trading-research-agents

Autonomous trading agents for crypto that can't fudge their own results.

Language models are good at reading a market and saying what they think. They are bad at arithmetic, they don't know what a trade costs, and they will happily overrule a limit you set. This project uses them for the first part only. The system itself, fixed rules with no model involved, fetches the data and works out every figure. The agents read those figures and give an opinion. Then the system prices the trade, applies your limits, sizes it, and either writes it down or sends one order with the stop attached. Every decision and every refusal is kept on disk with its reason, so you can check afterwards what happened and why.

It's an early release, so expect settings to change between versions. What works today: a universe of perpetuals found and measured by the system, a screener that picks where to look, the full autonomous cycle on live data, four analysts and up to three validators, stops and targets the analyst names inside bounds you set, the gates that decide, sizing from your own rules, real orders on a venue's practice environment behind a mandate you sign, a risk manager that can only make the desk more careful, and two auditors that read the records.

Contents

• What it solves
• Quick start
• What you see, in order
• How one cycle decides
• Venues
• Models and providers
• From a replay to real orders
• Your money, your orders, your positions
• Watching a desk, and what is kept
• Command line
• What it guarantees, and what is not built yet
• Documentation

What it solves

Quick start

You need Python 3.11 or newer. uv is the quickest way in.

uv tool install 'trading-research-agents[ccxt,openai,data]'

tra init my-desk --profile autonomous && cd my-desk
cp .env.example .env        # put your model key in here; no venue key is needed yet
tra check                   # what's ready, and the one thing to fix next
tra run                     # one autonomous cycle, in the sandbox: nothing leaves your machine

The extras are what the project talks through: ccxt for venue data and orders, openai for every OpenAI-compatible provider (Groq, DeepSeek, xAI, OpenRouter, a local server), data for datasets. Add anthropic or google to the list for those providers. Without uv, pip install 'trading-research-agents[ccxt,openai,data]' in a virtual environment does the same.

To work on the code itself, install from a clone instead:

git clone https://github.com/BijectiveLabs/trading-research-agents && cd trading-research-agents
uv tool install --editable '.[ccxt,openai,data]'

A project made by tra init --profile autonomous checks out like this before you touch it (shortened):

ok    strategy.toml: valid; core 'agent-pending'; instrument BTCUSDT
ok    roster: technical_analyst; `tra run` asks these
ok    channel: bybit/taker-taker enters as a taker, priced at that fee; an order crosses the book at once
ok    execution: sandbox; nothing leaves the machine
ok    regime: measured on 15m with 1h, 4h as context; trending at 2.0+, ranging at 1.0 or less
ok    conviction: floor 0.4; ladder 0.75+ -> 1.0x, 0.55+ -> 0.5x, 0.4+ -> 0.25x
ok    targets: at least 5 bps net; at least 2.0x the round trip; at most 6 round trips a day
ok    exits: the analyst names its stop and target; the stop is held between 20 and 300 bps, the
      target between 1.5x and 4.0x the stop
ok    risk per trade: 50 bps of equity at the stop, applied to every size the ladder produces
ok    size: 0.01 in base units, at the step 0.001
ok    data.toml: chains for ohlcv, orderbook, funding, open_interest; `tra run` uses them
todo  [agents].provider is still the placeholder; name the provider you have a key for, and its model
1 thing(s) to fix first

Name your provider and model in strategy.toml (see Models and providers) and tra run decides once. tra run --every 15m keeps deciding: the first pass runs now, then one every fifteen minutes on the clock (:00, :15, :30 and so on), so the wait after a pass is whatever is left to the next mark, and the desk tells you the time it ends at.

Type tra on its own inside the desk and you get the console, which is the next section.

What you see, in order

1. The console. Run tra inside your desk and it opens the cockpit: what is ready, what isn't, and the next command to run. Under it is a prompt that takes every command and draws it right there. Arrow keys go back through what you typed, tab completes, help lists the commands and exit leaves. For scripts and cron, tra -c "run --now" runs one command and exits.

