MKT CAP$2.21T+0.8%
24H VOL$125.9B
BTC DOM59.4%
HEALTH40BEARISH
SHORT-TERM61NEUTRAL
LONG-TERM19BEARISH
OI$51.1B+7.6%
24H LIQ$252M
LONG/SHORT58.8% / 41.2%
REGIME (LT)ESTABLISHED BEAR MARKET
REGIME (ST)CHOPPY HIGH VOLATILITY
HL OI$7.8B
WHALESSHORT 46.0%
MKT CAP$2.21T+0.8%
24H VOL$125.9B
BTC DOM59.4%
HEALTH40BEARISH
SHORT-TERM61NEUTRAL
LONG-TERM19BEARISH
OI$51.1B+7.6%
24H LIQ$252M
LONG/SHORT58.8% / 41.2%
REGIME (LT)ESTABLISHED BEAR MARKET
REGIME (ST)CHOPPY HIGH VOLATILITY
HL OI$7.8B
WHALESSHORT 46.0%
Plug real-time crypto data into your AI agent — one command: Get your free API key →
Get API KeyLogin
Open-Source · MCP · Obsidian Vault

An LLM wiki-brain for
crypto strategy generation

AlgoBrain is an expert-curated knowledge base of ~4,900 interlinked markdown nodes — strategies, concepts, assets and market narratives — served to AI agents over a local MCP server. It gives a language model the context to derive and analyse millions of crypto trading strategies, grounded on live CryptoDataAPI data.

~4,900
Wiki nodes
1.55M+
Strategy configs
2,400+
Asset pages
640
Agent workflows
The AlgoBrain vault as a live Obsidian graph — ~4,900 interlinked nodes across strategies, concepts, assets and market narratives, color-coded and cross-linked.

What's inside the brain

A structured, interlinked wiki built for strategy generation — not a blog, not a docs site. Every node is designed to be read by a language model as high-signal context.

~445 strategy pages

Funding-rate harvesting, arbitrage, liquidation plays, MEV exploitation, grid, mean-reversion and momentum — parameterized into 1.55M+ distinct specifiable configurations an agent can enumerate and adapt.

1,000+ concept pages

The building blocks: market microstructure, derivatives, on-chain mechanics, risk and edge taxonomy — the vocabulary a model needs to reason about why a strategy works.

2,400+ asset pages

Per-asset context across crypto, plus documented market narratives — 69 archetypes with 290 quantified historical instances so strategies are grounded in what actually happened.

Obsidian vault

Opens as a ready-to-explore vault with a color-coded knowledge graph and pre-configured plugins — browse the interlinks visually, or let an agent traverse them programmatically.

Served to your agent over a local MCP server

AlgoBrain runs a local Model Context Protocol server so any MCP-capable agent — Claude Code, Cursor and others — can search and read the wiki as native tools while it works.

Five tools are exposed over Streamable HTTP at http://127.0.0.1:8010/mcp:

wiki_search wiki_read wiki_stats wiki_lint wiki_ingest

The agent searches for relevant strategy and concept nodes, reads them for context, then pairs that knowledge with live and historical market data from CryptoDataAPI to specify, ground and backtest a strategy.

# 1 · set up & install python -m venv .venv .venv\Scripts\python.exe -m pip install -r tools/requirements.txt # 2 · start the local MCP server # via Claude Code: /start-servers # or directly: powershell -ExecutionPolicy Bypass -File tools/start_servers.ps1 # → server live at http://127.0.0.1:8010/mcp # stop with tools/stop_servers.ps1

Grounded on CryptoDataAPI

A knowledge base is only useful if its strategies can be tested against reality. CryptoDataAPI is AlgoBrain's canonical data layer — the wiki teaches the strategy, the API grounds it in real market data.

190+ REST endpoints

Live and historical prices, funding, open interest, liquidations, order-book depth, regime analysis and whale tracking — auth with an X-API-Key header.

640 agent workflows

That many wiki pages carry an AI agent workflow section with parameterized signal endpoints and a matching backtesting archive — read the strategy, then run it.

Backtest archive to 2020

Clean Parquet history for regime-conditioned backtests, plus live dashboards on cryptodataapi.com linked throughout the knowledge base for verification.

Explore the data layer: API docs · backtest data · market regimes · whale activity. Pair AlgoBrain with the CryptoDataAPI MCP server so one agent has both the knowledge and the live data.

Built to be maintained by an LLM

  • Strategy development — edge taxonomy, hypothesis-to-backtest workflows, overfitting detection and capacity analysis
  • Entities — exchanges, DeFi protocols, quant funds and trading legends
  • Data sources — a provider catalog with live dashboard links
  • Dataview + YAML frontmatter — every node is queryable and typed
  • Append-only op logwiki/log.md records every change

The whole vault follows an LLM-maintenance pattern: a schema defined in CLAUDE.md, node templates in templates/, and an append-only operation log — so an agent can grow the brain safely, node by node, without breaking the graph.

Written in Python (~93.5%) with PowerShell tooling (~6.5%), using MCP over Streamable HTTP and the Obsidian vault format.

Licensing

Code — MIT

Everything under tools/ is MIT-licensed. Use it, fork it, ship it.

Knowledge base — CC BY 4.0

The wiki/, templates/, raw/ and attachments/ are CC BY 4.0 — free to use with attribution.

FAQ

Who is AlgoBrain for?

Anyone building AI trading agents or researching crypto strategies with a language model. It gives the model a structured, expert-curated knowledge base to reason over instead of relying on whatever it happened to memorize.

Do I need CryptoDataAPI to use it?

The wiki itself reads standalone, but AlgoBrain is designed to be paired with CryptoDataAPI as its data layer — that's what turns a strategy idea into something you can specify, ground and backtest. A free API key is enough to start; deep history is Pro Plus.

Does it actually generate strategies?

It provides the knowledge and structure for an agent to generate them — ~445 strategy templates parameterized into 1.55M+ configurations, plus the concepts and market narratives to reason about which fit current conditions. The agent + CryptoDataAPI data does the generating and testing. We wrote about why that 1.5M number is a trap — the count is the easy part; the edge is not.

How do I connect it to Claude Code?

Clone the repo, install tools/requirements.txt, and run /start-servers (or the PowerShell script) to launch the MCP server on port 8010. Point your agent at it, and add the CryptoDataAPI MCP server alongside for live data.

Give your agent a trading brain

An open-source knowledge base of strategies, concepts and market narratives — served over MCP, grounded on CryptoDataAPI data. Clone it and connect it to your agent today.

View on GitHub Add the data layer: MCP server → · Backtest data →