Lists (1)
Starred repositories
[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation
CPU-only data quality toolkit for LLM instruction tuning. Dedup, PII detection, contamination checking, quality scoring.
A plugin for Claude Code and Codex that turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.
A kernel library written in tilelang
DSPy: The framework for programming—not prompting—language models
TeamClaw, AI Agent Desktop Workspace
LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional RAG (retrieve-and-answer from scratc…
🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models
CADAM is the open source text-to-CAD web application
AI You Control: Choose your models. Own your data. Eliminate vendor lock-in.
Smart Model Routing for Personal AI Agents. Cut Costs up to 70% 🦞👧🦚
ripgrep recursively searches directories for a regex pattern while respecting your gitignore
A smarter cd command. Supports all major shells.
Code search MCP for Claude Code. Make entire codebase the context for any coding agent.
A lightweight, lightning-fast, in-process vector database
GitNexus: The Zero-Server Code Intelligence Engine - GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a GitHub repo or ZIP file, and get an interactive …
Mobile first batteries included web ui for sst/opencode. Git integration, in browser terminal, isolated workspaces.
OpenViking is an open-source context database designed specifically for AI Agents(such as openclaw). OpenViking unifies the management of context (memory, resources, and skills) that Agents need th…
OpenCode plugin for Morph - FastApply, WarpGrep codebase search, FlashCompact
Paste any GitHub URL → interactive architecture map. See how files connect, find what breaks if you change something. No install, no accounts — runs entirely in your browser.
📄 Production-ready MCP server for PDF processing - 5-10x faster with parallel processing and 94%+ test coverage
An MCP server plus a CLI tool that indexes local code into a graph database to provide context to AI assistants.
I set out to implement TurboQuant (PolarQuant + QJL) for Gemma 4 31B's KV cache — a 31 billion parameter model running on a single Mac. It doesn't work on this model. What I built instead is faster.