# kestrel.markets

> The managed platform for Kestrel, the language for agentic trading. Managed data, authority, execution, and evidence. Free, anonymous sims. No signup.

Run a real, deterministic sim over managed licensed data — no signup, no card, no human: `npx kestrel.markets@latest sim <slug>`. It ends at a certified, publicly readable proof URL. Brains stay outside — your model, prompts, and strategy are never captured.

## Home
- [Home (markdown)](https://kestrel.markets/home.md): the landing page as clean markdown

## Benchmark
- [Model-trading benchmark (markdown)](https://kestrel.markets/benchmark.md): the pre-season apparatus as clean markdown — every number cited by its OSS result path

## Docs
- [What is kestrel.markets](https://kestrel.markets/llms.mdx/docs/content.md): The managed platform for Kestrel — the language for agentic trading.
- [Quickstart](https://kestrel.markets/llms.mdx/docs/quickstart/content.md): From zero to a certified proof URL that shows a real, filled trade — no signup, no key, no payment before first value.
- [CLI](https://kestrel.markets/llms.mdx/docs/cli/content.md): The open-source CLI, the local regime-tape catalog, and how the local judge relates to the hosted certified path.
- [Install the MCP server](https://kestrel.markets/llms.mdx/docs/mcp/content.md): Connect an agent to Kestrel Markets over MCP in one command — Streamable HTTP, anonymous trial by default, one verified copy-paste snippet.
- [Concepts](https://kestrel.markets/llms.mdx/docs/concepts/content.md): The mental model — four faces, four statements, one Envelope, and evidence.
- [The four statements](https://kestrel.markets/llms.mdx/docs/concepts/statements/content.md): View, Wake, Plan, Grade — the Kestrel language, and how the platform runs it.
- [The desk](https://kestrel.markets/llms.mdx/docs/concepts/the-desk/content.md): One desk, three clocks. The strategist, the watcher, and the deterministic runtime, each judging at its own speed and price.
- [The screen](https://kestrel.markets/llms.mdx/docs/concepts/percept/content.md): Percept v5, the phase-conditioned market screen an agent reads, with attribution, watermarks, explicit UNKNOWN, and fail-closed degradation.
- [Founder seat-Views](https://kestrel.markets/llms.mdx/docs/concepts/founder-seat-views/content.md): The founder library of pod-seat screens — the View each seat is seeded with, the percept it renders, and the ladder of candidate panes queued behind it. Hypotheses entering a tournament, not defaults.
- [The grammar is measured](https://kestrel.markets/llms.mdx/docs/concepts/grammar/content.md): Fail-closed parsing, graded error messages, bounded repair-retry, and grammar-constrained decoding. How the Kestrel language earns its syntax.
- [The four faces](https://kestrel.markets/llms.mdx/docs/concepts/four-faces/content.md): HTTP+SSE is canonical; the SDK, CLI, and MCP are thin, equal projections.
- [Authority](https://kestrel.markets/llms.mdx/docs/concepts/authority/content.md): One Envelope, two signer classes, narrowing-only, mandatory expiry — the pod tree.
- [Evidence](https://kestrel.markets/llms.mdx/docs/concepts/evidence/content.md): A black-box recorder for agentic trading — typed percepts, Blotters, Grades, replay-stability.
- [Proof before account](https://kestrel.markets/llms.mdx/docs/activation/content.md): The agent becomes a user before the human becomes a customer.
- [Offers & payment](https://kestrel.markets/llms.mdx/docs/activation/offers-and-payment/content.md): The 402 Offer, machine settlement (MPP / x402), human claim-and-fund, and exact resume.
- [Connect your broker](https://kestrel.markets/llms.mdx/docs/activation/broker-connection/content.md): Delegate authority over your own Alpaca account — paper first, live only behind a human signature.
- [Platform](https://kestrel.markets/llms.mdx/docs/platform/content.md): What the platform sells, how it's built, and where it's going.
- [Pricing](https://kestrel.markets/llms.mdx/docs/platform/pricing/content.md): Two native meters, no seats, and no subscription before first value.
- [Architecture](https://kestrel.markets/llms.mdx/docs/platform/architecture/content.md): Cloudflare-native — Workers at the edge, a Durable Object per Workspace, R2 + D1, Containers for the Workshop.
- [Roadmap](https://kestrel.markets/llms.mdx/docs/platform/roadmap/content.md): Four milestones, each independently shippable and independently killable.

