Microsoft's MarkItDown tops GitHub with 100k+ stars, turning messy docs into LLM-ready Markdown
mdancho84 · x · 2026-09-06
MarkItDown, a quiet Python tool from Microsoft, has shot to the top of GitHub trending with 100,000+ stars. It converts almost any file — PDFs, Word docs, PowerPoints, Excel, images — into clean Markdown, addressing one of the biggest RAG bottlenecks: getting messy real-world documents into a format models can actually use, with far less preprocessing.
More from coding & agent
- Same model, 63% vs 97% on ARC-AGI-3: 7 harness rules beat max reasoning — victor_explore · 2026-09-07
- Matt Shumer: I 4x'd my Pro/Max subs as agentic models remove the attention bottleneck — mattshumer_ · 2026-09-07
- GPT-6 Astra codes the geometry, Dreamina Seedance 2.5 renders the final footage — HeyAmit_ · 2026-09-07
- Grok Bot's topic-based agent form factor hailed as better than threads — brandon_galang · 2026-09-07
- Codex defaults to 3 subagents — one config.toml line raises concurrency to 64 — daniel_mac8 · 2026-09-07
- Teaching Qwen Next 3D sculpting in Blender by having GPT Astra coach it via MCP — LegacyRemaster · 2026-09-07