- San Francisco
- dch.xyz
- @nearlydaniel
Stars
mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local
Python library for capturing audio from a specific process (PID). Built on WASAPI process loopback for Windows. Linux (ALSA/PulseAudio/PipeWire) and macOS (CoreAudio) support planned.
Run BitNet b1.58 ternary LLMs with WebGPU — in browsers and native apps
Knowledge infrastructure to make your agents smarter. Search, scrape and 550+ data providers through one API.
Watchtower — monitor, inspect, and debug all API traffic between AI coding agents (Claude Code, Codex CLI) and their APIs, with a real-time web dashboard.
Automatically mock your HTTP interactions to simplify and speed up testing
A plugin that synchronizes cursor positions between VSCode and JetBrains IDEs.
Process Compose is a simple and flexible scheduler and orchestrator to manage non-containerized applications.
🧑🏫 Automatically transform documents into beautiful slide decks
Scalable RL solution for advanced reasoning of language models
🪢 Open source AI engineering platform: AI Gateway, agent observability, evals, and prompt/skill management, built on OpenTelemetry. One open platform for every AI call and every agent. Self-host or…
A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.
Official inference framework for 1-bit LLMs
High-performance In-browser LLM Inference Engine
Omnivore is a complete, open source read-it-later solution for people who like reading.
Run agents in Obsidian - OpenCode, Codex, Claude Code etc.
Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
Vision infrastructure to turn complex documents into LLM-ready data
Aria is Your AI Research Assistant Powered by GPT Large Language Models
The official Python library for the OpenAI API
Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.