Design philosophy
Condor Agents separate what LLMs do well, reasoning under uncertainty, from what traditional software does well, reliable and repeatable execution.
The result is an agent that thinks like a discretionary trader but acts like a systematic one, with a full record of every tick.
Executor-based trading
Agents never place orders directly. The risk gate always refusesplace_order. An agent trades in one of two ways:
- Executors. It creates Hummingbot executors (position, grid, DCA, order or LP) with the
create_*_executortools. - Controller-based bots. It deploys and retunes a Hummingbot bot that runs a controller, with
manage_bots. A deploy may declare a loss cap (max_global_drawdown_quote). Leaving it out deploys with no platform-side cap. A cap you set can’t exceed the session’smax_position_size_quote, and must be below the capital the bot trades. See the Market Making Expert for a loop that works this way.
Ownership through controller_id
Each loop session has its own ID, such asmy_agent.my_loop_3. Every executor the session creates must carry that ID as its controller_id; the risk gate refuses a create without it. This gives you:
- Isolation. An agent only manages its own executors.
list_executorsreturns the whole fleet on the server, so the agent can see other executors, but the risk gate refuses any attempt to stop an executor owned by another live session. - A virtual portfolio. Positions and PnL are tracked per
controller_id, so each session has its own book even when several agents share one exchange account. See Inventory. - Position handover. When an executor closes with
keep_position=true, the position stays in that session’s inventory.
Mental model
An agent is a folder on disk and a tick loop in memory. The folder is its long-term memory; the data it gathers each tick is its situational awareness; the LLM is its decision function; executors and bots are its hands; the risk gate is the wrist it can’t move past.
Run modes
Choose the mode in the Start dialog or with the loop’sexecution_mode setting.
Only
loop creates a session. Start with dry_run to check that the agent, server and exchange are wired up.
Risk limits
Each session has six risk limits, set in the loop’sdefault_config.risk_limits or in the Start dialog:
What each one does is on the Architecture page.
Stop vs. shutdown
- Stop ends the loop and leaves its executors, positions and bots open.
- Emergency shutdown closes the session’s executors according to the agent’s
shutdown.mdpolicy, then stops. Ashutdown_drawdown_pctbreach triggers it automatically.
Getting started
- Run a shipped agent. Follow one of the agent guides.
- Create your own. Ask Condor to build one with its Agent Builder, or write the folder yourself as described in Architecture.
- Watch and control it. See Agent Loops.

