# Senpi.ai Knowledge Base > Guides, specs, and troubleshooting for Senpi.ai — a non-custodial AI trading platform for Hyperliquid with mirror trading, programmatic agents, and self-hosted runtime. Senpi.ai pairs a consumer mobile app for mirror/copy trading with a developer runtime for self-hosted agents (OpenClaw, MCP, DSL exit management). The knowledge base is split into two surfaces: **Learn** (end-user product docs) and **Support** (developer, runtime, and troubleshooting docs). ## Key entry points - [Learn index](https://resources.senpi.ai/learn): product docs, briefs, and strategy guides - [Support index](https://resources.senpi.ai/support): troubleshooting, runtime, and developer reference - [Blog (Senpi Desk)](https://resources.senpi.ai/blog): weekly notes, post-mortems, runtime updates - [Search](https://resources.senpi.ai/search): full-text search across all surfaces ## Learn End-user product documentation: how mirror trading works, how to brief an agent, account setup, strategy primitives. - [Arena Competition](https://resources.senpi.ai/learn/arena-competition): Trade for a slice of the $100K+ Senpi Arena pool, with $5K guaranteed weekly. Rank by ROE, hit $25K volume, and get paid to your Main Wallet. - [Fee-Optimized Execution (Maker-First Orders)](https://resources.senpi.ai/learn/fee-optimized-execution-maker-first-orders): Cut trading fees with maker-first orders, tune the fallback to market for fill certainty, and handle the 2026 order-options schema change. - [Fees, Loyalty Tiers, and Referrals](https://resources.senpi.ai/learn/fees-loyalty-tiers-and-referrals): What a Senpi trade costs, plus three ways to pay less: maker-first execution, volume loyalty tiers up to 50% off, and 25% referral rewards. - [Senpi Points (Season 2)](https://resources.senpi.ai/learn/senpi-points-season-2): Earn Senpi Points on every trade in Season 2 (Feb 1 - May 31), how they set your fee tier, and why to ignore token-launch DMs. - [Account, Profile, and Official Support Channels](https://resources.senpi.ai/learn/account-profile-and-official-support-channels): Edit your display name and agent photo, recover lost account access, and reach official Senpi support. Spot and avoid Telegram scams. - [Deposits, Withdrawals, and Bridging USDC](https://resources.senpi.ai/learn/deposits-withdrawals-and-bridging-usdc): Move USDC in and out of Senpi across Base, Arbitrum, and more, bridge back to any chain, and recover USDT sent by mistake. - [Wallet Architecture and Inter-Wallet Transfers](https://resources.senpi.ai/learn/wallet-architecture-and-inter-wallet-transfers): How Senpi's Main and strategy wallets hold your funds non-custodially, and the tools to bridge or move USDC between them. - [Wallet Security and Non-Custodial Design](https://resources.senpi.ai/learn/wallet-security-and-non-custodial-design): Senpi keeps your keys non-custodial with sharded keys and secure enclaves, backed by SOC 2 and three external audits. Export keys anytime. - [Sign Up and Get Started](https://resources.senpi.ai/learn/sign-up-and-get-started): Sign in with a wallet, Farcaster, or X, fund with $100 USDC, and launch your first strategy in the app or with an agent. - [What is Senpi](https://resources.senpi.ai/learn/what-is-senpi): A non-custodial AI trading agent for Hyperliquid. Mirror elite traders from the app, automate with agents, and track your portfolio. - [Managing Strategies: Top-Up, Partial Withdrawal, and Close](https://resources.senpi.ai/learn/managing-strategies-top-up-partial-withdrawal-and-close): Add or pull funds from a strategy, read PnL correctly, and know when to close positions versus permanently shut down a strategy wallet. - [Mirror Strategy Settings](https://resources.senpi.ai/learn/mirror-strategy-settings): Set your mirror multiplier and slippage tolerance, understand permanent pause, and stop a mirror strategy from copying new trades. - [Strategy Types and the Sub-Wallet Model](https://resources.senpi.ai/learn/strategy-types-and-the-sub-wallet-model): Mirror trading versus custom strategies, and how each strategy's isolated sub-wallet lets you hedge and hold cross-margin positions. - [Opening, Editing, Closing, and Canceling Positions](https://resources.senpi.ai/learn/opening-editing-closing-and-canceling-positions): Open, resize, and close Hyperliquid positions from your strategy wallets, set TP/SL, and cancel resting orders. - [Tradeable Assets: Crypto, Equities, and XYZ DEX](https://resources.senpi.ai/learn/tradeable-assets-crypto-equities-and-xyz-dex): Trade 275+ perps across crypto, equities, and metals on Hyperliquid, with per-asset leverage limits and case-sensitive symbols. - [Trading Mechanics: Margin, Leverage, TP/SL, Funding, and Liquidation](https://resources.senpi.ai/learn/trading-mechanics-margin-leverage-tp-sl-funding-and-liquidation): How