2. The pass over your instruments. Type run --every 5m and the desk first refreshes any data series that are due, one line each. Then it looks at every instrument on your list, one data pull apiece, and measures it. The screen steps through them live:

3. One cycle per instrument it takes. Code found the candidates and measured them; the screener chose among them and cited each instrument's own figures; the system's own order is kept beside the choice. The instruments taken get a full cycle. The terminal shows the whole pipeline from the start and updates it as each step begins and ends. Steps that run at the same time spin at the same time, each with its own clock, and the line underneath says who is working right now:

4. The result. When the cycle finishes, the table gives way to the pass over the universe, what was taken and what was held and why, then the data the cycle used and what the round trip costs:

After that, what each validator argued, how conviction weighed the analysts, the risk at the stop, and whether the trade clears the desk's targets:

5. Between cycles. The desk says when the next pass is, on the clock and in minutes, for example next pass at 14:30:00 UTC, in 10m 57s, and counts down to it. An auditor woken by an alarm gets a spinner of its own.

The same cycle as plain text (--plain, a pipe or a log), from a real run on live data, shortened:

cycle 2026-09-29T02-59-16Z BTCUSDT: 5.344s of agents, 15.042s of validators
  funding        ccxt:bybit         age 4.267s
  ohlcv          ccxt:bybit         age 32.746s
  orderbook      ccxt:bybit         age 7.544s
macro      risk-off: the operator declared a bullish state for US10Y; measured correlation is
           neutral (0.0) on a modest sample, weak evidence that does not overturn the declaration
sentiment  positive: declared state is bullish, and the measured figures both support it
technical: long on range_reversion at 0.65 over 5 bars: the close is stretched low in the window
read: zscore=-0.587, vwap_gap_bps=-3.99, ret_1_bps=1.59
validator contra   oppose on 2 cited figure(s)
validator pro      support on 3 cited figure(s)
conviction: 0.800 of 1.0 (macro 1.0, sentiment 0.5, technical 1.300)
risk: 8.29 bps of equity at the stop against the declared 50 bps, size 0.010
cost: 12.87 bps round trip, 2.00 of it estimated
gate: 25.0000 bps claimed clears 12.8723 bps cost plus 0.0000 bps margin
  refused targets: the claimed edge is 1.94x the round trip and the desk declared 2.0x;
                   the cost is certain and the edge is not

That trade was refused. It cleared the cost gate and still died, because this desk asks for an edge of twice the cost and got 1.94 times. A refusal names the figure behind it, every time.

How one cycle decides

flowchart TD
    find[["the system finds the universe and measures each instrument<br/>one data pull each; every value carries its source and age"]] --> wake
    wake{"trigger<br/>has anything moved since the last look?"}
    wake -- "no" --> held["held: one data pull, no tokens spent"]
    wake -- "yes" --> pick["the screener picks among what the system admitted<br/>citing each instrument's own figures"]
    pick -- "none taken" --> held
    pick -- "taken" --> briefs
    briefs["the system writes the briefs<br/>each role sees only the figures its job needs"] --> round1
    subgraph round1["asked at the same time"]
        direction LR
        tech["technical analyst<br/>a direction, a confidence, a horizon"]
        macro["macro analyst"]
        chain["on-chain analyst"]
        mood["sentiment analyst"]
    end
    round1 --> price["the system prices the round trip<br/>fee, spread, impact, funding, slippage"]
    price --> exits{"the stop and the target<br/>the analyst's levels, held inside your bounds<br/>does the trade break even at half its kind winning?"}
    exits -- "no" --> refused
    exits -- "yes" --> round2["validators, as many as you declare<br/>a claim that cites no figure is thrown away"]
    round2 --> matrix{"confluence<br/>do your declared states agree with the direction?"}
    matrix -- "no" --> refused["a refusal that names its figure"]
    matrix -- "yes" --> size["conviction<br/>how much, from your ladder"]
    size --> risk{"risk per trade<br/>what does it lose at the stop?"}
    risk --> gate{"cost gate and targets<br/>does the edge clear the cost, by your margin?"}
    gate -- "no" --> refused
    gate -- "yes" --> intent["the intent, written into the cycle"]
    intent --> venue["venue mode only<br/>one order, the stop and take profit attached"]

