GitHub
2026-03-30
CowAgent是基于大模型的超级AI助理,能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、拥有长期记忆并不断成长,比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页等接入,可选择OpenAI/Claude/Gemini/DeepSeek/ Qwen/GLM/Kimi/LinkAI,能处理文本、语音、图片和文件,可快速搭建个人AI助理和企业数字
Read more
GitHub
2026-03-30
⚡ Flip LLM API — Access 35+ AI models (Mistral, Llama 4, DeepSeek, GLM, Qwen 3, Kimi K2, Phi 3, Minimax) through a single unified REST API. Features session memory via Firebase RTDB, custom system pro
Read more
GitHub
2026-03-30
Open Source Continuous Inference Benchmarking Qwen3.5, DeepSeek, GPTOSS - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72 vs H100 & soon™ TPUv6e/v7/Trainium2/3
Read more
GitHub
2026-03-30
Dùng chatgpt, gemini, qwen, deepseek để search và tổng hợp thông tin
Read more
GitHub Releases
2026-03-29
# v1.0.0 (2026-03-27)
## 🎉 Initial Release
OpenClaw Zero Token is a fork of OpenClaw that enables **zero API token costs** by leveraging browser automation to access mainstream AI platforms for
Read more
GitHub
2026-03-29
chinese_chess4human_vs_ai is a Python Xiangqi game for Human vs AI play. It supports legal move validation, turn management, captures, and check/checkmate logic. Users must configure their own api_key
Read more
arXiv
2026-03-27
Converting a pretrained Transformer into a more efficient hybrid model through distillation offers a promising approach to reducing inference costs. However, achieving high-quality generation in disti...
Read more
GitHub Releases
2026-03-26
2.9.14
## What's Changed
* Merge latest zed upstream paying close attention to and u... by @lukemarsden in https://github.com/helixml/helix/pull/1998
* fix: allow multiple viewers to stream the s
Read more
GitHub Releases
2026-03-25
## What's Changed
* Merge latest zed upstream paying close attention to and u... by @lukemarsden in https://github.com/helixml/helix/pull/1998
* fix: allow multiple viewers to stream the same sessio
Read more
GitHub
2026-03-16
A multi-agent competitive framework where leading Chinese LLMs (such as Qwen, DeepSeek, and ERNIE) play dual roles as mystery-solvers and judges. The project evaluates models' strategic reasoning and
Read more