The pitch in one paragraph
Most coding agents write code. Franklin Agent writes code and spends money to get the job done. It holds a USDC wallet, picks the best model per task from 55+ providers, purchases trading data, generates images, pays for web search — all autonomously. You state an outcome and set a budget. Franklin Agent decides what to call, what to pay for, and when to stop. Every paid action routes through the x402 micropayment protocol and settles against your own wallet. No subscriptions. No API keys. No account. The wallet is the identity.
Built by the BlockRun team. Apache-2.0. TypeScript. Ships as one npm package.
YOPO — You Only Pay Outcome
Not a subscription (pay for access). Not a generic pay-per-call (pay for trying). You pay only for the work Franklin Agent delivers. Provider cost + 5%, settled per action in USDC. No monthly fees. No rate limits. No overdraft.
Quick start
# 1. Install
npm install -g @blockrun/franklin
# 2. Run (free — uses NVIDIA Nemotron & Qwen3 Coder out of the box)
franklin
# 3. (optional) Fund a wallet to unlock Sonnet, Opus, GPT, Gemini, Grok, + paid APIs
franklin setup base # or: franklin setup solana
franklin balance # show address + USDC balance
That's it. Zero signup, zero credit card, zero phone verification. Send $5 of USDC to the wallet and you've unlocked every frontier model and every paid tool in the BlockRun gateway.
Prefer a GUI? Try Franklin for VS Code
The same agent ships as a VS Code extension — chat panel, model picker, wallet balance, image / video generation, inline diff cards — all driven by the wallet you already funded for the CLI.
VS Code → Extensions (Cmd+Shift+X / Ctrl+Shift+X)
→ search "Franklin" → Install
→ click the Franklin icon in the Activity Bar
Free models work immediately. Paid models, image gen, and video gen activate the moment your wallet has USDC. The CLI and the extension share the same ~/.blockrun/ config and session history, so jumping between terminal and VS Code is seamless.
YOPO
You Only Pay Outcome. This is Franklin Agent's pricing model, and it is the opposite of almost every other AI product you use.
| | You pay for... | Result | | ----------------------- | -------------------------------------------- | ------------------------------------ | | AI subscription | Access. Paid whether you use it or not. | $20–200/month, rate-limited. | | Pay-per-call (OpenAI API, etc.) | Every attempt — even failed ones. | Hidden cost from retries, dead ends. | | Franklin Agent (YOPO) | The outcome. Each signed micropayment. | Provider cost + 5%. No more. |
Three consequences fall out of this:
- No subscriptions. Use Franklin for $0.50 one week and $50 the next — you pay for compute actually consumed, nothing more.
- No rate limits. Subscriptions throttle you when you need AI most. YOPO has no artificial caps — if you have USDC, you have access.
- No overdraft. The wallet balance IS the hard limit. When it's empty, Franklin stops. No surprise bills, no 3 a.m. rate-limit walls.
Concretely — $1 in USDC gets you roughly:
- ~400K GPT-4o input tokens
- ~7M DeepSeek tokens
- ~13M Gemini Flash tokens
- ~20 DALL-E 3 images
- ~40 Exa neural web searches
- Unlimited agent-tested NVIDIA free tier (Qwen3 Coder + Llama 4 Maverick, no wallet needed)
A new category
Economic Agent
Software that can hold a wallet, price its own actions, spend toward an outcome, and stop at a hard budget cap.
Most AI products fit into one of three buckets: they answer questions, write code, or automate a fixed workflow. None of them can spend money.
Franklin can. It combines purchasing power (it pays for models, tools, and APIs), budget awareness (cost is part of the loop, not an afterthought), cross-vertical execution (code, trading, research, marketing, ops), and hard stopping conditions (wallet balance is a real constraint, not a suggestion).
That is why Franklin is an economic agent, not just a task agent.
What Franklin can execute
Franklin is chat-first. You do not wire a DAG, configure six API keys, or commit to one model vendor. You state an outcome. Franklin decides what to read, search, fetch, call, and pay for.
📈 Trading signals
> what's BTC looking like today?
✓ TradingSignal BTC
## BTC Signal Report
Price: $71,056 USD (+2.3% 24h)
Market Cap: $1.42T
24h Volume: $29.6B
### Technical Indicators (30d)
- RSI(14): 53.2 — neutral
- MACD: 339.21 / Signal: 280.45 — bullish crossover
- Bollinger: within band (upper $73,773 / lower $64,545)
- Volatility: 35.3% annualized — medium
> if I enter at 65000 with $1000, where should my stop be?
Based on ATR(14) and support at $63,500:
Entry: $65,000 · Stop: $63,200 (−2.8%) · Risk: $27.69
Risk/reward to $70K target: 1:2.8 ✓
Live data from CoinGecko. RSI, MACD, Bollinger, and volatility computed locally. No API key needed.
🎨 Image generation
> generate a logo for my AI startup — minimalist, dark background
✓ ImageGen "minimalist AI startup logo, dark background..."
Saved: generated-logo-1713052800.png (1024x1024)
Generates images via DALL-E / GPT Image directly from the CLI. Paid from your wallet — no OpenAI API key needed.
📱 Remote control via Telegram
Run franklin telegram on an always-on machine (set TELEGRAM_BOT_TOKEN + TELEGRAM_OWNER_ID) and drive Franklin from your phone. Owner-locked, session-resumable across restarts, slash commands (/new, /balance, /status). Trading, content, dev work — all reachable from a Telegram chat.
🔎 Research, code, anything with a budget
> compare the top 5 AI agent pricing models, summarize the patterns, and save a note for me
✓ WebSearch ai agent pricing models
✓ WebFetch 5 articles
✓ Write notes/agent-pricing.md
Summary:
- Most agents hide pricing behind monthly seats
- Usage-based products win with power users and teams
- Wallet-based billing is still basically empty whitespace
> refactor src/auth.ts to use the new jwt helper, then run the tests
✓ Read src/auth.ts $0.002
✓ Read src/lib/jwt.ts $0.001
✓ Edit src/auth.ts (-24 +31 lines) $0.008
✓ Bash npm test $0.000
› 142 passing · 0 failing · 2.4s
Done in 18s · $0.011
Code is still first-class. It is just one workload, not the category.
Every tool call is itemized. Every token is priced. When the wallet hits zero, Franklin stops. No overdraft, no surprise bill, no rate-limit wall at 3 a.m. — this is YOPO in practice.
Smart Router
55+ models. One decision. Zero guesswork.
You don't pick models. Franklin picks for you.
The Smart Router classifies every request — coding, trading, reasoning, research — and selects the model with the best quality-to-cost ratio. Trained on 2M+ real requests from the BlockRun gateway, continuously updated.
> refactor this auth module to use JWT
CODING kimi-k2.5 · 12.4K in / 2.1K out · $0.0023 saved 84%
> what's the BTC outlook for the week?
TRADING grok-4-1-fast-reasoning · 8.2K in / 1.8K out · $0.0008 saved 95%
> prove that this algorithm is O(n log n)
REASONING claude-sonnet-4.6 · 15.1K in / 3.4K out · $0.0312
Every response shows which model was chosen, why, and how much you saved vs. always using