Starred repositories
AgentOpt automatically finds the best LLM model combination for each step of your agent — optimizing for accuracy, cost, and latency.
🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
"OpenHarness: Open Agent Harness with a Built-in Personal Agent--Ohmo!"
Memory Sparse Attention - A scalable, end-to-end trainable latent-memory framework for 100M-token contexts.
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
The absolute trainer to light up AI agents.
Based on Nano-vLLM, a simple replication of vLLM with self-contained paged attention and flash attention implementation
MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.
[ICML 2026 Spotlight] Latent Collaboration in Multi-Agent Systems
ChatDev 2.0: Dev All through LLM-powered Multi-Agent Collaboration
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…
A modern chat interface for AI agents built with Next.js, Tailwind CSS, and TypeScript.
Image annotation with Python. Supports polygon, rectangle, circle, line, point, and AI-assisted annotation.
中文langchain项目|小必应，Q.Talk，强聊，QiangTalk
NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥
2022搜狐校园算法大赛NLP赛道第一名开源方案（实验代码）
微信大数据2021 1st，qq浏览器2021 3rd，mind新闻推荐2020 1st，NAIC2020 AI+遥感影像 2nd
“英特尔创新大师杯”深度学习挑战赛 赛道3：CCKS2021中文NLP地址相关性任务
这里是用torch写的简洁版的GLUE评测代码。This is the simpler code written by torch in GLUE.