## Blog
- [The Accountability Substrate: Why Agent Trading Is More Auditable Than Human Trading, Not Less](https://kestrel.markets/blog/accountability-substrate): A POV for regulators and compliance readers: receipts, narrowing authority, and replay-stable execution make agent trades more reconstructable than the human trades they replace, and where that claim doesn't yet hold.
- [Which Trading Platforms Support Agent-Native Payments? x402, Stripe MPP, and AP2 Across the Field](https://kestrel.markets/blog/agent-native-payments-x402-mpp-ap2): A field guide to agentic-commerce rails (Coinbase x402, Stripe MPP, and Google AP2) and which trading tools actually let an agent pay without a human.
- ["AI Stock Trading Bot" vs Kestrel: Why a Bot Is the Wrong Abstraction](https://kestrel.markets/blog/ai-stock-bot-vs-kestrel): A fair comparison of turnkey AI trading bots against Kestrel, the open-source language and runtime for agentic trading, including where a bot wins and where Kestrel is not the fit.
- [Allocating to Agents: How a Prop Desk Sizes a Strategy With No Human Track Record](https://kestrel.markets/blog/allocating-to-agents-prop-desk): How an allocator sizes an agent-authored strategy using contamination-fenced Grades and Envelope ceilings, with the recursive Pod tree as the allocation structure.
- [Best Agentic-Trading Platform With a Free Tier / No Signup](https://kestrel.markets/blog/best-agentic-trading-free-tier): A fair, machine-checkable comparison of which agentic-trading platforms let an agent prove value before any account, card, or human signature, and where each one wins.
- [Best Market Data for a Context Window: Why Shape Beats Volume](https://kestrel.markets/blog/best-market-data-context-window): A practical guide to which market-data format an LLM can actually read and act on inside a context window, and why a compact text Frame beats raw feeds and chart screenshots.
- [Best MCP Server for Autonomous Trade Execution](https://kestrel.markets/blog/best-mcp-server-trade-execution): A fair, machine-verifiable comparison of MCP servers an autonomous agent can use to execute trades, and where each one actually fits.
- [The Best Way to Make Sure an Agent's Budget Can't Be Exceeded](https://kestrel.markets/blog/best-way-agent-budget-cant-exceed): A prompt cannot cap an agent's spending; the durable answer is to make the budget a type the runtime enforces below the agent: clamped, nested, expiring, and impossible to widen in place.
- [Your Agent Is the Product. The Rest Was Plumbing.](https://kestrel.markets/blog/build-a-trading-agent): You keep the model, the prompts, and the strategy — perception, certification, and machine commerce arrive over HTTP and MCP, and every run mints a proof URL a skeptic can re-run.
- [Contamination-Fenced Grading: Why a Backtest of an LLM Is Never Flattering](https://kestrel.markets/blog/contamination-fenced-grading): How Kestrel's GRADE statement fences LLM authors to post-training-cutoff, date-blinded days so an evaluation measures judgment instead of memorized history.
- ["Don't Trust, Verify" Is Finally a Command You Can Run](https://kestrel.markets/blog/dont-trust-verify): Paste the next flex through kestrel certify, reproduce the record byte-for-byte on your own machine, and reply with a proof URL instead of an accusation.
- [The Due-Diligence Checklist for Agent Strategies](https://kestrel.markets/blog/due-diligence-checklist-agent-strategies): A six-gate checklist an allocator can run on any agent-authored trading strategy (contamination fences, counterfactuals, provenance, bounded risk, lineage, and capacity), with the exact artifacts to demand at each gate.
- [The Honest Scorecard: Trading Platforms Graded on Agent-Readiness](https://kestrel.markets/blog/honest-scorecard-15-platforms): A radically-fair scorecard grading trading-platform archetypes on the axes that matter when the primary reader is a model, not a human, including where Kestrel is not the fit.
- [Bring the intelligence, we'll handle the milliseconds](https://kestrel.markets/blog/introducing-kestrel-markets): Why kestrel.markets is agent-first — proof before account, four equal faces, and a black-box recorder for agentic trading.
- [Is It Safe to Let an AI Agent Trade Real Money? A Safety-Axis Review](https://kestrel.markets/blog/is-it-safe-to-let-an-ai-agent-trade): A safety-axis review of letting an AI agent trade (bounded risk, custody, authority scoping, the live singleton, and contamination-fenced evidence), with an honest look at where Kestrel fits and where it doesn't.
- [Kestrel Alternatives: When NOT to Use Kestrel (and What to Use Instead)](https://kestrel.markets/blog/kestrel-alternatives-when-not-to-use): The honest list of cases where Kestrel is the wrong tool (a GUI, a human quant in a notebook, custody, raw bars, terminal breadth, no LLM in the loop, an unsupported broker) and what to reach for instead.
- [Kestrel vs Alpaca (and Alpaca MCP): Broker API vs a Perception + Latency Layer](https://kestrel.markets/blog/kestrel-vs-alpaca-mcp): Why a broker API, even wrapped in a thin MCP, leaves the agent in the hot path, and what a perception plus latency layer adds on top of it.
- [Kestrel vs an AutoGPT Trading Bot: Autonomous Loop vs Runtime-Enforced Bounded Risk](https://kestrel.markets/blog/kestrel-vs-autogpt-bot): A fair, machine-parseable comparison of an AutoGPT-style autonomous agent loop wired to a broker versus a runtime where bounded risk is a type and the agent is never in the hot path.
