-
PingCAP
- San Francisco Bay Area
- @shenli3514
- in/li-shen-876b091a
Stars
Runtime-state database for AI agents: persistent session logs, replay, forks, and artifacts.
SGLang is a high-performance serving framework for large language models and multimodal models.
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
Persistent, forkable workspaces for AI agents. Git-aware snapshots, verified resets, and control over what survives across sessions.
The open-source alternative to Claude Cowork (powered by opencode)
Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.
A local-first toolkit for testing agent experience in Agent-Native developer tools.
A Kawaii React UI component library 一个可爱的 React UI 组件库
DeepSeek Harness: Everything is a Plugin.
An extremely fast Python package and project manager, written in Rust.
White-box LLM post-training course: SFT, DPO, GRPO/RLVR, Agent SFT, and Mini Agent RL on one 16 GB GPU.
Write HTML. Render video. Built for agents.
The open-source SDK for bringing any agent into any chat platform: Slack, Microsoft Teams, Discord, Telegram - with native, Interactive UI.
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
MoonEP: A Perfectly Balanced Expert Parallelism Library via Dynamic Redundant Experts
The Little Book of Reinforcement Learning
Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering.
Curated infrastructure resources for building production AI agents: runtimes, sandboxes, workspaces, tool protocols, security, observability, and evaluation.
Fast and memory-efficient exact attention
Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability.
AI-agent skills for distributed-systems testing
Skardi is a self-improving context framework for ai agents
Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.