Skip to content
View xylcbd's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report xylcbd

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.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. 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

Starred repositories

Showing results

SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.

Python 16,047 1,497 Updated Aug 15, 2026

Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local

C 66,532 4,203 Updated Aug 8, 2026

The open source coding agent.

TypeScript 197,814 25,480 Updated Aug 16, 2026

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

Python 13,616 1,487 Updated Aug 13, 2026

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Python 62,134 10,710 Updated Nov 12, 2025

LLM training in simple, raw C/CUDA

Cuda 30,812 3,734 Updated Jun 26, 2025

Provide with pre-build flash-attention 2 and 3 package wheels on Linux and Windows using GitHub Actions

Python 1,690 78 Updated Aug 16, 2026

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

202,778 20,809 Updated Apr 20, 2026

from vibe coding to agentic engineering - practice makes claude perfect

HTML 64,531 6,411 Updated Aug 15, 2026

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…

Python 106,742 10,383 Updated Aug 15, 2026

The agent that grows with you

Python 231,103 45,903 Updated Aug 16, 2026

AI agents running research on single-GPU nanochat training automatically

Python 93,907 13,312 Updated Mar 26, 2026

Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.

Python 72,064 6,495 Updated Aug 16, 2026

slime is an LLM post-training framework for RL Scaling.

Python 8,041 1,148 Updated Aug 14, 2026

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…

Python 80,057 10,959 Updated Aug 15, 2026

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

Python 74,311 12,033 Updated Aug 15, 2026

A community collection of OpenClaw use cases for making life easier.

31,662 2,724 Updated Mar 24, 2026

The open agent skills tool - npx skills

TypeScript 28,970 2,462 Updated Aug 14, 2026

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

TypeScript 386,405 81,215 Updated Aug 16, 2026

IronClaw is an Agent OS focused on privacy, security and extensibility

Rust 12,603 1,488 Updated Aug 16, 2026

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

Cuda 3,645 479 Updated Jan 17, 2026

青稞Talk

218 2 Updated Jul 27, 2026

🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

TypeScript 33,155 3,572 Updated Aug 15, 2026

Speed Always Wins: A Survey on Efficient Architectures for Large Language Models

406 33 Updated Nov 11, 2025

GRID: Generative Recommendation with Semantic IDs

Python 726 126 Updated Oct 15, 2025

A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.

Python 3,240 451 Updated Aug 15, 2026

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

C++ 6,283 1,085 Updated Aug 15, 2026

We write your reusable computer vision tools. 💜

Python 49,428 4,671 Updated Aug 14, 2026

[ICLR 2026] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification.

Python 1,096 26 Updated Aug 1, 2026

Implementation for FP8/INT8 Rollout for RL training without performence drop.

Python 309 23 Updated Nov 7, 2025
Next