An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…

A fast, keyboard-driven Kubernetes TUI. Browse any resource, edit objects, follow logs, and shell into pods.

Hivemind turns your traces into reusable skills across agents

Like htop, but for AI coding agents. Monitor Claude Code & Codex CLI sessions, tokens, context window, rate limits, and ports in real-time.

The open-source app everyone uses to manage agents at work

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing…

Lossless Claw — LCM (Lossless Context Management) plugin for OpenClaw

a simulated network for chaos testing with testing/synctest (or not). gosimnet implements net.Conn

Your personal intelligence agent. Watches the world from multiple data sources and pings you when something changes.

Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability.

A dev agent multiplexer for git worktrees and coding agents.

Drop-in replacement for React Native's TextInput component with Markdown formatting.

SGLang is a high-performance serving framework for large language models and multimodal models.

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

Structured Outputs

Next shadcn firebase auth boilerplate

Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"

A proof-of-concept project that showcases the potential for using small, locally trainable LLMs to create next-generation documentation tools.

Bindings for mobx-state-tree and GraphQL

Cog inference for flux models

Flux diffusion model implementation using quantized fp8 matmul & remaining layers use faster half precision accumulate, which is ~2x faster on consumer devices.

Official inference framework for 1-bit LLMs

chat with private and local large language models

Author's Implementation for E-LatentLPIPS

Implementation of F5-TTS in MLX

smolLM with Entropix sampler on pytorch

Entropy Based Sampling and Parallel CoT Decoding

Entropy Based Sampling and Parallel CoT Decoding

Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch

This is the template I use to start new full-stack projects.