AI multi-agent pipeline built specifically for academic papers. Upload a PDF or LaTeX source, get an editable PowerPoint with original figures preserved. Three-role architecture (Strategist, Executor, Critic) with 4-pass deep reading, SVG-to-PPTX conversion, and optional icon semantic search. Early-stage but architecturally impressive. MIT license.
Open →AI Agent Skill for automated patent technical disclosure document generation. Full pipeline: patent point mining, CNIPA novelty search, sanitized disclosure document generation, self-check, and multi-round revision. Outputs .md + .docx dual format. Follows AgentSkills standard, works in Claude Code and Cursor. Focused on Chinese patent system (CNIPA). MIT licensed.
Open →Local LLM inference engine built on Apple MLX framework. 2-4x faster than Ollama on Apple Silicon with 0.08s cached TTFT. OpenAI-compatible API for drop-in replacement. DeltaNet state snapshot for hybrid architecture prompt caching. 58 model aliases, 17 tool call parsers, 3,200+ test cases. Open-source, Apple Silicon only.
Open →Jakob Nielsen argues that AI is triggering the first major UI paradigm shift in 60 years: users are becoming supervisors instead of operators, delegating intent rather than issuing commands. This rewrites the definition of usability and introduces three crises: the articulation barrier, the credibility trap, and the cognitive wheelchair.
Open →The Claude Code Telegram plugin extends your desktop AI assistant to mobile devices via MCP. This guide covers four-step installation, secure pairing with allowlist configuration, group and multi-bot setup, so you can remotely operate your desktop Claude session from your phone with full skill and tool permissions.
Open →