{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"github-blockrunai--franklin","slug":"blockrunai--franklin","name":"Franklin","type":"agent","url":"https://franklin.run","page_url":"https://unfragile.ai/blockrunai--franklin","categories":["ai-agents"],"tags":["ai-agent","ai-marketing","ai-trading","autonomous-agent","autonomous-economic-agent","blockrun","crypto-native","franklin","llm-agent","micropayments","multi-model","pay-per-action","runcode","typescript","usdc","wallet","wallet-native","x402"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"github-blockrunai--franklin__cap_0","uri":"capability://automation.workflow.autonomous.usdc.payment.execution","name":"autonomous-usdc-payment-execution","description":"Enables agents to autonomously spend USDC stablecoins from an embedded wallet to pay for external services, API calls, and computational resources. The agent evaluates task requirements, estimates costs, and executes blockchain transactions without human approval for each payment. Implements a trust-bounded spending model where the agent operates within pre-configured budget limits and payment thresholds per transaction type.","intents":["I want my agent to pay for third-party API calls (e.g., image generation, data processing) directly from its wallet without manual approval","I need the agent to autonomously purchase computational resources or services based on task complexity","I want to set spending limits and let the agent optimize cost vs quality tradeoffs for different tasks"],"best_for":["autonomous agent developers building economic workflows","teams deploying agents that need to purchase external services at scale","crypto-native applications requiring micropayment infrastructure"],"limitations":["Blockchain transaction finality introduces 12-60 second latency per payment depending on network congestion","USDC availability limited to Ethereum, Polygon, and Solana mainnet/testnet — no L1 Bitcoin or other chains","No built-in spending prediction or cost estimation — requires manual configuration of price feeds per service","Transaction costs (gas fees) can exceed micropayment amounts on Ethereum mainnet, making small payments uneconomical"],"requires":["TypeScript runtime (Node.js 18+)","Wallet with USDC balance (testnet or mainnet)","RPC endpoint access (Alchemy, Infura, or self-hosted)","Agent framework integration (Franklin agent runtime)","Pre-configured spending policy and budget limits"],"input_types":["task description (text)","service pricing schema (JSON)","budget constraints (numeric)"],"output_types":["transaction hash (string)","payment confirmation (JSON with amount, recipient, timestamp)","remaining budget state (numeric)"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-blockrunai--franklin__cap_1","uri":"capability://planning.reasoning.multi.model.provider.routing","name":"multi-model-provider-routing","description":"Routes tasks to different LLM providers (OpenAI, Anthropic, local Ollama, etc.) based on cost, latency, and capability requirements. The agent evaluates task complexity and selects the optimal model provider, potentially splitting work across multiple models. Integrates with the payment system to select models based on budget constraints and expected output quality.","intents":["I want my agent to use cheaper models (e.g., GPT-3.5) for simple tasks and reserve expensive models (e.g., GPT-4) for complex reasoning","I need the agent to fall back to local models when API quotas are exhausted or network is unavailable","I want to optimize cost per task by routing to the most cost-effective provider that meets quality thresholds"],"best_for":["cost-conscious teams running agents at scale","applications requiring model diversity for different task types","teams with hybrid cloud/on-premise infrastructure"],"limitations":["No automatic model capability detection — requires manual configuration of which models handle which task types","Latency variance across providers (OpenAI ~500ms, local Ollama ~2-5s) can cause unpredictable total execution time","Context window limits vary by model — no automatic context truncation or summarization across provider boundaries","No built-in cost prediction accuracy — estimates based on token counts may diverge from actual billing"],"requires":["API keys for at least one provider (OpenAI, Anthropic, etc.)","Model configuration schema defining capabilities and costs per model","TypeScript runtime with async/await support","Network access to provider APIs or local Ollama instance"],"input_types":["task description (text)","model capability requirements (JSON schema)","budget constraint (numeric)"],"output_types":["model selection decision (JSON with provider, model name, estimated cost)","LLM response (text or structured)","actual cost incurred (numeric)"],"categories":["planning-reasoning","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-blockrunai--franklin__cap_2","uri":"capability://automation.workflow.wallet.native.agent.identity","name":"wallet-native-agent-identity","description":"Uses the agent's blockchain wallet address as its persistent identity and reputation anchor. The wallet serves as both a payment instrument and an identity credential, enabling agents to build on-chain