Finance & Business1 month ago
Omnichannel Agentic RAG Platform | Ambuj Kumar Tripathi
Financial document parser powered by agentic RAG with web search and human reasoning.
ambujkt · HN
11-Node Agentic RAG with MCP and PII Shield Under 512MB RAM
The full gallery
Tech stack
17 projects
Financial document parser powered by agentic RAG with web search and human reasoning.
ambujkt · HN
11-Node Agentic RAG with MCP and PII Shield Under 512MB RAM
Convert PDF, DOCX, XLSX, CSV, JSON, XML, HTML, Images to clean Markdown optimized for AI Agents, RAG, and Vector DBs. 100% Privacy-First, In-Browser Conversion.
@13SahajChawla · X
For professionals to redact their client's sensitive informations before giving AI to process it & while converting any kind of document to a structured MD file. Better quality outputs, 100% privacy with on-browser local processing, and fully free!
Unified context layer for AI agents that integrates email, drive, Slack, Notion, and GitHub.
@marcin_u2 · X
-> here it is! claude finally knows everything gpt knows. and both of them know everything that's happened across your email, drive, slack, notion, github and granola :)
The job board for AI developers — RAG, agents, evals, inference. First-party roles pulled nightly from company career sites.
alastairr · HN
Job board and MCP server for AI developers
Maintains and serves your personal context to Claude, ChatGPT, and other AI assistants.
@feed_thebots · X
Create AI assistants for technical documentation that respond to user questions instantly.
@emilsnotes · X
Our customers using Claude Code move faster than we can ship features. So we stopped fighting it and leaned in. Here's why it's paying off: 👇️ Some context: powers AI agents that answer millions of technical questions per month. Those conversations are a goldmine - they tell you exactly what users struggle with and where your docs fall short. We've built a lot of analytics on top of this (Coverage Gaps, Top Questions, and more), and teams love them. But here's the honest truth: no dashboard covers every edge case for every company. Meanwhile, our sharpest customers were already exporting kapa data and throwing their coding agents at it in ways we never designed for. So instead of chasing every workflow with a UI, we took the best practices we've seen actually work and packaged them as Kapa Skills - installable in Claude Code, Cursor, or Codex: 1/ Analyze Coverage Gaps: your agent works through the topics kapa couldn't answer and writes the missing content straig
Store and share prompts, rules, and context that AI tools like Claude Code, Cursor, and ChatGPT can access via MCP.
@vibexp_io · X
Your plan is now code. Claude Code Dynamic Workflows fan out up to 1,000 subagents, 16 at once, each in its own context, verifying until the results converge. Built for big bug hunts, migrations and audits. Source:
Search indexed open-source code and packages with version history, metadata, and dependency information.
@Jack_Timonen · X
Manage DNS, SSL, renewals, and domain ownership across multiple registrars from a single dashboard.
@itstarun1994 · X
Embed an AI knowledge assistant into your docs for instant voice and text answers.
k7vin · HN
Lens AI – generate your JSON-LD files and keep them up-to-date
Upload agency documents to create an AI knowledge base that answers questions with citations.
@tim_edgert · X
Launched Echo — an AI tool that turns your agency's scattered docs into instant, cited answers
Organize notes and collections, ask questions, and generate podcasts and study materials.
mistakevin · HN
I've been working on https://notebooker.ai if anyone is interested in giving some feedback. I tried to post a Show HN yesterday with details about how I built it, but was auto-flagged and not sure what rules I broke. Everything that I've built on top of open-notebook, like the plugin system for your own "creators" (aka, podcasts, infographics, etc) is at https://github.com/Notebooker-ai plus a Cloudflare Worker AI deployer to play with different models. Been working on it for about six months.