- Los Angeles
-
08:32
(UTC -07:00) - https://sanskar.dev
- in/sanskar-thapa
Highlights
- Pro
Lists (1)
Sort Name ascending (A-Z)
Stars
Hivemind turns your traces into reusable skills across agents
A self-improving RLM agent for coding workflows and long-running autonomous tasks.
Community model zoo for Apple Core AI (iOS/macOS 27): 57 models — LLM, VLM, OCR, ASR, TTS, image/video/music gen, forecasting — each gated against its source model and shipped with the recipe that …
Model export recipes, Python primitives, and Swift runtime utilities for on-device AI
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
A convenient CLI to streamline LiteRT related development workflows, including converting, quantizing, compiling, managing, running, benchmarking and visualizing LiteRT (TFLite) models on various h…
3x faster speeds on MLX | Qwen 3.6 27B | Native MTP Speculative Decoding On Apple Silicon With No External Drafter.
AI agents running research on single-GPU nanochat training automatically
Autonomous experiment loop extension for pi
DFlash: Block Diffusion for Flash Speculative Decoding
Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models
A curated directory of open-source AI agent skills for Swift and Apple platform development.
LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
Official Code Repository for the paper "Distilling LLM Agent into Small Models with Retrieval and Code Tools"
Memory Sparse Attention - A scalable, end-to-end trainable latent-memory framework for 100M-token contexts.
(Development of Screenize is currently paused) Open-source macOS screen recording app with auto-zoom, cursor effects, and timeline editing — Screen Studio alternative.
An intelligent system for detecting, classifying, and analyzing edge cases in autonomous driving data from the Waymo Open Dataset. Features an interactive React dashboard and AI-powered analysis us…
SwiftUI agent skill for Claude Code, Codex, and other AI tools.
Python bindings for access to the on-device model at the core of Apple Intelligence through the Foundation Models framework
nothing just an experimental component
Production ready toolkit to run AI locally