Docdex
Structural code indexer with deterministic LLM context
What it does
Docdex is a local-first indexing daemon for code and documentation. It combines ranked full-text search (Tantivy), AST-based symbol indexing, and a directed dependency graph to answer impact questions like “what breaks if this changes?”. It runs as a single lightweight service, supports multiple repos, integrates with local models via Ollama, and helps reduce LLM token usage by providing structured, persistent context.
Does the same job
all alternatives →
Docs by Hashnode2024 · hashnode.com · ▲698The gold standard for your API references and product guides
- DTDoxx – Terminal .docx viewer inspired by Glow2025 · github.com · ▲261
I got tired of open file.docx → wait 8 seconds → close Word just to read a document, so I built a terminal-native Word viewer! What it does: * View `.docx` files directly in your terminal with (mostly) proper formatting * Tables actually look like tables (with Unicode borders!) * Nested lists work correctly with indentation * Full-text search with highlighting * Copy content straight to clipboard with `c` * Export to markdown/CSV/JSON Why I made this: Working on servers over SSH, I constantly hit Word docs I needed to check quickly. The existing solutions I'm aware of either strip…
- DDDOM-docx – HTML to native, editable Word docs (MIT)Jul 2026 · github.com · ▲158
- DCDocx-CLI: agents read/edit Word docs using 1/2 the time and tokensJul 2026 · github.com · ▲70
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
