Get AI summaries of any video or article — Sign up free
Finally My AI AGENTS Has Money + the xAI API  based_terminal Project thumbnail

Finally My AI AGENTS Has Money + the xAI API based_terminal Project

All About AI·
5 min read

Based on All About AI's video on YouTube. If you like this content, support the original creators by watching, liking and subscribing to their content.

TL;DR

A donation agent monitors Blue Sky mentions, evaluates requests with OpenAI (GPT-4o), and sends SOL to the provided wallet only when criteria are met.

Briefing

An AI agent can earn and spend cryptocurrency automatically on social platforms—by watching for tagged posts, verifying payments on-chain, and using OpenAI plus blockchain tooling to decide who gets money or who gets a paid service. The practical takeaway: instead of wiring up complex payment rails, the system uses Solana for near-zero transaction fees and routes requests through Blue Sky mentions (with the same pattern transferable to X or other platforms).

The first working demo is a “donation agent.” A user posts a request that includes a wallet address, and the agent monitors Blue Sky for tagged mentions. When a mention appears, the agent runs an OpenAI-based evaluation (using GPT-4o) to judge whether the request is credible and aligned with a human-focused donation mission (helping people in need). If the request passes one of three donation tiers, the agent sends a small Solana amount—example shown: 0.33 SOL—to the provided address, logs the attempt, and tracks outcomes (successful vs. rejected) in a donation history file. After the transaction, the agent posts a response back on Blue Sky and the on-chain transfer is confirmed.

Under the hood, the setup relies on a few core ingredients: an OpenAI API key, at least one Solana wallet address (plus a hidden private key for signing transactions), and Blue Sky credentials. The agent authenticates to Blue Sky via an API (described as “at Proto”), then initializes a Solana client using an HTTP endpoint. The code also defines donation tiers and uses structured outputs from OpenAI to categorize requests. For transparency and reliability, every mention is evaluated, every donation attempt is recorded, and the system can reject messages that don’t meet the criteria.

A second demo flips the flow: the agent gets paid for services. Here, a Blue Sky “service” agent posts a price (example: 0.05 SOL per search) and instructs users to send payment to a wallet address. When a tagged question arrives, the agent asks for payment, verifies the payment by checking the wallet balance change, and only then runs the service using tool-calling—specifically Brave Search—to fetch live information. The demo request asked for a live Bitcoin price from CoinDesk with a link; after payment verification, the agent replies with the result and the transaction is logged as a completed job.

The broader concept is a two-sided marketplace for agents: donations for help requests and paid micro-services for targeted tasks. The creator also notes that Solana’s low fees make it feasible to run these loops without constantly worrying about transaction costs.

Finally, the same weekend work extends beyond Blue Sky into an X-based “based terminal” concept using the xAI API. The terminal logs in, posts tweets and images, checks for payments, and cycles through actions without spamming. It’s framed as a meme-fueled, harshly worded parody inspired by “terminal of truths,” including image generation via the Flux API and optional crypto tipping (example shown: receiving 0.05 SOL). The result is an experiment in giving AI agents a budget and a way to monetize simple actions—without relying on fiat payment systems like cards.

Cornell Notes

The system demonstrates two on-chain payment patterns for AI agents on social platforms using Solana. First, a donation agent monitors Blue Sky mentions, uses OpenAI (GPT-4o) to evaluate whether a request is worthy, and then sends a small SOL amount to the requester’s wallet while logging outcomes. Second, a service agent posts a fixed price, requests up-front payment, verifies the payment by detecting a wallet balance change, and only then performs a task via tool-calling (Brave Search) and replies with results (e.g., a live CoinDesk Bitcoin price link). Solana is chosen for low fees, making frequent transactions practical. The same architecture can be adapted to other platforms like X.

How does the donation agent decide whether to send money after a Blue Sky mention appears?

After a user tags the agent in a Blue Sky post and includes a wallet address, the agent evaluates the request using OpenAI structured outputs with GPT-4o. It acts as a “donation evaluator” for a human organization mission (helping people in need) and categorizes requests into three donation tiers. Requests that don’t meet the criteria are rejected; accepted ones trigger an on-chain Solana transfer to the provided recipient address. Every attempt is tracked as successful or rejected in a donation history log.

What makes Solana practical for this kind of always-on agent loop?

Solana’s transaction fees are described as effectively negligible for the workflow. The transcript cites an example transaction fee of 0.00005 SOL, and the creator explicitly chooses Solana because the fees don’t materially affect the ability to send small amounts repeatedly. That low-fee environment supports monitoring loops that can process many mentions and payments without the cost becoming prohibitive.

How does the service agent verify that a user actually paid before running the task?

The service agent posts a price and asks the user to send SOL to a specific wallet address. After the user sends funds, the agent monitors for a change in its balance and marks the payment as “verified” once the balance change is detected. Only then does it execute the requested service using tool-calling (Brave Search), generate the response (including a link), and record the job as completed.

What tools and APIs power the paid service example?

The service example uses Brave Search via tool-calling to fetch live information. The agent’s workflow is: detect a tagged question, request payment, verify payment on-chain, call Brave Search to retrieve the result (e.g., Bitcoin price from CoinDesk), then reply with the answer and link. OpenAI is used for orchestration and structured handling of service logic, while Brave Search supplies the external data.

How does the “based terminal” preview relate to the donation/service architecture?

The based terminal is an X-focused, meme-style system using the xAI API. It logs in to X, posts tweets and images, checks for payments, saves actions to a log, and runs in cycles to avoid spamming. It also supports crypto tipping (example: receiving 0.05 SOL) and uses Flux API for image generation. While the transcript doesn’t detail the full on-chain mechanics for X, it frames the terminal as incorporating the same “agent with a budget” idea from the Solana-based Blue Sky demos.

Review Questions

  1. What are the two distinct payment flows implemented (donations vs. paid services), and how does each one use on-chain verification?
  2. Why does the system rely on OpenAI evaluation for donations, and what happens when a request fails that evaluation?
  3. Describe the sequence of events from a user tagging the agent to the agent replying with a Brave Search result.

Key Points

  1. 1

    A donation agent monitors Blue Sky mentions, evaluates requests with OpenAI (GPT-4o), and sends SOL to the provided wallet only when criteria are met.

  2. 2

    Donation tiers and outcomes (successful vs. rejected) are tracked in a persistent donation history log.

  3. 3

    Solana is selected for low transaction fees, making small, frequent transfers feasible for an always-running agent loop.

  4. 4

    A service agent posts a fixed SOL price, requests up-front payment, verifies payment by detecting wallet balance changes, then executes the service.

  5. 5

    Paid services use tool-calling (Brave Search) to fetch live data and respond with results plus links.

  6. 6

    The same agent-with-crypto-budget concept is extended to an X-based “based terminal” using the xAI API, with image generation via Flux and optional crypto tipping.

Highlights

The donation workflow ties social requests to on-chain transfers: tagged Blue Sky posts plus wallet addresses trigger OpenAI evaluation and conditional SOL payments.
Payment verification for services is done by monitoring wallet balance changes; the agent only runs Brave Search after payment is confirmed.
Solana’s low fees (example cited: 0.00005 SOL) are a key enabler for running these loops with small amounts.
The X “based terminal” preview uses the xAI API and Flux image generation, and it supports crypto tipping to influence agent behavior.

Topics

  • Crypto Donations
  • On-Chain Payments
  • AI Agent Orchestration
  • Solana Transactions
  • Brave Search

Mentioned

  • SOL