Explore the directory

A production skill of 29 scripts for building, testing, and automating iOS apps with Claude Code, wrapping Xcode builds and simulator interaction to save the token and context cost of raw xcodebuild output.

• Agent skills
• Mobile

A context layer that keeps CLAUDE.md, Cursor rules, AGENTS.md, and Copilot instructions synchronized to a codebase, writing them from a pre-commit hook and mirroring shared skills, rules, and MCP servers across agents.

• Agent skills

An MCP server that connects Claude, Cursor, and other MCP clients to a SearXNG instance, giving them privacy-respecting web search, page reading, and query-suggestion tools.

• MCP servers

An extensible LLM quantization toolkit supporting GPTQ, AWQ, GGUF, FP8, and other formats across NVIDIA, AMD, Huawei Ascend, and Intel hardware, integrated with Transformers, vLLM, and SGLang.

• Models
• Inference

A local AI agent framework that turns a phone into an on-device agent runtime, running small vision-language models directly on the device and calling native mobile skills such as Calendar, Reminders, and Health.

• Agent frameworks
• Mobile

A self-hosted, E2B-compatible sandbox platform for AI agents where sandboxes persist indefinitely and cost nothing while idle, instead of being disposable cloud sandboxes billed by the second.

• Agent frameworks
• Containers

A collection of installable Agent Skills for AI coding agents that render motion-graphics and video effects, such as progress-ruler animations, fisheye screen-capture effects, logo-to-motion conversion, and Remotion-based visualizations.

• Agent skills
• Generative media

A community-built Chrome, Edge, and Chromium side panel that connects a browser's active web context to a local Hermes Agent gateway, a self-hosted remote gateway, or Hermes Cloud.

• Coding agents

A self-hosted search gateway for AI agents that exposes a single Perplexity-compatible search API backed by several providers, falling back to the next one automatically if one is rate-limited or down.

• RAG
• LLM gateways

An optimal control library for robots under contact sequences, using differential dynamic programming solvers to compute optimal trajectories and feedback gains.

• Libraries

An archived TypeScript-first framework for building serverless, composable AI agents with memory and tools, developed on the local machine and deployed with one command, now succeeded by a set of AI primitives.

• Agent frameworks

A self-hosted runtime for building, orchestrating, running, observing, evaluating, and controlling agentic systems on a company's own infrastructure, composed visually or generated with AI.

• Agent frameworks

A curated list of more than 130 terminal-native AI coding agents and the harnesses that orchestrate, sandbox, or extend them, covering open-source, platform, and closed-source tools.

• Coding agents
• Curated lists

A PyTorch-native inference engine built on Diffusers that adds hybrid cache acceleration and parallelism, quantization, and CPU offload for diffusion transformer (DiT) image and video models.

• Inference
• Generative media

A method pack that makes AI coding agents plan against a project's real baseline before editing, prove completion with fresh verification evidence, and skip ceremony on simple tasks, across Codex, Claude Code, and other skill-aware hosts.

• Agent skills

An MCP server that lets an AI agent connect to and manage Jupyter notebooks in real time, running against a local Jupyter install, JupyterHub, or a scalable hosted code sandbox from local to the cloud.

• MCP servers
• Data engineering

A web-based client for managing Claude Code projects, browsing full conversation history, monitoring running tasks in real time, and resuming sessions, with a built-in terminal for running commands.

• Coding agents

An agent skill distilled from a specific professor's teaching style, built from hundreds of lecture transcripts, a knowledge graph of his course material, and an authorized interview used to calibrate and correct the skill's assumptions.

• Agent skills

An open-source, cloud-native runtime, SDK, and CLI for agentic AI that gives every AI resource, such as an LLM, vector database, storage, or cache, one unified API across providers so agent logic can be written once and run anywhere.

• Agent frameworks

An AI coding agent that edits code by symbol rather than by string, using AST surgery, a full LSP, and a persisted code graph, then checks its own edits with the project's typecheck, lint, and tests.

• Coding agents

A free, open-source native Mac system-maintenance app for junk cleanup, app uninstalling, duplicate finding, and disk analysis, with a built-in MCP server so AI agents can query and clean the system with consent.

• MCP servers
• Desktop utilities

An autonomous agent that runs deep-learning experiments around the clock on a local machine, a remote server over SSH, or a Slurm cluster, tracking real job outcomes with constant-size memory and zero-cost monitoring.

• Agent frameworks
• Models

A Chinese-language companion to DeepLearning.AI's Agentic AI course series, providing translated course content, structured notes, and walkthroughs of the example code for each module.

• Tutorials

A high-performance AI search and retrieval platform built for retrieval-augmented generation, semantic search, and hybrid search, designed to hold up to a billion vectors on a single node.

• RAG
• Databases