Blog
Tutorials, strategy ideas and product updates from the Sigrex team.
Building an Evolving Strategy with Checkpoints and an LLM Coach
Letting an AI edit a running strategy sounds great until you ask one question: how do you know the new version is better? In August we showed how an LLM Reaction can supervise a Code Strategy and patch it when something breaks. This post takes the same idea further. The AI may now replace the whole trading logic, and a small set of rules keeps that from turning into guesswork. We call the setup Evo. It trades BTCUSDT on paper, and it is built only from parts you already have on Sigrex: one Cod
2026-10-10
How to Forward Test a Strategy
Sigrex has no backtester, and that is a design consequence, not a missing feature. A strategy here can read any API and ask any LLM, and you can't replay that from history. What you can do is run the strategy on the live market with nothing attached to it, and watch. Why a backtester doesn't fit Sigrex A backtest replays the past. It feeds old data into your rules and counts what would have happened. That works when two things are true: every input the strategy uses has a recorded history, an
2026-10-02
Talk to Your Trading Bots: Introducing the Sigrex MCP Server
Building trading automation usually means a lot of clicking. Open a strategy, edit a value, save, check the logs, switch to another bot, repeat. It works, but it's slow, and it pulls your attention away from the part that actually matters: the trading ideas themselves. Today that changes. With the Sigrex MCP server, you can connect AI assistants like Claude and ChatGPT directly to your Sigrex account and manage your whole trading setup in plain language. Ask a question, get an answer from your
2026-09-25
Building a News-To-Trade Workflow for Polymarket
Prediction markets move on information. A market resolves on a specific, checkable question — did the rate cut happen, did the bill pass, did the company hit the number — and every time new information about that question becomes public, there's a brief window before the market price catches up with it. Most of that window closes in minutes. Nobody is checking Polymarket by hand fast enough to consistently catch it. This post walks through a pipeline that does the watching for you: Perigon deli
2026-08-26
Building Copy Trading Pipeline for Polymarket
Copy trading a wallet on Polymarket is straightforward in principle: every trade a wallet makes is public, on-chain, and available through a free API. The harder question is how to relay those trades into your own bot without inheriting the source wallet's exact position sizing, without double-processing the same fill twice, and without losing visibility into what actually got copied and why. This walks through one way to do that: a Code Strategy that polls a wallet, a Data Webhook that stores
2026-08-17
Building Self-Improving Strategies with LLM Reactions
Here's a thing that happens to basically every strategy eventually: it works great for a while, and then it just... doesn't. Maybe the market shifted. Maybe you hardcoded a threshold that made sense in March and stopped making sense in June. Maybe there's a small bug that's been quietly eating trades for two weeks and you only find out when you happen to open the logs. The usual fix is you, checking in, noticing something's off, and going to patch it. Which works, but it doesn't scale past howe
2026-08-10
Building an LLM Strategy That Monitors X (Twitter) Feeds
What if your trading bot could read a tweet, weigh it against current market conditions, and decide — on its own — whether it's worth a trade? That's the idea behind this strategy: an LLM-powered bot that monitors Elon Musk's X (Twitter) feed, cross-references it with live BTC/ETH/FLOKI prices, and only acts when a post is both relevant and significant. This post walks through exactly how it works, piece by piece, using the real production prompt as the reference. The full working strategy fro
2026-08-03
Connecting External APIs Securely with $.Http
Standard JavaScript runtimes like Node.js or browsers rely on global functions like fetch or axios to interact with external web services. However, in secure algorithmic environments, accessing unmanaged networking interfaces can introduce significant latency, security risks, or memory overhead. In Code Strategies, external network communication is handled through the built-in $.Http object. $.Http provides a streamlined, secure utility for sending HTTP requests, managing caching automatically
2026-07-23
Time Gates in Code Strategies
When building automated trading algorithms, controlling when your strategy evaluates the market is just as important as defining what it does. Because Code Strategies run continuously in an infinite loop—executing one iteration immediately after another—performing a full market evaluation or making external network requests on every single pass can lead to rate-limiting issues, noisy signal processing, and degraded performance. This is where Time Gates come in. A Time Gate creates a controlle
2026-07-23