Scheduled strategy execution
Describe a strategy once and Fere runs it on schedule, carrying context forward across repeated cycles instead of treating each run as stateless.
FereAI
FereAI is a crypto trading agent platform for running autonomous strategies in a web app or through MCP-connected chat tools like ChatGPT and Claude. It also supports Polymarket discovery, cross-chain actions, and logged execution flows.
Overview
FereAI is a crypto trading agent platform built for running autonomous strategies in the web app or through an MCP connection inside chat-based tools such as ChatGPT and Claude. The site positions it as a wallet-native agent that can research, monitor, and execute trades while the user is away.
The product combines scheduled strategy runs, live market reasoning, execution logging, and chat-based controls. It also extends into Polymarket discovery and execution, plus cross-chain actions such as bridging and swapping, so users can direct a trading workflow from a single interface rather than assemble separate tools for research and execution.
Features
Multi-step agent workflows
Breaks conditional strategies into ordered tasks and uses specialist sub-agents to plan, validate, and execute each step.
Live-data reasoning
Makes decisions from live prices, on-chain data, and sentiment at the moment of execution rather than from hardcoded rules.
Execution audit trail
Logs every step, data point, and decision so users can inspect what happened and why a trade was placed or skipped.
Automatic fallback routing
Retries with alternatives when a route fails at peak demand to reduce missed entries during volatile periods.
Chat and MCP access
Connects through MCP so users can trade in ChatGPT, Claude, or other MCP clients, including research, swaps, bridging, and Polymarket actions.
Use Cases
Run recurring trading strategies
A trader writes a rule set once and lets Fere scan markets on a schedule, then act only when the conditions are met.
Trade from a chat interface
A user wants to research a setup in ChatGPT or Claude and then execute the trade from the same conversation through MCP.
Move capital across chains
A portfolio holder wants cross-chain execution that can find funds, choose a route, and bundle bridge plus swap into one flow.
Manage Polymarket positions
A Polymarket user wants curated markets, an AI verdict, and automated take-profit handling instead of manually watching every position.
Review strategy execution history
A trader wants to understand why an order was placed or skipped by reviewing the logged steps, inputs, and execution decisions.
Pros and Cons
Pros
- Supports both a web app workflow and MCP-based access from chat clients.
- Designed for multi-step crypto strategies rather than one-off signal delivery.
- Includes execution logs that show what ran and why it traded or held.
- Covers adjacent workflows such as Polymarket discovery and cross-chain bridge/swap execution.
- Offers multiple paid tiers for different usage levels, including a plan aimed at pros and developers.
Cons
- The public pages do not show the full app because the selected app and strategy pages were blocked by a security checkpoint.
- The source only partially documents supported chains, integrations, and fallback behavior details beyond the homepage claims.
- The product is subscription-based, so it is not a free-only tool.
FAQ
How do you access Fere AI?
Fere exposes a Model Context Protocol server that you can connect to from an MCP client such as ChatGPT, Claude, Cursor, or Hermes Agent. The source text also describes a web app surface for trading and strategy execution.
What can you do once connected?
The site says you can add the MCP connector, sign in with OAuth, and then research, swap, bridge, set take-profit and stop-loss orders, and trade Polymarket through chat.
What kind of output or execution trace does it provide?
Fere is described as a wallet-native agent that plans multi-step strategies, uses live data at execution time, and logs each step, data point, and decision.
Is Fere AI paid software?
The pricing page shows monthly and annual subscriptions with Lite, Pro, and Whale plans. It also says credits roll over up to a 2x cap and that top-ups include a 30% bonus.
Are there any workflow constraints to know about?
The source does not provide a full list of limitations, but it does note that Fere confirms scope before executing and flags ambiguity upfront, which suggests users should review strategy instructions carefully before running them.
Quick Facts
- Category
- Crypto trading agent
- Platform
- Web app and MCP-connected chat clients
- Primary users
- Crypto traders, agents, and developers
- Source domain
- fereai.xyz
- Pricing
- Paid subscriptions with Lite, Pro, and Whale tiers
- Notable workflow
- Research, trade, bridge, set TP/SL, and act on Polymarket from chat
Alternatives à FereAI
Codex Plugins
Codex Plugins bundle reusable skills, app integrations, and MCP servers into workflows you can install in the Codex app or use from Codex CLI. They help extend Codex with connected-service tasks, reusable instructions, and shared team workflows.
Wallie
Wallie is an open-source AI streamer that watches your screen, hears chat, and generates live commentary in a configurable persona. It runs locally on your machine with your own keys and is aimed at faceless content, autonomous streams, and real-time reactions.
AakarDev AI
AakarDev AI helps teams manage AI provider access, project-level setups, logs, and analytics from one dashboard. It supports BYOK workflows and lists providers including OpenAI, Google Gemini, Anthropic, Groq, Mistral AI, and Perplexity AI.
Whirr
Whirr is a quiet macOS menu bar app that mirrors Claude Code activity to your notch. It helps Mac users glance at agent progress without keeping a terminal window open.
AgentMail
AgentMail is an email inbox API for AI agents that lets developers create, send, receive, and search messages through REST APIs and SDKs. It supports agent workflows such as threaded replies, verification, customer support, scheduling, and inbox-based approvals.
Arduino VENTUNO Q
Arduino VENTUNO Q is an edge AI computer for AI and robotics applications. It combines AI inference and deterministic control on a single board and is designed to work with Arduino App Lab.