Framework for building multi-agent equity research agents
I built Hermes, an open-source Python framework for multi-agent financial research. Most AI “equity research” demos stop at generating text. In practice, real workflows require pulling structured XBRL financials from SEC filings, extracting labeled sections like MD&A and Risk Factors, merging macro and market data, building actual Excel models with formulas, and generating investment memos in Word or PDF. Hermes is designed to handle that full pipeline end to end. It includes 35 financial data tools covering SEC EDGAR (via edgartools), FRED, Yahoo Finance market data, and RSS-based financial…
What it does
In the maker’s words, at launch
I built Hermes, an open-source Python framework for multi-agent financial research. Most AI “equity research” demos stop at generating text. In practice, real workflows require pulling structured XBRL financials from SEC filings, extracting labeled sections like MD&A and Risk Factors, merging macro and market data, building actual Excel models with formulas, and generating investment memos in Word or PDF. Hermes is designed to handle that full pipeline end to end. It includes 35 financial data tools covering SEC EDGAR (via edgartools), FRED, Yahoo Finance market data, and RSS-based financial news. It also provides composable specialist agents for filings, macro data, market data, modeling, report generation, and multi-agent orchestration. On the output side, it can generate Excel workbooks using openpyxl, create Word documents, export PDFs, and index filings with ChromaDB for semantic search. It includes async rate limiting, file-based caching (filings cached permanently, quotes never cached), and streaming progress events. Hermes is MIT licensed and designed to be extended. You can register custom tools and agents and plug in your own data sources or models. I’d love feedback from both AI engineers and finance professionals, especially around validation, reliability, and real-world research workflows. Repo: https://github.com/schnetzlerjoe/hermes
Does the same job
all alternatives →
- FAFactIQ – a realtime econ+finance database for AI agentsJul 2026 · github.com · ▲7
Hey HN, we built an Econ+Finance database to let AI agents do investment research. We spend a lot of tokens to organize macro releases and SEC filings into a clean format, so that your agents have more context to do actual analysis. The problem AI agents are great at data analysis. But they become ineffective if most of their context window is spent on gathering and cleaning data, instead of validating hypotheses. Data in the wild is messy and rarely standardized. Definitions and measurements change over time. This problem is compounded by a fragmented data universe. Point solutions exist…
- PFPersonal Financial Advisor with AI2024 · project-hermes-ai.vercel.app · ▲5
Hey guys, I am trying to do something different, Fintech + AI. I feel there is a complete abundance of Fintech AI tools in the B2B Saas space but not so much done for the consumer space. So I started working on project-hermes, it's a personal financial advisor designed to understand your bank statements and credit reports with ease and intelligence. What makes Project Hermes unique? 1. AI-powered insights: Get smart, tailored advice on your financial health. 2. Easy to use: Just upload your documents and let Hermes do the rest! 3. Secure and private: Your data's safety is our top priority.…
- BSBull.sh: Financial Modeling Agent CLIJan 2026 · github.com · ▲7
Built a free open source agentic CLI tool for financial modeling & analysis. Hadn't played around with real equity valuation modeling for awhile and wanted to build tooling to get myself back into the game. Bull.sh lets you query & store 10-Qs, 10-K in a local vector store to chat with them, build investment thesis from scratch or build full framework models through the CLI to export into excel. It's open source, just requires your own Anthropic API key and (optionally) AlphaVantage Free API key if you want save some tokens from scraping. Feel free to play around with it. Some ideas I have…
- IPI published 100 AI generated books on Amazon2020 · ▲20
To be specific, the content is generated by a GPT-2 based model. https://amzn.to/2TCc0v2 Let me know if you have any questions :-)
- BABigwig – an Agentic News Site for financial markets2025 · askbigwig.com · ▲5
Hey HN, For the last couple of months, we have been building an AI agent for continuous statistical analysis, and we're looking for feedback while it's still early in development. We call it BIGWIG - an autonomous agent that is specialised, and very good at, performing advanced statistical analysis, through long traces of iteration and reasoning. As it builds statistical models it also "emits" outputs back to the user that you can then interact with, iterate on and schedule for follow up analysis. While we're still in BETA, we've launched a public analysis site that showcases some of the…
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 · 18d 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 · 26d ago · cactuscompute.com