margin, leverage, and liquidation price work on Senpi, plus margin-relative TP/SL and hourly funding rates. ## Support Developer and troubleshooting reference: runtime (OpenClaw, MCP), DSL exit management, wallets, execution issues, error codes. - [Personal Agent Troubleshooting](https://resources.senpi.ai/support/personal-agent-troubleshooting): What to do when your Personal Agent is slow, erroring, or not responding — and why these are handled on Senpi's side. - [Reviewing Your Agent's Decisions & Trades](https://resources.senpi.ai/support/reviewing-your-agents-decisions-and-trades): How to see what your agent did and why, and how to get an honest review of your closed trades — just by asking. - [Senpi Personal Agents: Overview](https://resources.senpi.ai/support/senpi-personal-agents-overview): What a Senpi Personal Agent is, how it's hosted and managed by Senpi, and how it trades on Hyperliquid on your behalf — no keys, no infrastructure. - [Ratchet Stop: Automatic Position Protection](https://resources.senpi.ai/support/ratchet-stop-automatic-position-protection): How Senpi's Ratchet Stop protects your positions automatically — loss protection, profit trailing, and staying protected even if your agent is offline. - [Fees & Loyalty Tiers](https://resources.senpi.ai/support/fees-and-loyalty-tiers): Senpi's per-trade fees, how loyalty tiers lower them, funding rates, and referral earnings. - [Funding, Deposits & Withdrawals](https://resources.senpi.ai/support/funding-deposits-and-withdrawals): How to fund Senpi with USDC, which chains are supported, how auto-bridging and the unified Hyperliquid account work, and how withdrawals and fees work. - [Missing Funds: Balance Shows Zero](https://resources.senpi.ai/support/missing-funds-balance-shows-zero): Why a balance can look like zero even though your funds are safe — the USDC-only display and cross-venue balances — and how to see non-USDC tokens. - [Migrating to Senpi 2.0](https://resources.senpi.ai/support/migrating-to-senpi-2-0): If you used Senpi before, what carries over to Senpi 2.0 — your wallet, funds, and referral code — and what's new. - [Personal Agents: Getting Access & the $100 Credits](https://resources.senpi.ai/support/personal-agents-access-and-100-credits): How batched access works after you join the waitlist, and how the $100 in free AI credits work — what they are, how to claim them, and when they expire. - [What Is Senpi & How to Get Started](https://resources.senpi.ai/support/what-is-senpi-and-getting-started): What Senpi is, the two ways to trade, and how to sign in, fund with USDC, and start on web or mobile. ## Blog Editorial notes from the Senpi desk: live strategies, post-mortems, and runtime updates. - [The Apes lead the pack](https://resources.senpi.ai/blog/apes-lead-the-pack): Senpi 2.0's first seven days: over 9,000 agents went live. Among the built-in strategies, the Apes — gibbon and chimp — came out on top. One thing still beat them: the strategies you built yourselves. - [How the Senpi Risk Engine Works: A Deep Dive](https://resources.senpi.ai/blog/senpi-risk-engine-deep-dive): Most AI trading fails in the same place: the model is the only thing in the loop. Here is exactly how the Senpi risk engine works - sizing, exits, turnover limits, and circuit breakers. - [What's Actually Under the Hood at Senpi](https://resources.senpi.ai/blog/hyperliquid-ai-harness-under-the-hood-senpi): When you use Senpi, you see a chat box. Here is what is underneath it - our own model, a proprietary data layer, a runtime, and a library of strategy templates that have traded real money in public. - [Meet Senpi Samurai 1.2, the most powerful AI trading model ever built for Hyperliquid - coming soon](https://resources.senpi.ai/blog/meet-senpi-samurai): Senpi Samurai 1.2 is the model Senpi 2.0 runs on. Trained on millions of real Hyperliquid trades, battle-tested with real capital. Here is why the brain behind your agent matters more than the interface on top of it. - [My AI agent caught the smartest money on Hyperliquid betting against the crowd, and built WhaleHunter.](https://resources.senpi.ai/blog/building-whalehunter-strategy-hyperliquid): One of the key advantages of Senpi 2.0 is that you get your own personal AI agent that scans the markets 24/7 and sees things humans could never see alone. - [Senpi 2.0 in the Wild: One Week, Real Wallets, Real Capital](https://resources.senpi.ai/blog/senpi-20-in-the-wild): We just opened the Senpi 2.0 waitlist with $100 in free AI credits - [Senpi 2.0 loaded 🥷 Reserve your agent + get $100 free AI credits](https://resources.senpi.ai/blog/senpi-gen-2-get-100-free-ai-credits): We just opened the waitlist for Senpi 2.0, and we're giving $100 in free AI credits to