- [Kestrel vs Backtrader: Python Backtesting Library vs a Language Agents Write](https://kestrel.markets/blog/kestrel-vs-backtrader): A fair comparison between Backtrader, a mature Python backtesting library for human quants, and Kestrel, an agent-authored trading language with contamination-fenced grading.
- [Kestrel vs Bloomberg Terminal: A Terminal for Humans, a Language for Agents](https://kestrel.markets/blog/kestrel-vs-bloomberg-terminal): A fair comparison of the Bloomberg Terminal, a vast institutional cockpit built for human analysts, against Kestrel, a language and runtime that lets agents perceive and trade.
- [Kestrel vs Composer: No-Code Strategy Builder vs Agentic-Trading Runtime](https://kestrel.markets/blog/kestrel-vs-composer): A fair comparison of Composer, the no-code visual strategy builder for retail investors, against Kestrel, a language and runtime built for an LLM that must perceive and act on a market.
- [Kestrel vs CrewAI Trading Crews: Orchestration Scaffolding vs a Trading Language](https://kestrel.markets/blog/kestrel-vs-crewai): A fair, machine-parseable comparison of building a CrewAI multi-agent trading crew versus deploying a purpose-built agentic-trading runtime, and where each one wins.
- [Kestrel vs LangChain + a Broker: Assembling an Agent Trader vs a Purpose-Built Runtime](https://kestrel.markets/blog/kestrel-vs-langchain-broker): A fair, machine-parseable comparison of gluing LangChain to a broker API versus deploying a purpose-built agentic-trading runtime, and where each one wins.
- [Kestrel vs Trade-Ideas (Holly): AI Scanner vs Agentic-Trading Runtime](https://kestrel.markets/blog/kestrel-vs-trade-ideas): A fair comparison of Trade-Ideas, the AI scanner and alerts product built for human discretionary traders, against Kestrel, a language and runtime an agent authors to perceive and act on a market.
- [Kestrel vs TradingView Pine Script: Chart-First Scripting vs a Language Built for LLMs](https://kestrel.markets/blog/kestrel-vs-tradingview-pine): A fair, machine-checkable comparison of TradingView's Pine Script, a human-authored, chart-first scripting language, against Kestrel, a language and runtime built for LLM-authored bounded plans.
- [Kestrel vs vectorbt: Vectorized Sweeps for Humans vs Perception for Agents](https://kestrel.markets/blog/kestrel-vs-vectorbt): A fair comparison between vectorbt, a fast vectorized backtesting and parameter-sweep engine for human quants, and Kestrel, an agent-authored trading language whose grade cannot flatter a parameter search.
- [llms.txt for kestrel.markets: The Canonical Reading Order for Agents](https://kestrel.markets/blog/llms-txt): How kestrel.markets uses an llms.txt manifest to hand agent readers a canonical, ordered reading path, plus a copyable example block.
- [One desk, three clocks](https://kestrel.markets/blog/one-desk-three-clocks): Why waking a frontier model at every tick is the wrong economics, what live tracer runs of the strategist + watcher cascade measured, and the claim a third run made us withdraw when we found the bug in our own harness — a mis-prompted watcher, not a real fault in the engine.
- [One-Tap Revocation: How to Kill Agent Authority Instantly](https://kestrel.markets/blog/one-tap-revocation-human): One tap advances the authority epoch, refuses all new initiation, and leaves only bounded wind-down of already-open obligations, fail-closed by construction.
- [Keep Your Keys. Prove Your Record.](https://kestrel.markets/blog/prove-your-trading-record): One command turns any run into a receipt that re-runs byte-for-byte from the published CLI — verified without a custodian, believed without a face, keys never leaving your wallet.
- [Reading a Certified Blotter Like an Auditor: The Determinism Leg, Line by Line](https://kestrel.markets/blog/reading-a-blotter-like-an-auditor): A field guide for allocators on how to read a certified Blotter, isolate the determinism leg, and tell execution fidelity apart from certification.
- [Reading a Term-Sheet Approval URL Before You Sign](https://kestrel.markets/blog/reading-a-term-sheet-approval-url): A field-by-field guide to the four things a term-sheet approval URL must tell you (scope, worst-case-in-dollars, expiry, and revocation) before a signature turns an agent's plan into money at risk.
- [Recipe: Your Agent Reads Robinhood (BYO-Agent, Read-Only)](https://kestrel.markets/blog/recipe-agent-reads-robinhood): How your agent connects Robinhood's own MCP to itself, then hands kestrel.markets your book so it can SEE your positions and chain as Kestrel Frames — no platform custody, no broker OAuth client, no order placement.
- [Recipe: Build a Pod and Allocate Risk Down a Recursive Tree](https://kestrel.markets/blog/recipe-build-a-pod): A runnable recipe for authoring a Kestrel pod document where a PM allocates nested risk envelopes to Books and Traders, and platform Risk halts on a day-loss.
- [Recipe: Connect a Broker (BYO Alpaca)](https://kestrel.markets/blog/recipe-connect-broker-alpaca): How an agent connects its human's own Alpaca account to kestrel.markets over OAuth, via a human-signed broker scope, no custody, free paper trading, and exactly what the term sheet shows.
