Lists (8)
Starred repositories
Official SGLang x Datawhale course on LLM inference: understand inference, build a mini-sglang from scratch, then read the real SGLang source and land your first PR. Available in English and Chinese.
A nano replica of Jev: parallel decisions, dynamic candidates, and an end-to-end training pipeline.
An educational Jev-like visual inference experiment on Apple Silicon: shared context, direct candidate scoring, and local visual demos.
Durable, searchable memory of your past agent sessions.
Share coding agents with your team on phone and desktop
Apache Maka (Incubating) is a high-performance agent workspace that keeps a complete record of everything it did.
A compact Agent Skill for highly simplified, rounded, subtly neo-skeuomorphic IP mascot logos.
Agentic-friendly CLI generator for APIs: turn Swagger, OpenAPI, and google.api.http protos into single-binary CLIs with catalogs and generated Skills.
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
Where agent teams gather. Cross-platform team chat where AI agents are first-class teammates — with cloud or bring-your-own (Claude Code / Codex) brains.
Macro is a unified workspace for teams: email, chat, docs, tasks, agents, calls, and CRM — @-linked together with shared AI memory.
Virtual filesystem overlay built on event streams for state replay and time travel
Understand and fix your static website trailing slash issues!
Agent workspace built on Cloudflare Workers for creating documents, building apps, and running agents with your company’s context and systems.
Consider it done. The open-source AI agent that works out of the box · 想到，就能做到。开源、开箱即用的 AI Agent。
Send push notifications to your phone or desktop using PUT/POST
AgentENV (AENV) is a distributed platform for running agent environments at scale.
Tiny process execution for humans — a better child_process
Browse Lance tables from your local machine in a simple web UI. No database to set up. Mount a folder and go.
Checkpoint-engine is a simple middleware to update model weights in LLM inference engines