles for your agent over MCP, and a funny AI code review GitHub Action: your PRs reviewed by Gordon Ramsay. Every source linked.
The source code of the https://speed.skk.moe
Pulp is an open source sample manager
Tell your coding agent which dependencies changed after its training cutoff. Diffs types and changelogs, writes a short block into AGENTS.md / CLAUDE.md.
Payload plugin for extending lexical typography options (Text color, Font size, Letter spacing, Line height, Font Family)
The 30 MB open-source edge AI agent runtime. Run AI agents offline on Linux (Raspberry Pi, Jetson). GPIO, UART, MQTT as first-class nodes. Industrial protocols (OPC-UA, Modbus) on the roadmap.
A Playwright JSON test results reporter that follows the CTRF schema
A fully typed, lightweight, and customizable terminal emulator component for Svelte 5. Features a virtual file system, custom commands, themes, and autoplay mode for demos. 🚀
Weave GraphQL schema and resolvers using runtime types in TypeScript/JavaScript
Source-available AI assistant with persistent bots that share conversations and work on isolated computers. Self-hosted, with web, desktop, and mobile apps.
TranslatedA mobile web app where the hamster Mugi (むぎ) practices Japanese conversation with you one-on-one. Core idea: the LLM outputs structured replies using a JSON Schema, with the Japanese lines and the Chinese tips in separate fields, and the frontend uses partial JSON parsing to display the reply as it streams in; prompt caching and voice caching are maintained even during long chats. Kanji readings are annotated by the LLM, and any that it misses are filled in by kuromoji on the server side. Corrections are automatically saved into a tips notebook, so you can practice speaking until you have mastered them. For voice, you can choose local VOICEVOX or cloud Google/Azure, and the keys stay only on the local server. Developed in collaboration with Claude Code (Opus 5.5); originally for personal use, it was released as open source with a brand-new git history that contains no personal data or third-party assets. Records of each decision are in docs/decisions/.
Tomorrow-AI 妥啦 · Personal AI companion for noncommercial self-hosting
Helicon-Focus: Focus Stacking and Depth-of-Field Blending Software for Windows
Movavi Screen Capture: Windows Video Recorder for Tutorials and Calls
Statgraphics: Advanced Statistical Analysis and Data Visualization for Windows
Shrink 500+ Videos in Batches with GPU-Accelerated Quality Compression
Add PST File to MS Outlook: Windows Utility for Bulk PST Import and Data Management
Keeper Password Manager: 256-bit AES Encryption and Two-Step Authentication for Secure Data Storage
Cinema-4d-Studio: Advanced 3D Modeling and Animation for Windows
functional/point-free utils for JavaScript
Pagico: Task Manager for Windows with Deadline Tracking and Tagging System
AD FastReporter: Windows system tuning utility for customizable Active Directory reporting and data