Lists (2)
Stars
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware
Create 💎 beautiful animations from boring screen recordings within ⏳ seconds
🪐 Markdown with superpowers: from ideas to papers, presentations, websites, books, and knowledge bases.
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
LLM evals to test open-source inference providers
Agent S: an open agentic framework that uses computers like a human
📄 PDF ->.MD/.JSON API & SDK for PaddleOCR-VL with structured data extraction. Self-hostable.
[CVPR 2025] A Comprehensive Benchmark for Document Parsing and Evaluation
OCR model that handles complex tables, forms, handwriting with full layout.
A framework-agnostic, git-native standard for defining AI agents
Python bindings for access to the on-device model at the core of Apple Intelligence through the Foundation Models framework
BullshitBench measures whether AI models challenge nonsensical prompts instead of confidently answering them, created by Peter Gostev.
Hundreds of models & providers. One command to find what runs on your hardware.
An HTTP/1.1 client, written from scratch for Node.js
Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork
Rivet Actors are the primitive for stateful workloads. Built for AI agents, collaborative apps, and durable execution.
PDF exporter for HTML presentations
Let coding agents diagnose and fix your React code
resume any AI coding session in another tool — Claude Code, Copilot, Gemini, Codex, Cursor
A blazing fast AI Gateway with integrated guardrails. Route to 200+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Open-source multi-agent platform that structures software engineering as a coordinated team of specialized AI agents. It enforces strict role separation, isolated execution sandboxes, structured co…
SGLang is a high-performance serving framework for large language models and multimodal models.
🌈 React for interactive command-line apps
WebMCP starter demo — a DoorDash-style food delivery app with 9 AI agent tools (imperative + declarative)