Starred repositories
Companion repository for the presentation
SGLang is a fast serving framework for large language models and vision language models.
A powerful, Flutter-inspired Terminal User Interface framework for building beautiful command-line applications in Dart.
Source code for the X Recommendation Algorithm
The AI coding agent built for the terminal.
Environments for LLM Reinforcement Learning
"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"
Git Based Memory Storage for Conversational AI Agent
Open-source LLM load balancer and serving platform for self-hosting LLMs at scale 🏓🦙
Press shortcut → speak → get text. Free and open source. More local-first apps soon ❤️
Qwen Code is a coding agent that lives in the digital world.
Embeddable library or single binary for indexing and searching 1B vectors
TerminusDB is a distributed, collaborative database designed for building, sharing, versioning, and reasoning on structured data.
Build Real-Time Knowledge Graphs for AI Agents
Letta is the platform for building stateful agents: open AI with advanced memory that can learn and self-improve over time.
Track stocks, crypto, and derivatives prices and positions in real time from your terminal
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
DSPy: The framework for programming—not prompting—language models
Portable file server with accelerated resumable uploads, dedup, WebDAV, FTP, TFTP, zeroconf, media indexer, thumbnails++ all in one file, no deps
The lean application framework for Python. Build sophisticated user interfaces with a simple Python API. Run your apps in the terminal and a web browser.
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
We write your reusable computer vision tools. 💜
Audio playback and capture library written in C, in a single source file.
XLeRobot: Practical Dual-Arm Mobile Home Robot for $660
Infrastructure that we use in every project using hooks_riverpod.
A LLM trained only on data from certain time periods to reduce modern bias