- All languages
- Assembly
- Astro
- Awk
- Batchfile
- Bikeshed
- C
- C#
- C++
- CMake
- CSS
- Clojure
- CoffeeScript
- Cuda
- Dart
- Dockerfile
- Elixir
- Go
- Go Template
- Groovy
- HTML
- Java
- JavaScript
- Jinja
- Jupyter Notebook
- Kotlin
- Logos
- Lua
- MATLAB
- MDX
- Makefile
- Markdown
- Mathematica
- MoonBit
- Nunjucks
- Objective-C
- Objective-C++
- PHP
- PLSQL
- PLpgSQL
- Perl
- PostScript
- PowerShell
- Python
- QML
- R
- Red
- Rich Text Format
- Ruby
- Rust
- SCSS
- Scala
- Shell
- Solidity
- Standard ML
- Stylus
- Svelte
- Swift
- SystemVerilog
- TeX
- TypeScript
- Vim Script
- Visual Basic .NET
- Vue
- Wikitext
- Zig
Starred repositories
Meta-Framework of Spatiotemporal Composability
DeepSeek Harness: Everything is a Plugin.
The fastest browser for AI agents to run browser automation, built for sharing your logged-in browser state with your AI agents, like Codex or Claude Code, without disturbing you. Zero cost, zero c…
Fork of NikoDemon80's H3 Motion Context adding multi-reference-compatible timeline audio and example workflows for Ref2VA, FL2VA, and music-video lip-sync.
A source-available Codex skill for distilling photographs into sparse editorial abstractions.
Make any agent harness multimodal-native.
Graph-Native Infrastructure for Context and Accountable AI Systems
Kition brings Markdown documents, Data table, a tool-using AI agent, browser research, and visual workflows into one desktop workspace.
ComfyUI MiniMax H3 Director workflow
Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF to clean Markdown. Built in Rust, with Node.js and Python bindings.
Spectrum-based acceleration for ComfyUI’s native MiniMax H3 audio-video model. Forecasts post-transformer features with Chebyshev ridge regression to skip selected transformer evaluations, with ada…
A powerful, ComfyUI Custom node automation suite for generating cinema-production-grade prompts explicitly formatted for the **MiniMax H3 Video Generation System**.
A timeline editor for MiniMax H3 inside ComfyUI - storyboard prompts, first/last keyframes, image/video/audio references, joint audio, live sampling preview, retakes and shot chaining.
The AI agent that interacts with you in the real world.
Fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thre…
Turn Codex threads into an organization of long-lived domain agents.
Surge-style whole-home gateway and control plane for macOS with IPv4/IPv6 support— mihomo TUN, dnsmasq-powered DHCP/DNS, per-device routing, and an agent-friendly validation workspace.
A framework for building realtime voice AI agents 🤖🎙️📹
DeepSeek-V4-Flash-0731 deployment on 2x RTX PRO 6000 Blackwell (SM120) with vLLM PR #41834 fork + DSpark speculative decoding. 无海外网络环境下的镜像源解决方案
A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents
A native macOS management tool for the first-generation DJI 4G module.
OpenMinis — The AI Agent app across platforms. Fully free and open source.
A simple, decentralized mesh VPN with WireGuard support.
☁️ Open file browser for S3, R2, and other storage backends.
Build local voice agents with open-source models
Open-source HyperFrames compositions behind HeyGen's product launch videos.
Consider it done. The open-source AI agent that works out of the box · 想到,就能做到。开源、开箱即用的 AI Agent。
Silero VAD: pre-trained enterprise-grade Voice Activity Detector