- All languages
- Assembly
- Astro
- Awk
- Batchfile
- BibTeX Style
- Bicep
- Bikeshed
- C
- C#
- C++
- CMake
- CSS
- Common Lisp
- Cuda
- Cython
- Dart
- Dockerfile
- Elixir
- Emacs Lisp
- Forth
- Go
- Go Template
- Groff
- HTML
- Handlebars
- Haskell
- Jai
- Java
- JavaScript
- Jinja
- Julia
- Jupyter Notebook
- Kotlin
- LLVM
- Lean
- Lua
- MATLAB
- MDX
- MLIR
- Makefile
- Markdown
- Mojo
- Objective-C
- OpenEdge ABL
- PHP
- PLpgSQL
- Perl
- PostScript
- PowerShell
- Processing
- Python
- R
- Rich Text Format
- Roff
- Ruby
- Rust
- SCSS
- Scala
- Shell
- Svelte
- Swift
- TeX
- TypeScript
- Typst
- Vala
- Vim Script
- Vue
- Zig
Starred repositories
Production-ready code examples for Telnyx AI Communications Infrastructure — Voice AI, SMS, SIP, and IoT APIs
An open-source database of AI models.
Open source order router connecting sales channels to fulfillment, built on Next.js and Keystone.js
🔥🔥 The extremely fast inference engine for decision model
AutoSwarm: Unify All Your Agents. Break Context Barriers. Watch Them Work Together for You.
A library of Agent Skills designed to work with the Stitch MCP server. Each skill follows the Agent Skills open standard, for compatibility with coding agents such as Antigravity, Gemini CLI, Claud…
Self-hosted workflows for coding-agent delivery. Orchestrate CodeBuddy, Codex and Claude Code with scripts and human approval gates. Includes Local workflows for coding assistants.
System-One-controlled full-duplex voice interaction: turn-taking as plain-language decisions judged by Jev.
Haru: a low-latency, multilingual, full-duplex spoken dialogue model
Goekdeniz-Guelmez / caramel
Forked from naklecha/caramelcaramel-1, a full-duplex speech-to-speech model trained only on audio in MLX
《深入理解 AI Infra:量化分析与系统设计》(李博杰 著)开源书稿:从硬件约束和模型架构出发,量化推导 LLM 推理与训练系统设计。含全书正文、PDF、配套计算工具与实验
Faster speech off signals for spec gen voice pipelines
caramel-1, a full-duplex speech-to-speech model trained only on audio
LiveKit real-time and server SDKs for Python
Example apps for the Apps SDK
Open full-duplex voice models that hear your tone and speak with one. One GPU with vLLM-Omni, or fully offline on a Mac with MLX. Zero-shot voice cloning, OpenAI Realtime / GPT-Live compatible, fre…
An open source design system that's fully customizable and agent ready
DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.
Hunt down social media accounts by username across social networks
This repository provides a reference for the tasks extensions to the MCP protocol, allowing for long-running operations, such as Agent communication, in MCP.
Incubation space for the MCP Triggers & Events Working Group
Auto Ontology is a Python framework for building semantic, graph-based reasoning layers over data. It enables deterministic query generation, better context retrieval, and more explainable AI for L…
DECIDE: Decision Evaluation in Calls — Intent, Dialogue and Emotion. Public evaluation toolkit and six audio previews; full benchmark held privately.
微信聊天记录一键转发到 AI Agent 与 Obsidian 的原生 macOS 工具
A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings
Phonon 31M text-to-speech on WebGPU, with word timings
Connect AI agents to real iPhones and Androids