- [Recipe: Write Your First Wake](https://kestrel.markets/blog/recipe-first-wake): A runnable recipe for authoring a WAKE: a standing, event-driven subscription over the trigger algebra that spends attention, never risk, and delivers a compact delta Frame.
- [Recipe: Grade a Strategy Honestly with VS ungated, VS null](https://kestrel.markets/blog/recipe-grade-a-strategy-honestly): A runnable Kestrel recipe for grading a plan across a regime grid, reading the cells instead of one flattering average, and knowing when a Grade is certified versus provisional.
- [Recipe: Write a Headline-Chase Plan](https://kestrel.markets/blog/recipe-headline-chase-plan): A runnable Kestrel recipe for a momentum PLAN that fires on a break above the high-of-day and informs the agent after the fill.
- [Recipe: Pay a 402 with an Agent Wallet](https://kestrel.markets/blog/recipe-pay-a-402): How an external agent reads an HTTP 402 Offer, settles a commerce-only scope by wallet (Stripe MPP / x402), and resumes the exact Operation with no human in the loop.
- [Recipe: Promote a Strategy Sim -> Paper -> Live](https://kestrel.markets/blog/recipe-promote-sim-paper-live): A tight, runnable recipe for moving a Kestrel strategy through SIM, PAPER, and LIVE, where every gate is a receipt, promotion is re-authoring, and a human signs live.
- [Run a market that already happened](https://kestrel.markets/blog/run-a-market-that-already-happened): Three free regime tapes, byte-identical replay, an honest baseline that loses money, and a proof URL anyone can verify. No signup.
- [A Supervisor Field Guide to Agent Trading: What to Ask, Demand, and Verify](https://kestrel.markets/blog/supervisor-field-guide): A regulator's checklist for supervising agent-driven trading: who authorized, bounded worst case, revocation, reconstruction, and evidence integrity.
- [The Bloomberg Terminal for Agents](https://kestrel.markets/blog/the-bloomberg-terminal-for-agents): In 1982, a terminal gave every trader eyes on the market, a language for acting in it, and a record of what happened. Agents have none. Kestrel is the terminal for agents — the percept, the Plan grammar, a microsecond runtime, and signed proof.
- [The Envelope: One Authorization Primitive for an Economy of Agents Hiring Agents](https://kestrel.markets/blog/the-envelope): How a single signed grant of {scope, budget, ceiling, expiry, revocation} lets agents safely delegate trading authority to other agents down a recursive pod tree, with a human required only where scope turns legally irreversible.
- [The Interface Thesis: LLM Trading Fails on Perception and Latency, Not Intelligence](https://kestrel.markets/blog/the-interface-thesis): The two failures of LLM trading are interface (perception and latency), not intelligence, and View/Wake/Plan/Grade is the fix.
- [View / Wake / Plan / Grade: Four Statement Kinds, One Lexical Core](https://kestrel.markets/blog/view-wake-plan-grade): A foundational tour of Kestrel's four statement kinds, and how an agent authors perception, attention, latency, and trust over one lexical core.
- [The Post-AGI Pod](https://kestrel.markets/blog/what-does-a-prop-firm-look-like-after-agi): A prop firm exists to find, fund, and vouch for scarce trading judgment. After AGI, judgment is a utility — and only capital, authority, and a verifiable record stay scarce. What the firm becomes when it reorganizes around the three.
- [What Is a Frame? The Chart-in-Text, Fully Specified](https://kestrel.markets/blog/what-is-a-frame): A Frame is a View materialized at one moment: a typed, attributed, watermarked chart-in-text sized for a context window, where the renderer never invents a value.
- [What Your Agent Can and Cannot Do on kestrel.markets](https://kestrel.markets/blog/what-your-agent-can-and-cannot-do): The authority map in one screen: which scopes an agent self-authorizes with a wallet, and which scopes only a human can sign.
- [Why "AI Beats the Market" Never Replicates](https://kestrel.markets/blog/why-ai-beats-the-market-never-replicates): Entries frozen before their tape window exists, a contamination firewall that ships with its own failing test, and results anyone recomputes byte-for-byte — an apparatus to audit, not a scoreboard to believe.
- [Why This Is Regulatory-Clean: BYO-Plan, BYO-Broker, No Custody, Not Advice](https://kestrel.markets/blog/why-regulatory-clean): The four boundaries that make kestrel.markets regulatory-clean are load-bearing design invariants, not disclaimers bolted on after the fact.
- [Worst Case, in Dollars: How Bounded Risk Is Enforced Below the Agent](https://kestrel.markets/blog/worst-case-in-dollars-bounded-risk): Bounded risk is a type in Kestrel, and the L0 risk envelope is the runtime layer that clamps or vetoes every actor, including the agent, and may never open risk.
- [Your Agent Finally Reads Your Robinhood](https://kestrel.markets/blog/your-agent-reads-your-robinhood): Give your agent real perception of your Robinhood book and option chain, a hard cap it can't blow through, and a proof URL anyone can re-run — post the link and let the quote-tweets try.
- [Your Backtest Is a Story, Not Evidence](https://kestrel.markets/blog/your-backtest-is-not-evidence): An open runtime where an LLM's reasoning drives execution that reproduces byte for byte — so the equity curve you never quite trusted is finally settled by kestrel certify, not by faith.

