VibeTrade – Trading Harness for Claude
Post-Opus 4.6, LLMs feel much better at using bash, code, local files, and tools. So I kept coming back to a simple question: if a model can use a computer reasonably well, why can’t I just give it my broker account, a strategy, and let it trade? My conclusion is that the blocker is not model capability in the abstract. It is the system around the model. A raw LLM breaks on a few practical things almost immediately: • no persistent operating memory across sessions • no trustworthy record of what it did and why • no hard approval boundary before money moves • no cheap always-on monitoring if…
What it does
In the maker’s words, at launch
Post-Opus 4.6, LLMs feel much better at using bash, code, local files, and tools. So I kept coming back to a simple question: if a model can use a computer reasonably well, why can’t I just give it my broker account, a strategy, and let it trade? My conclusion is that the blocker is not model capability in the abstract. It is the system around the model. A raw LLM breaks on a few practical things almost immediately: • no persistent operating memory across sessions • no trustworthy record of what it did and why • no hard approval boundary before money moves • no cheap always-on monitoring if every check requires an LLM call • no reliable enforcement of limits, permissions, or workflow rules unless that lives outside the model So the problem is not really “can the model call a broker API?” The problem is that trading needs a harness. My friend and I built one for this called Vibe Trade. It is open source, MIT licensed, and currently runs locally on your machine connected to Dhan. The basic design is: 1. Immutable trade journal Every action is logged at decision time with timestamp, reasoning, and observed signals. The agent cannot rewrite its own history after the fact. 2. Hard approval gate Before any order is placed, the system generates a structured approval request. Execution is blocked until the user approves. This is enforced in code, not left to the model’s discretion. 3. Event loop outside the LLM Market watching is handled in plain JS on a timer. Price checks, time rules, and indicator thresholds run every 30 seconds without invoking the model. The LLM only wakes up when something needs reasoning. 4. Playbooks / skill files Strategies live in markdown documents that get loaded as operating context on each decision. Example: “replicate the Nifty Defense Index and rebalance weekly.” This gives the agent a stable workflow definition instead of relying on chat history. The first use case that made this feel real to me was very unglamorous: portfolio rebalancing. I used to make Smallcase-style index replication portfolios and then forget to rebalance them on time. With this setup, I can define the strategy once, let the non-LLM layer monitor for conditions, and have the agent prepare actions for approval. That was the first point where it stopped feeling like a demo and started feeling useful. A few caveats: • UI is still weak; it is mostly a chat interface right now • Dhan only for now • local install only for now • requires Node.js and an Anthropic API key Repo: github.com/vibetrade-ai/vibe-trade I’m posting this mainly because I think more people will try building “LLM as operator” systems now that tool use is better, and finance makes the failure modes very obvious. The questions I’m interested in are: • What other harness components are missing for something like this? • Would you trust a local system like this more than a hosted one, or less? • What repeatable financial workflows would you automate first?
Does the same job
all alternatives →
- FAFinterm.ai Bloomberg terminal for Claude CodeJul 2026 · finterm.ai · ▲6
Hi, my name is Kam, and today my cofounder Josh and I are shipping Finterm, a CLI that gives coding agents direct access to financial data: stock prices, options data, SEC filings, and Ticker Deep Research, a filtered ticker news search. I’m a developer and have been a full-time trader for the past few years.Recently I have been using LLMs more and more in my trading and strategy. I always found it frustrating that Claude Code or GPT did not have direct access to actual financial information and had to rely on web search, so it couldn’t get me more granular numbers for specific options…
- CCClaude Code for Sales and GTMJan 2026 · github.com · ▲8
Tried all SaaS Sales and GTM tools; ended up vibe-coding a simple tool that just works. Uses Claude Code as a backend (funny, I know). Helps enrich, qualify, and prepare high-quality reach-outs
- CLCompliant LLM toolkit for ensuring compliance & security of AI systems2025 · github.com · ▲7
With the right technique, I was able to break the so-called secure models like Claude and OpenAI. So, I built an open-source tool to automate this and find security holes in any hosted model. I got claude-sonnet-4 to demonstrate the following harmful behavior: - steal data from downstream tool calls using sql injection, code injection and template injection attacks - install spyware or malware using prompt obfuscation to send data to a third-party server Try it yourself with this simple command: pip install compliant-llm && compliant-llm dashboard
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
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
