SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.

专业的短剧剧本创作skill,从选题立项到分集撰写、质量自检、合规审核、海外出海，覆盖短剧剧本生产全流程。

将被语言阻隔的作品，带到读者的语言中。Bringing literature into your language.

Effortlessly manage Git worktrees in Visual Studio Code! 🚀

Mine the dialogue out of your coding-agent session logs: timelines, transcripts, cross-examination, and (eventually) agent-as-judge evaluation

The memory-first, self-improving agent harness built on EverOS, with MiroThinker-powered deep research and reasoning.

Open-source graph database superpowers for your existing Postgres data.

DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms

The agent that grows with you

🎨 The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, slides, images & video — real files, …

Kimi Code CLI — The Starting Point for Next-Gen Agents

Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and VPS.

Memory library for building stateful agents

Algorithm powering the For You feed on X

Communicate with an LLM provider using a single interface

Open-source game engine with a C++17 / Vulkan runtime and a Python production layer.

Raspberry Pi Pico 2 W port of Claude Desktop Hardware Buddy, with BLE firmware and a 3D-printable case.

Thirteen editorial diagram types for Claude Code. Self-contained HTML + SVG. No shadows, no Mermaid-slop.

Reference and an example for the Bluetooth API for makers in Claude Cowork & Claude Code Desktop

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

You like pytorch? You like micrograd? You love tinygrad! ❤️

The Native Terminal Emulator with a builtin AI Harness

Batteries for your Pydantic AI agent.

agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes.

"Advanced" agentic dev patterns — we made the mistakes in production so you can make them in staging.

An open-source database of AI models.

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

Python Type Checker / Language Server

Memory Sparse Attention - A scalable, end-to-end trainable latent-memory framework for 100M-token contexts.