LongCat-2.0
1.6T MoE trained entirely on AI ASICs
Product HuntOpen SourceLaunched Jul 7, 2026148#10 of the day
About LongCat-2.0
LongCat-2.0 is an MIT-licensed 1.6T-parameter MoE model with ~48B active parameters, 1M context, LongCat Sparse Attention, and post-training for coding and agentic workflows. It was trained on AI ASIC superpods and integrates with Claude Code, OpenClaw, and Hermes.
The people behind LongCat-2.0
We haven't found the people behind LongCat-2.0 yet. New makers are added as we find them.
More Open Source launches
InyonAnswer your coding agents from your phoneOct 23, 2026 · 1 person
NanotypeA private online text editor with markdown. Open and type.Oct 23, 2026 · 1 person- Whiteboardthe open-source IDE for thoughtful software designOct 22, 2026 · 1 person
Tetriz Engg Intelligence + ConnectorsConnect coding sessions to PRs, issues, quality, and ROIOct 22, 2026 · 1 person
TessaryStop your agents from failing silently in productionOct 22, 2026 · 1 person
LLM Test ServerYour LLM tests, without the providerOct 22, 2026 · 1 person
Made LongCat-2.0? Ask us to remove this listing or your details.