Who does what:

The macro, on-chain and sentiment analysts read dated series you declare under sources/. Each one is either a file you keep or a feed the desk refreshes itself (FRED, the Crypto Fear & Greed Index, or any paid vendor that answers JSON over https). tra sources show lists every series with where it came from and how old its last value is, and a value older than its max_age is shown as stale and never counted. Data sources has the details.

Which validators run is yours to declare. A vote never decides on its own: it moves conviction by the weight you give it ([conviction].validator_weight), and a stance counts for what it says beyond its assignment, since a pro that supports is expected to.

Analysts are allowed to disagree. Each one's view becomes a score between -1 and 1, computed from its own figures against the lines you drew, so a macro reading barely past its line counts as a small voice and one far past it counts as a big one. Conviction adds them up: agreement grows the size, opposition shrinks it in proportion, and only opposition that outweighs the case stops the trade. A short at 0.70 confidence against a barely bullish macro and sentiment scores 0.56 and trades at half size; against a strongly bullish context it scores 0 and doesn't trade.

The technical analyst knows what kind of market it is working in before it decides. The system measures the regime on its timeframe (trending up, trending down, ranging or mixed) and on the higher timeframes you list in [run].context_intervals, and it hands over what your macro thresholds say this cycle as well. A setup that doesn't fit the regime, such as a trend trade in a sideways market, is refused by name; [regime] holds the lines.

Everything after the analysts is arithmetic over numbers you declared. No model can place, cancel or resize an order, read a file outside the project, or edit your configuration. Agents has the full table of what an agent can reach, and The cycle walks through every step.

Venues

A cycle reaches venues through ccxt. Here is what that means in practice today:

"Everything" means ccxt reports the five things a safe order needs: send it, attach the exits, read the position, read the open orders, cancel. Only Bybit has been run end to end with real orders, so treat every other venue as untested: start on its practice environment and read what it sends.

Adding the venue you trade on is four steps, and one command writes most of it:

tra venues okx            # what it can do, and which keys it signs with
tra venues okx --setup    # the blocks to paste into envelope.toml, data.toml, strategy.toml and .env

The setup leaves your fees blank on purpose, because a guessed fee would price every trade wrong, and the file won't load until you fill them in. Venues has the full table, the keys each venue needs, and the four steps.

Models and providers

You choose the provider and the model; nothing is hard-coded. Each provider reads its key from the environment (or the .env beside your config) and nowhere else.

Whatever the provider, every answer is parsed against a closed schema by the system before anyone reads it, so a model that only offers JSON mode is held to the same shape as one with strict schemas.

[agents]
provider = "groq"
model = "openai/gpt-oss-120b"
effort = "medium"                    # minimal | low | medium | high | xhigh | max, where the
                                     # vendor takes it; left out, the vendor's default applies
fallback = ["google:gemini-flash-latest", "anthropic:claude-opus-5-5"]

[agents.roles.sentiment_analyst]     # a role that only labels can run on a cheaper model
model = "a-cheaper-model"
effort = "low"

fallback is tried in order when a provider is rate limited or down, with the same brief. A vendor's free tier meters each model on its own, so roles can share a provider across two models and each model keeps its own allowance; tra check judges the load per model and says when one is too much. Every call is a line in usage.jsonl with its tokens and latency, and nothing caps spend unless you declare a ceiling. tra keys --probe proves each key works without sending a prompt. A vendor of your own is about thirty lines (Model providers).

From a replay to real orders

What it trades: linear perpetual futures (USDT- or USDC-margined swaps) on any venue ccxt reaches, long and short, with the leverage and margin mode you declare. Spot, dated futures, inverse contracts and options are not built yet; until they are, venue mode checks the market type on every order and refuses anything that is not a linear perpetual. Boundaries says what adding one would take.

