TickDB open-sources its MCP server, Skill definitions, and CLI so AI agents can query unified real-time market data across stocks, forex, and crypto without writing REST clients.
doc7 converts documents into Markdown by showing page images to a local vision model, bypassing OCR pipelines and cloud per-page fees.
To give AI agents and quant scripts a legitimate, unified pipe into official Tonghuashun A-share market data.
It exists so Italian law firms can use ChatGPT on sensitive documents without ever shipping a codice fiscale off their laptop.
It builds an agent-ready knowledge base over your local files without dragging them into a proprietary workspace.
OpenLake wants storage to bypass the host entirely and land straight in GPU memory.
BiliSum exists to convert Bilibili, YouTube, and local videos into structured, offline notes and a personal knowledge base that keeps data off the cloud.
An MCP server that hands LLMs live web access, anti-bot evasion, and 60+ data tools—if you pay past the first 5,000 requests.
Ix builds a persistent symbol graph of your repository so both you and your AI assistant can ask structural questions instead of grepping blind.
Your AI coding conversations are trapped in undocumented SQLite schemas and scattered log files; this extracts them before the next update wipes everything.
A Rust search engine that auto-indexes folders so AI agents can query code and documents without stuffing their context windows.
A Python client that turns the Hub's model zoo into a local filesystem with caching, search, and inference baked in.
An MCP server that turns conversational data requests into AntV visualizations without you picking colors or chart types.
Documentation and SDK examples for a paid API that replaces brittle CSS selectors with natural-language prompts and optional live search.
Modular agent skills that hand LLMs the boring office work—Excel analysis, slide decks, research reports, and infographics—instead of letting them hallucinate about it.
A battle-tested Java toolkit that extracts metadata, references, and full text from academic PDFs using a cascade of ML models.
Memgraph wants to be the single database operation your GraphRAG pipeline actually needs.
Daft is a Rust-backed dataframe engine that treats images, audio, and embeddings as native types rather than generic Python objects, letting AI pipelines scale from a laptop to a Ray cluster without JVM baggage.
Scans running WeChat process memory to extract SQLCipher keys, then exposes your chat database as a JSON-first CLI designed for AI agent consumption.
A pipeline that turns messy PDFs and slides into structured, navigable memory for AI agents instead of flat text shards.
heatdrop uses Google Analytics to see which pages get read — nothing else. Your call. How we handle data.
