Discussion

Search code, repositories, users, issues, pull requests...

zc2610: Hi HN. We built LangAlpha because we wanted something like Claude Code but for investment research.It's a full stack open-source agent harness (Apache 2.0). Persistent sandboxed workspaces, code execution against financial data, and a complete UI with TradingView charts, live market data, and agent management. Works with any LLM provider, React 19 + FastAPI + Postgres + Redis.

zc2610: Some technical context on what we ran into building this.MCP tools don't really work for financial data at scale. One tool call for five years of daily prices dumps tens of thousands of tokens into the context window. And data vendors pack dozens of tools into a single MCP server, schemas alone can eat 50k+ tokens before the agent does anything useful. So we auto-generate typed Python modules from the MCP schemas at workspace init and upload them into the sandbox. The agent just imports them like a normal library. Only a one-line summary per server stays in the prompt. We have around 80 tools across our servers and the prompt cost is the same whether a server has 3 tools or 30. This part isn't finance-specific, it works with any MCP server.The other big thing was making research actually persist across sessions. Most agents treat a single deliverable (a PDF, a spreadsheet) as the end goal. In investing that's day one. You update the model when earnings drop, re-run comps when a competitor reports, keep layering new analysis on old. But try doing that across agent sessions, files don't carry over, you re-paste context every time. So we built everything around workspaces. Each one maps to a persistent sandbox, one per research goal. The agent maintains its own memory file with findings and a file index that gets re-read before every LLM call. Come back a week later, start a new thread, it picks up where it left off.We also wanted the agent to have real domain context the way Claude Code has codebase context. Portfolio, watchlist, risk tolerance, financial data sources, all injected into every call. Existing AI investing platforms have some of that but nothing close to what a proper agent harness can do. We wanted both and couldn't find it, so we built it and open-sourced the whole thing.

esafak: You shouldn't dump data in the context, only the result of the query.

zc2610: Yes, thats is the idea and exactly what we did

zz07: One thing I really like about this project is how it fully takes the advantage of LLM throughout the workflow to fill out the last-one-mile gap. Currently most agent products in the market suffer from imcomplete workflows. Imagine a powerful agent that handles 95% of the work perfectly but still requires the user to drag the files or open some links for it to finish the last few steps. The user experience is greatly undermined. However, LangAlpha iterates a lot to solve all those pain points. This is especially important considering the target users, financial workers, may not be export in CS and may not understand the mechanism behind LLM well. For example, LangAlpha uses smart skill injection to provide the agent with skills to help the user update user preferences: everything can literally be done in a casual chat.

erdaniels: Then people would lose a lot of money

xydac: Its crazy how many similar threads exists today.

ForOldHack: Note: Never make angry the gods of code. Never. If you do, they will leave angry on Friday night, and come back with some *amazing* thing like this on Monday:Obligatory: Brilliant Work. Brilliant."We wanted both and couldn't find it, so we built it and open-sourced the whole thing."\m/ \m/ /m\ /m\

D_R_Farrell: I've been wondering for a long time about when this more Bayesian approach would become available alongside an AI. Really excited to play around with this!Is this kind of like a Karpathy 2nd brain for investing then?

jskrn: Sounds interesting. The video isn't working, wish I could see the hosted version without creating an account.

zc2610: Thanks for feedback. i am working on that already.it should be easy to self host in docker though.

TeMPOraL: > The other big thing was making research actually persist across sessions. Most agents treat a single deliverable (a PDF, a spreadsheet) as the end goal. In investing that's day one.This is a problem with pretty much everything beyond easy single-shot tasks. Even day-to-day stuff, like e.g. I was researching a new laptop to buy for my wife, and am now enlisting AI to help pick a good car. In both cases I run into a mismatch with what the non-coding AI tools offer, vs. what is needed:I need a persistent Excel sheet to evolve over multiple session of gathering data, cross-referencing with current needs, and updating as decisions are made, and as our own needs get better understood.All AI tools want to do single session with a deliverable at the end, that they they cannot read, or if they can read it, they cannot work on it, at best they can write a new version from scratch.I think this may be a symptom of the mobile apps thinking that infects the industry: the best non-coding AI tools offered to people all behave like regular apps, thinking in sessions, prescribing a single workflow, and desperately preventing any form of user-controlled interoperability.I miss when software philosophy put files ahead of apps, when applications were tools to work on documents, not a tools that contain documents.

zc2610: Exactly, this is especially important for agents given the limited effective context window.

kolinko: Nice!What I missed from the writeup were some specific cases and how did you test that all this orchestration delivers worthwhile data (actionable and full/correct).E.g. you have a screenshot of the AI supply chain - more of these would be useful, and also some info about how you tested that this supply chain agrees with reality.Unless the goal of the project was to just play with agent architecture - then congrats :)

zc2610: Great advice!For demo purpose and to attract attention, i was primarily picking some cases with cool visuals (like the screenshot of the AI supply chain you mentioned). we have some internal eval and will try to add more cases in the public repo for reference.

uoaei: More signs of the AI bubble. Completely unprofessional behavior ("cool visuals" not "real results"). And don't give me that "hacker culture" bullshit, these people are targeting Wall Street as paying customers.