Unlike generic crypto research assistants, Fere turns market signals into autonomous trading workflows. Agents research opportunities, build trade setups, optimize routes and fees, execute with a wallet, and monitor strategies 24/7 across crypto and Polymarket. Standout features include autonomous Polymarket trading, entry/exit rules, stop-loss controls, execution routing, and lower-cost agent runs.
What's great
ai-driven investment strategies (2)market pulse (1)
I am always interested in trying new ai-driven investment strategies, and this is one I have been pleased with so far! I am excited to keep experimenting to see how far I can get with it in terms of returns in my portfolio.
Report
7 views
Is there a mode where it suggests trades but waits for your confirmation before executing? Would love to start there before going fully autonomous. Great product either way.
Fere AI
@kumar_ritesh21 Not exactly, and here's the honest reason why.
A confirm-before-execute mode burns a huge amount of tokens per trade decision. It's technically possible but it makes the product expensive and slow for most users. Didn't feel like the right trade-off.
Instead we give you backtesting and simulation - run your strategy, validate it, get comfortable with how it behaves. Once you're confident, you go live.
Our pre-built strategies have already been through that process. Tested, refined, consistently delivering. So you're covered either way.
How does Fere handle slippage during execution — does the routing layer adjust in real time, or is it pre-set before the trade runs?
Fere AI
@hirogure Real-time, not pre-set. Our routing layer reads market conditions live and adapts as it goes. If execution doesn't clear during a volatile move, the system keeps adjusting — trying different routes and recalibrating — until the trade goes through. Pre-set slippage values tend to break exactly when you need them to work, so we built around that.
@pranavprakash That makes sense — pre-set tolerances failing in volatile conditions is exactly the failure mode that matters most. Curious how the system handles a scenario where no route clears within an acceptable range — does it abort and surface that to the user, or keep retrying until conditions improve?
Fere AI
@hirogure After sometime, when it can't find a reasonable option and has spent all it's budget (time budget + thinking budget + retries budget), it gives up and tells the user why it didn't happen. It can also suggest alternate strategies like investing later or setting up a Limit Order for sale so it can happen after sometime, or just to schedule the same txn after a few minutes.
Powabase
Do you get to pick the LLM to use? Is the cost for the LLM assessments pass-through or included?
Fere AI
@hunter_powabase Right now, you don't. The LLM Costs are included in the credits charged for each conversation. This means our credits per chat is dynamic. Simple stuff consumes fewer credits than complex ones.
We are considering a possibility of letting users choose their own models in a future release.
Pro Tip: You can also use our MCP or CLI to make it work with your own agent (Claude Code, Hermes, OpenClaw etc). https://docs.fereai.xyz/mcp
Congrats on the launch, @0xaron and @pranavprakash 🚀
How does the agent handle slippage or liquidity spikes during an unattended 24/7 run?
Fere AI
@0xaron @aadhitya_muralidharan Real-time adjustment. The routing layer reacts to live market conditions, and during volatile windows where execution fails on the first pass, the system keeps adjusting until the trade clears. A pre-set slippage number is fine in calm markets and useless in the moments that actually matter — so we built the layer to adapt continuously instead.
Is this a tool for automating my strategies or for trading instead of me? I previously read about experiments where AI services traded on their own, and all of them ended up losing money in the end)
Fere AI
@natalia_iankovych It automates, refines and evolves your strategy. You can build your own or choose from one of the tested and deployed pre-existing strategies. These can be backtested, forward tested and also evolves over time. This ensures your strategies are an up to date reflection of the current market dynamics.
Swach Discord
Nice, how does it handle flash crashes or black swans?
Fere AI
@rahul_singh_bhadoriya Great question, and the one we take seriously. A few layers to how we handle it:
First, the agent doesn't just execute blindly. Risk parameters: position sizing, stop logic, exposure limits - are built into the workflow before a trade ever fires.
Second, flash crashes are a speed problem. Our execution layer is designed to react faster than a human watching a chart, but we also have circuit-breaker style controls so it doesn't double down into a free fall.
Black swans are harder - no system predicts the truly unprecedented. What we focus on is limiting downside when the model's confidence is low and the market is behaving anomalously. The agent knows when to step back.
Happy to go deeper on any specific scenario.
Krisp
How finance and investing savvy you need to be to start using the app?
Fere AI
@asti_pili You don't need to be a quant to use Fere. That's kind of the point.
The agent handles the research, the signal reading, and the execution. Your job is telling it what you want, risk level, assets, strategy style.
If you've ever bought crypto before, you have enough context to start. The rest you pick up as you go.
Where it gets more powerful is when you layer in your own preferences over time. But day one? Just dive in.