MiniMax-H3 Character Swap
Swap a character in a clip with a reference (H3 LoRA V1.5)
BitsExplorer finds what people are building with AI, every day. See today's picks →
vLLM delivers state-of-the-art LLM serving throughput with PagedAttention
vLLM delivers state-of-the-art LLM serving throughput with PagedAttention
Description excerpted from the original listing, which is linked below.
Debate Desk
Bull and bear agents argue from the same market evidence, a judge decides, and every practice trade lands on Solana with its reasoning trail committed on chain.
HunyuanVideo
Text-to-video with Tencent HunyuanVideo on ZeroGPU
Plazmi Connect
Connect AI agents to Plazmi: MCP Registry, Claude Code plugin, Claude Desktop extension, Gemini CLI
Hrih Skills
Agent Skills for Claude Code and other agents: design-inspiration looks at real design galleries before building; copywriter writes copy from facts and edits out the AI tells.
ppu.toys — make pictures like it’s 1991
A ShaderToy-style playground for the SNES PPU. Write Lua, watch the frame update live, and publish tiny graphics toys.
MUON: run your coding agents as one governed crew
MUON is the governed harness above coding agents. Direct Claude Code, Codex, Cursor and OpenCode as one crew, on your machine, with shared memory you confirm and gates you control.
Pinna: every call records itself, ready for your AI agents
Records every call on its own, in Zoom, Teams, Meet, FaceTime and more, with no bot. Transcribed on your Mac by default. With Pro, your AI agents read every meeting over MCP.
The week in AI-built software
Every Monday: how many projects were built with AI that week, which tools built them, where they came from, and the week's picks.
Read the latest week