You can stop at any of these steps. Each is one command, and each was run end to end before this README was written.

The replay of that day printed net -294.19 bps for the example core, and it is shown as it came out: a backtest that only shows good news is one nobody should believe.

Venue mode is the only mode that can lose money, so it has a door in front of it. Read the mandate with tra mandate; when you accept it, tra mandate --sign "Your Name" keeps it in the project as MANDATE.md and signs [execution] with your name and today's date, in one step. Signing does not switch anything on. tra check names whatever else is missing.

Your money, your orders, your positions

Once orders flow, three things look after the money, all of them the system's own rules and none of them a model:

Who decides what, in one line each: the analysts propose the direction, your risk rule sets the size, you choose the leverage, and no model touches the last two. Leverage never makes a trade bigger. It only decides how much margin the trade ties up and how far away liquidation sits.

[execution]
mode = "venue"
leverage = 3                     # the one setting you must choose; everything else has a default
margin_mode = "isolated"         # isolated | cross
hold_limit = "timeout"           # close by time after [exit].timeout_bars; or horizon, or none

Underneath, on every venue: the order goes only to the environment you declared (demo, testnet or mainnet); an open position or a working order refuses a second entry; a size off the venue's step is refused rather than rounded; a clock more than a second off the venue's refuses before anything is signed; and Ctrl-C or a service stop cancels a resting order before the process leaves. Every close goes to positions.jsonl and every finished trade to round_trips.jsonl. Capital, orders and positions has every setting, every refusal and the arithmetic behind each one.

One thing to know before you rely on it: the position checks run at the start of each pass of tra run --every. With no desk running, an open position has its venue-side stop and take profit and nothing else, so a desk meant to run unattended belongs under a supervisor.

Orders cross the book by default (taker-taker): they always fill, which is how most desks trade. Point [run].venue_key at a maker-taker channel and entries rest on the book as post-only orders instead - a lower fee, fewer fills, since a resting order can be left behind by the market. Either way the cost gate prices the fee of the channel you chose.

Watching a desk, and what is kept

The console runs commands in its own process, so closing it ends what it was running. A desk that should keep running belongs under a supervisor (systemd, a service manager, tmux), and then you look at it from anywhere with:

tra watch --every 5s       # a read-only view built from the records the desk writes

tra watch opens no connection, holds no key and takes no lock, so opening and closing it does nothing to the desk.

What is kept, and where:

Command line

Every command says what it did. Exit code 0 means cleared, 1 means a gate said no, 2 is a usage error. --json gives machine-readable output and --plain gives text instead of panels.

Getting started

Running

Data

The ladder, research and hosts

What it guarantees, and what is not built yet

Some rules are guarantees, enforced by the system and tests, and every change has to keep them:

• No model touches an order or a key. Models read figures and answer; the system sizes, prices, limits and sends.
• No model can loosen a control. A model can tighten a limit, step the ladder down or arm the kill switch; never widen, promote or disarm.
• One decision, at most one order. A venue error is recorded and the next cycle decides again; nothing is retried around real capital.
• Stale or missing data is refused, never read as zero or as current.

Other things are simply not built yet, and contributions are welcome: spot, inverse, dated futures and options; decentralised venues; more than one account; transfers and treasury; routing and execution algorithms; portfolio accounting. Boundaries lists each one with what it does today and what a contribution would need. The example strategy cores are examples: your edge is yours to declare.

Liability says plainly where responsibility sits when real capital is involved.

Documentation

The full documentation is at docs.bijectivelabs.dev. Its source is in docs/, so a change in behaviour and the page that describes it go in the same pull request.

Development

uv sync
uv run ruff check . && uv run ruff format --check .
uv run mypy
uv run pytest

CONTRIBUTING.md has the branch flow and the standards the code is held to.

License

MIT. See LICENSE; NOTICE lists the third-party software this package builds on.

Built by Bijective Labs.