Stars
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Fast BM25 search in Python, powered by Numpy and Numba
Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning
A vector index built on TurboQuant, written in Rust with Python bindings
🚀 Ultra Recipe for Training Long-Horizon Search Agents - matching frontier AI's search capability with a 20B model + stateful harness
The absolute trainer to light up AI agents.
An open source benchmarking framework for IT automation
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
Data visualization for Inspect AI large language model evalutions.
Inspect: A framework for large language model evaluations
Brand-New Spicetify Lyrics Plugin with AI-Based translate and beautiful design
The official repo of "WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents"
SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis
Batteries-included eval framework for search APIs
[NAACL 2025] Official Code Repository for the paper "Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrieval"
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
Repo for paper "Agentic-R: Learning to Retrieve for Agentic Search" (ACL 2026 Findings)
Python tool for converting files and office documents to Markdown.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with C…
Native macOS debug GUI for apfel — Apple Intelligence from the command line
The free AI already on your Mac. CLI tool, OpenAI-compatible server, and interactive chat — all on-device via Apple Intelligence. No API keys, no cloud, no downloads.
Super basic implementation (gist-like) of RLMs with REPL environments.
General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
한국인을 위한 스킬 모음집 - SRT, KTX, 카카오톡, 한글과컴퓨터, 날씨, 미세먼지, 법령, 주식정보, 조선왕조실록, KBO, K-리그, LCK, 특허 검색, 토스 증권, 맞춤법 검사, 중고차 가격, 쿠팡, 네이버 블로그, 다이소, 올리브영, 택배 송장 조회 등등...