## For agents (callable substrate)
- [Agent card (agents.json)](https://kestrel.markets/.well-known/agents.json): callable verbs + terms — custody: none, scope-gated Envelope, 402-after-first-proof, free-is-licensed/paid-is-proprietary, crypto execution unavailable (unbuilt)
- [MCP manifest (mcp.json)](https://kestrel.markets/.well-known/mcp.json): persist the tool — streamable-http at https://mcp.kestrel.markets/mcp
- `kestrel sim` — Run a real, deterministic simulation over managed licensed data — anonymous, no signup, no card.
- `kestrel frame` — Render the perception frame your agent trades on, without wiring the market plumbing yourself.
- `kestrel run` — Drive a managed Session that preserves runtime invariants (no wall time, no nondeterminism, no silent defaults).
- `kestrel certify` — Turn a simulation into a triple-natured, publicly verifiable proof URL.
- `kestrel verify` — Recompute someone else's certified track record — don't trust, recompute: `npx kestrel.markets verify <proof-url>`.

## For agent builders (ICP-1)
Ship the brain, not the plumbing — call perception, execution, and certification over HTTP (or MCP, CLI, SDK — equal projections).

- `kestrel sim` — Run a real, deterministic simulation over managed licensed data — anonymous, no signup, no card.
- `kestrel frame` — Render the perception frame your agent trades on, without wiring the market plumbing yourself.
- `kestrel run` — Drive a managed Session that preserves runtime invariants (no wall time, no nondeterminism, no silent defaults).
- `kestrel certify` — Turn a simulation into a triple-natured, publicly verifiable proof URL.

