Tag
Explore by tags
Converts PDF, Office docs, EPUB, images, audio, HTML and ZIP archives into structured Markdown for LLM pipelines, preserving headings, tables and links instead of visual layout. Adds optional OCR, audio transcription and LLM image captions.
Brings an agentic chat experience to the terminal: describe a task in natural language and it plans, edits files, and runs commands to build the app. Written in Rust, ships on macOS and Linux. Now succeeded by the closed-source Kiro CLI.
A self-hostable virtual companion: a VRM or Live2D character you own that voice-chats in real time, plays Minecraft and Factorio, and runs models in-browser via WebGPU or across 25+ LLM providers like Ollama, OpenAI, and Claude.
Generates structured, streaming UIs from LLM output and renders them in React using a compact OpenUI Lang, built component libraries, and chat surfaces; claims up to ~67% token savings vs JSON and includes a playground and CLI.
Companion resources for Chip Huyen's AI Engineering book: chapter summaries, study notes, prompt examples, case studies, and a few analysis scripts. Focuses on engineering practices for adapting foundation models to production rather than step-by-step code tutorials.
Runs iterative, fully-local web research loops using locally hosted LLMs (via Ollama or LMStudio): it auto-generates search queries, gathers and summarizes results, reflects to find gaps, re-queries, and emits a final markdown report with sources.
A library of specialized AI agents that automate data science steps: loading, cleaning, wrangling, feature engineering, SQL queries, EDA, and ML modeling via H2O and MLflow. Higher-level analyst workflows chain these under a supervisor agent.
A 100-line LLM framework built on one graph abstraction of nodes and flows, with zero dependencies and no vendor wrappers. The tiny core composes agents, workflows, and RAG, and is small enough for a coding agent to read and extend on its own.
A 671B-parameter Mixture-of-Experts language model (37B activated) trained on 14.8T tokens with 128K context, FP8-first training, a Multi-Token Prediction module, and Hugging Face weights—focused on efficient MoE training and long-context use cases.
Captures, transcribes, and summarizes meetings entirely on the user's machine with real-time local transcription and speaker diarization. Privacy-first design keeps audio, transcripts, and models local; supports Ollama, Claude, Groq, OpenRouter or custom OpenAI-compatible endpoints.
Open-weight Mixture-of-Experts LLM with 671B total parameters but 37B activated per token, trained on 14.8T tokens for 2.788M H800 GPU-hours. Matches leading closed models at a fraction of typical training cost via FP8 and architectural tricks.
Simulates a trading firm using LLM agents in specialized roles — fundamentals, sentiment, news and technical analysts feed bull/bear researcher debates, then a trader and risk team decide. Works across US, global and crypto markets and 10+ LLM providers.