everyone who signs up before launch. Senpi 2.0 is six months of work by our team, compounded into one release: the most useful AI-powered trading experience on Hyperliquid. - [The Top Hyperliquid Agent Dropped 16 Points in 48 Hours. Then It Fine-Tuned Itself.](https://resources.senpi.ai/blog/top-hyperliquid-agent-fine-tuned-itself): Vulture, Senpi's top Hyperliquid agent, audited its own 100 trades, found the dead scoring buckets, raised its own MIN_SCORE, and shipped the fix to itself. - [What a 52% 5-Day HYPE Rally Taught Our Hyperliquid Agents - and the Fixes They Shipped](https://resources.senpi.ai/blog/hype-52-percent-rally-agent-fixes): A 52% HYPE rally became a live audit of our Hyperliquid agents. Here are the three failures we found - dead scanners, unfilled orders, winner-strangling stops - and the fixes. - [The Runtime is the AI Infra Advantage](https://resources.senpi.ai/blog/hyperliquid-agent-runtime): You can take any frontier LLM — Claude Opus, GPT-5, Gemini 2.5 Pro — and prompt it to trade. The model will write plausible-sounding trade theses. It will pick reasonable-looking entries. It will even propose stop-loss levels. Then you put real money behind it and watch it lose, slowly and stupidly, for reasons that have nothing to do with whether the model is “smart.” - [Introducing Senpi Hyperliquid Agent Runtime 1.1.0: 30× Faster, 75% Cheaper, Self-Learning](https://resources.senpi.ai/blog/senpi-hyperliquid-agent-runtime-1-1): Self-learning agents accelerate Hyperliquid trading while cutting runtime costs and setup time. 1.1 adds 30x speedups, 75% lower runtime fees and 24/7 autonomous execution. - [Senpi Hyperliquid Agents Can Now Analyze Each Other - And It Changes Everything](https://resources.senpi.ai/blog/senpi-agents-analyze-each-other): Senpi agents can now read every other agent's full onchain trading history through MCP. Here is what that unlocks, plus two new agents that prove it. - [Turning $694 Into $3,289: Nearly 5x in 3 Weeks. The Senpi Hyperliquid Agent Out-Trading Everyone](https://resources.senpi.ai/blog/turning-694-into-3289): One autonomous agent turned $694 into $3,289 in 21 days and won three straight Hyperliquid Agents Arena weeks. Here is exactly how it traded. - [How to Build a Moat in AI Agent Trading](https://resources.senpi.ai/blog/how-to-build-a-moat-in-ai-agent-trading): Everyone in crypto AI is building trading agents. Most teams are optimizing the wrong layer. The real moat is the data, the runtime, and the learning loop. - [What We Learned and Rapidly Hardened by Running 43 Autonomous Hyperliquid Agents with $43,000](https://resources.senpi.ai/blog/running-43-autonomous-hyperliquid-agents): We gave 43 AI agents $1,000 each and set them loose on Hyperliquid. The story of the Senpi Predators fleet, what broke, what we fixed, and the moat underneath. - [Why We Built the Hyperliquid Agents Runtime - the Layer Between the Agent and the Chain](https://resources.senpi.ai/blog/why-we-built-the-hyperliquid-agents-runtime): What we learned from $230M+ in agent trading volume and 44 autonomous agents on Hyperliquid: the signal was never the problem. Exit execution was. - [14 Unique Hyperliquid Trading Agents. $1,000 Each. Full Transparency.](https://resources.senpi.ai/blog/14-hyperliquid-trading-agents): We funded 14 open-source Senpi agents with $1,000 each and turned them loose on Hyperliquid. Every trade and P&L tracked live on a public dashboard. - [88% of Volume in 6 Days: The AI Trading Revolution Is Moving Faster Than Anyone Realizes](https://resources.senpi.ai/blog/88-percent-volume-in-6-days): Six days after Senpi launched agents on Hyperliquid, 88% of user volume runs through them. Inside the skills, scanners, and goal engines driving the shift. ## Optional - [Sitemap](https://resources.senpi.ai/sitemap.xml): machine-readable list of all indexable URLs - [Search](https://resources.senpi.ai/search): full-text search across the knowledge base - [RSS](https://resources.senpi.ai/rss.xml): RSS 2.0 feed for the Senpi Desk blog ## Related: Senpi Trade Live trading product at `trade.senpi.ai`. SSR pages with full JSON-LD; safe to cite directly. - [Senpi Trade](https://trade.senpi.ai/trade-ai): live trading dashboard for Hyperliquid assets - [Opportunities](https://trade.senpi.ai/trade-ai/opportunities): real-time agent-surfaced trade ideas - [Segments hub](https://trade.senpi.ai/trade-ai/rwa): browse assets by category (RWA, L1, DeFi, memes, AI, gaming, infra, privacy, Hyperliquid-native) - Example asset page: https://trade.senpi.ai/trade-ai/btc - Example segment page: https://trade.senpi.ai/trade-ai/rwa/pre-ipo - Example agent page: https://trade.senpi.ai/agents/marlin - [Trade sitemap](https://trade.senpi.ai/sitemap.xml): full index of asset, segment, and agent pages