The open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills.

Elixir grammar for tree-sitter

An efficient AI coding agent

Command-line JSON processor

Set up your Stremio account with just a few clicks

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

Open-source AI agent. Lives in your terminal.

Contain AI coding agents within secure container sandboxes that limit filesystem access and control network communication.

AI agents built for coworking.

Browse Mastodon, Bluesky, X, Misskey, Nostr and RSS all in one app. One timeline, all your accounts, cross-post everywhere.

Message to Nostr, Bluesky, and Mastodon from one place.

Using BFS & DFS like techniques over LLMs for iteratively exploring the solution search space at scale.

Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware

A specialized Claude Code workspace for creating long-form, SEO-optimized blog content for any business. This system helps you research, write, analyze, and optimize content that ranks well and ser…

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 …

The orchestration layer for AI coding agents — persistent memory, conductor, dashboard, and multi-agent workflows. Works with Claude Code, Codex, OpenCode, Cursor. Apache 2.0.

End-to-end token optimizer for Claude Code, Copilot CLI & OpenCode. Up to 95% bash compression, cross-call redundancy, caveman persona, markdown compressor. Zero new dependencies.

SageOx is the hivemind for agentic engineering

llama.cpp fork with TQ3_1S/4S CUDA kernels — 3.5-bit WHT quantization achieving Q4s quality at 10% smaller size. Based on RaBitQ-inspired Walsh-Hadamard transform. Enables 27B models on 16GB GPUs w…

DFlash: Block Diffusion for Flash Speculative Decoding

Find, benchmark and install in CLI 200+ FREE coding LLM models across 20+ providers in real time

Graph-powered code intelligence, multi-agent coding with codebase-aware AI. No more grep & pray

Craft quality software with AI discipline. Spec-driven development plugin for Claude Code and Opencode — quality gates, adversarial testing, and evidence capture.

A 3D raycasting engine running inside a TrueType font's hinting virtual machine

An operating system

🐈 A collection of LLM inference providers and models

PersonaPlex code.