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

Highlights

  • Pro

Block or report liusongxiang

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

DeepSeek Harness: Everything is a Plugin.

TypeScript 109,663 10,575 Updated Aug 13, 2026

A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents

JavaScript 2,147 170 Updated Aug 15, 2026

Bringing real-time voice to life.

TypeScript 891 82 Updated Aug 13, 2026

Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

Python 8,083 676 Updated Aug 14, 2026

Open Frontier Intelligence

8,452 656 Updated Aug 6, 2026

Open Source framework for voice agents, multimodal apps, and realtime AI. Maintained by Daily and the community.

Python 14,122 2,462 Updated Aug 15, 2026

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Andr…

C++ 14,193 1,629 Updated Aug 13, 2026

A framework for building realtime voice AI agents 🤖🎙️📹

Python 13,016 3,560 Updated Aug 14, 2026

Extracted system prompts from Anthropic - Claude Fable 5, Opus 5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-5.6-Sol, Codex. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravity. xAI - Grok, Curso…

JavaScript 62,953 10,335 Updated Aug 15, 2026

MOSS-Transcribe-Diarize 0.9B is an open-source SOTA end-to-end audio understanding model for long-form multi-speaker transcription, diarization, timestamps, and acoustic event awareness.

Python 1,496 81 Updated Jul 24, 2026

Awesome GUI Agent Paper List

TypeScript 883 41 Updated Aug 14, 2026

你想蒸馏的下一个员工,何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.

Python 30,658 4,224 Updated Jul 27, 2026

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

202,658 20,800 Updated Apr 20, 2026

GLM-5: From Vibe Coding to Agentic Engineering

6,964 897 Updated Aug 11, 2026

A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models

667 21 Updated Aug 15, 2026

Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.

HTML 21,388 1,471 Updated Aug 15, 2026

GLM-OCR: Accurate × Fast × Comprehensive

Python 7,282 658 Updated Apr 21, 2026

This is a collection of resources for computer-use GUI agents, including videos, blogs, papers, and projects.

577 44 Updated Apr 15, 2026

Scalable pipeline for synthesizing verifiable RLVR training data for computer-use agents

Python 186 17 Updated Aug 13, 2026

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

TypeScript 6,728 1,050 Updated Aug 15, 2026

Awesome List for Agentic RL

HTML 1,780 71 Updated Aug 11, 2026

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

Rust 127,370 8,694 Updated Aug 15, 2026

Use Codex from Claude Code to review code or delegate tasks.

JavaScript 31,901 2,195 Updated Jul 8, 2026

The agent that grows with you

Python 230,906 45,814 Updated Aug 15, 2026

Synthetic GUI Pointing Data Generation

Python 14 2 Updated Apr 13, 2026

OpenClaw-RL: Train any agent simply by talking

Python 5,633 607 Updated May 23, 2026

A curated list of resources about AI agents for Computer Use, including research papers, projects, frameworks, and tools.

1,733 135 Updated Sep 26, 2025

[NeurIPS 2025 Spotlight] OpenCUA: Open Foundations for Computer-Use Agents

Python 818 107 Updated May 25, 2026

Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps

Python 47,023 8,311 Updated Aug 15, 2026

Secure, Fast, and Extensible Sandbox runtime for AI agents.

Python 13,229 1,136 Updated Aug 15, 2026
Next