Skip to content
View lxe's full-sized avatar
🦀
Crab
🦀
Crab

Sponsoring

@ljharb
@Jaex
@kovidgoyal

Block or report lxe

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

π^4: A Foundation Model for 4D Scene Geometry and Motion

Python 277 10 Updated Nov 18, 2026

Turn your coding agents into research agents

Rust 8,226 565 Updated Nov 19, 2026
TypeScript 2 Updated Nov 18, 2026

Omarchy bar plugin for Orble sandboxes: boxes, SSH, desktops, exit node, SSH keys and credit, through the orble CLI

QML 2 Updated Nov 19, 2026

fast and simple push to talk dictation

Python 49 6 Updated Nov 14, 2026

Adaptive HF Modem for amateur radio.

Rust 12 2 Updated Nov 19, 2026
C++ 58 14 Updated Nov 19, 2026
Python 5 Updated Oct 23, 2026

Manina AI: let an AI model use a real iPhone with a $7 ESP32: AirPlay eyes, USB HID hands, any OpenAI-compatible vision model. No Mac, no developer account, no jailbreak.

Swift 5,096 698 Updated Nov 18, 2026

See and operate an unmodified iPhone from a Linux PC: AirPlay mirror in, Bluetooth HID mouse/keyboard out, plus a CLI and skill for agents.

Python 686 65 Updated Nov 15, 2026

let your agent control your phone

Python 5,103 529 Updated Nov 9, 2026

Monitoring platform for ML teams building real‑world AI at scale.

Python 180 2 Updated Nov 19, 2026

Auto researching harness that burns through everything.

TypeScript 107 15 Updated Nov 17, 2026

Drop-in OpenAI-compatible cache that replays repeated computer-use and agent workflows at near-zero cost.

JavaScript 53 12 Updated Sep 20, 2026

Connect your agents & product to 1,000 APIs.

TypeScript 13,262 1,540 Updated Nov 19, 2026

A native macOS auto-research harness for Codex and Claude Code. Pick an open research project and press Play.

Python 84 15 Updated Nov 18, 2026

Deployment & experimentation of LLM inference at production scale (P/D disaggregation, KV offloading, parallelism, and autoscaling).

Jupyter Notebook 66 8 Updated Sep 26, 2026

Open Coding agent. Shift + Tab Go Team Mode: a team of small models, frontier results.

Go 412 48 Updated Nov 18, 2026

🔥 Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser sandbox that lets you automate the web without worrying about infrastructure.

TypeScript 7,989 1,015 Updated Nov 19, 2026

Browser automation CLI for AI agents

Rust 52,762 3,692 Updated Nov 19, 2026

The best way to control Claude Code, Codex and more from any computer or phone

TypeScript 65,792 11,509 Updated Nov 19, 2026

Batched DeepSeek-V4.1-Flash inference on 8x V100 (sm_70): low-bit lookup formats, split experts, NVLink collectives

Rust 10 2 Updated Oct 25, 2026

Lucebox inference engine for heterogeneous hardware & consumer GPUs

C++ 3,018 299 Updated Nov 18, 2026

Run GLM-5.3 (744B), GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one dashboard, OpenAI- and Anthropic-compatible API.

C++ 3,053 427 Updated Nov 19, 2026

Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s on agent tasks, ~41 in fast mode, 512K context. Plus GLM-5.3-Flash, Qwen3.8 an…

C++ 539 66 Updated Nov 19, 2026

Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.

C++ 45,799 5,080 Updated Nov 18, 2026

The open agent skills tool - npx skills

TypeScript 40,035 3,540 Updated Nov 17, 2026

A hierarchical inference engine for frontier MoE models: hot experts on the GPU (CUDA, Vulkan), warm ones in RAM, cold ones streamed from NVMe. Written in C, runs on the hardware you already own.

C 52,085 6,302 Updated Nov 18, 2026

DeepSeek-V4.1-Flash-1017 (552B MoE + 196B Engram) on 2x RTX 3090 + 128 GB RAM. Rust + CUDA, T16 quantization. 40+ tok/s measured with expert deferral + FP8 projections.

Rust 107 24 Updated Nov 4, 2026

SolidCraft: an open-source parametric 3D CAD application built in pure Rust. Desktop, web, and automation through MCP.

Rust 17,181 2,386 Updated Nov 19, 2026
Next