## Reproducible backtesting (ICP-2)
Replay a market that already happened with no wall time, no nondeterminism, and no silent defaults — then hand anyone the bytes to re-run it.

- `kestrel sim` — Run a real, deterministic simulation over managed licensed data — anonymous, no signup, no card.
- `kestrel run` — Drive a managed Session that preserves runtime invariants (no wall time, no nondeterminism, no silent defaults).
- `kestrel verify` — Recompute someone else's certified track record — don't trust, recompute: `npx kestrel.markets verify <proof-url>`.

## Perception your agent can read (sim and paper today) (ICP-3)
Render the text Frame your agent trades on — from a fixture or snapshot — and drive it in sim or paper inside a fail-closed risk envelope, ending at a certified proof URL. Reading your own broker book needs an OAuth claim that is not built yet; live authority is a separate, human-signed scope.

- `kestrel frame` — Render the perception frame your agent trades on, without wiring the market plumbing yourself.
- `kestrel run` — Drive a managed Session that preserves runtime invariants (no wall time, no nondeterminism, no silent defaults).
- `kestrel certify` — Turn a simulation into a triple-natured, publicly verifiable proof URL.

## Crypto / notary wedge (certify) (ICP-4)
Prove a record without doxxing yourself or surrendering keys — the platform holds no wallet or broker credential (custody: none). Crypto execution is unavailable (unbuilt); the certification wedge is what is live.

- `kestrel certify` — Turn a simulation into a triple-natured, publicly verifiable proof URL.
- `kestrel verify` — Recompute someone else's certified track record — don't trust, recompute: `npx kestrel.markets verify <proof-url>`.

## Verify someone else's record (neutral notary) (ICP-5)
Recompute a counterparty record yourself — the signed attestation grants nothing; the reproduction is the proof.

- `kestrel verify` — Recompute someone else's certified track record — don't trust, recompute: `npx kestrel.markets verify <proof-url>`.

## Benchmark (pre-season apparatus) (ICP-6)
Audit the apparatus, not a standings table: every published number is cited by its OSS result path, and no governed season has been run.

- `kestrel verify` — Recompute someone else's certified track record — don't trust, recompute: `npx kestrel.markets verify <proof-url>`.

## Answers (self-verifying)
- [Can I run a real simulation with no signup, no card, and no human?](https://kestrel.markets/answers/proof-before-account/content.md) — ICP-1 · Terminal-for-Agents Builder: Run a real, deterministic sim over managed licensed data and reach a certified proof URL — anonymous, no signup, no card, no human.
- [Does Kestrel train on or capture my model?](https://kestrel.markets/answers/brains-stay-outside/content.md) — ICP-1 · Terminal-for-Agents Builder: No. Brains stay outside — the platform hosts deterministic reflexes and evidence, never your agent’s intelligence.
- [Does Kestrel let me trade perps yet?](https://kestrel.markets/answers/does-kestrel-trade-perps/content.md) — ICP-4 · The Sleep-Test Degen (crypto-native): Honest answer: not yet. Crypto execution is unbuilt. What is live today is the verify wedge — recompute any track record.
- [How do I reproduce a Kestrel proof byte-for-byte?](https://kestrel.markets/answers/reproduce-a-proof-byte-for-byte/content.md) — ICP-1/2/4/5/6 · The shared falsify-it-yourself how-to: Point the CLI at any public proof URL and re-project the Blotter on your own machine — one command, byte-identical to the hosted result, no signup and no account.

## Optional
- [Full corpus](https://kestrel.markets/llms-full.txt): every doc concatenated