reputation, receive payments, and participate in economic protocols. Agent actions are cryptographically signed using the wallet's private key, creating an auditable transaction history.","intents":["I want my agent to have a persistent identity that can accumulate reputation and credit history across multiple tasks","I need to track all agent spending and earnings on-chain for compliance and auditing","I want agents to receive payments from users or other agents directly to their wallet"],"best_for":["autonomous agent networks requiring inter-agent payments and trust","regulated environments needing full transaction auditability","applications building agent reputation systems"],"limitations":["Wallet recovery and key management are developer responsibilities — no built-in key rotation or secure enclave support","On-chain identity is pseudonymous — no built-in KYC/AML integration for regulatory compliance","Transaction history is immutable and public on mainnet — privacy concerns for sensitive agent operations","Wallet creation and funding requires manual setup — no automated onboarding for new agents"],"requires":["Blockchain RPC endpoint (Ethereum, Polygon, or Solana)","Private key management (environment variables, secure vaults, or HSM)","USDC contract ABI and deployment address for target network","TypeScript ethers.js or web3.js library"],"input_types":["wallet private key (hex string or mnemonic)","network identifier (string: 'ethereum', 'polygon', 'solana')"],"output_types":["wallet address (0x... format)","transaction signature (hex string)","on-chain transaction receipt (JSON)"],"categories":["automation-workflow","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-blockrunai--franklin__cap_3","uri":"capability://tool.use.integration.x402.payment.protocol.negotiation","name":"x402-payment-protocol-negotiation","description":"Implements HTTP 402 Payment Required protocol for service negotiation and cost signaling. When an API returns a 402 status with pricing information, the agent automatically evaluates the cost, executes payment via its wallet, and retries the request with proof of payment. Enables seamless integration with X.402-compliant services without manual payment handling.","intents":["I want my agent to automatically handle services that require per-request payments via HTTP 402","I need the agent to negotiate pricing and payment terms with X.402-compliant APIs","I want to integrate with services that use micropayment models without custom payment logic"],"best_for":["agents integrating with X.402-compliant API providers","micropayment-based service ecosystems","developers building agent-to-service economic protocols"],"limitations":["X.402 adoption is minimal — most APIs do not implement this standard, limiting practical applicability","No built-in dispute resolution — if service fails after payment, agent has no automatic refund mechanism","Payment proof (e.g., transaction hash) may not be immediately available due to blockchain finality delays","Requires service provider to implement X.402 server-side — no fallback for non-compliant services"],"requires":["X.402-compliant API endpoint","Agent wallet with sufficient USDC balance","HTTP client with 402 status code handling","Blockchain RPC for transaction submission and confirmation"],"input_types":["HTTP request (method, URL, headers, body)","402 response with pricing schema (JSON)"],"output_types":["HTTP response after payment (status 200+)","payment transaction hash (string)","service response data (varies by endpoint)"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-blockrunai--franklin__cap_4","uri":"capability://planning.reasoning.task.cost.estimation.and.budgeting","name":"task-cost-estimation-and-budgeting","description":"Estimates the cost of tasks before execution by analyzing task complexity, required model capabilities, and external service calls. The agent compares estimated cost against remaining budget and either executes the task, requests approval, or defers to a cheaper alternative. Maintains a budget ledger tracking cumulative spending and remaining allocation per time period.","intents":["I want the agent to refuse tasks that exceed its remaining budget without wasting resources","I need visibility into estimated vs actual costs for each task to optimize spending","I want to set daily/weekly spending limits and have the agent respect them automatically"],"best_for":["teams deploying agents with fixed budgets or cost constraints","applications requiring cost transparency and predictability","multi-agent systems with shared budget pools"],"limitations":["Cost estimation accuracy depends on historical data — new task types may have unpredictable costs","No built-in cost prediction for complex multi-step workflows — requires manual estimation per step","Blockchain transaction costs (gas) are volatile and difficult to predict in advance","Budget ledger is in-memory — no persistence across agent restarts without external storage"],"requires":["Historical cost data for tasks and models (CSV, JSON, or database)","Price feed for USDC/USD conversion (Chainlink, CoinGecko, or manual config)","Budget configuration (total allocation, time period, per-task limits)","Task complexity classifier (heuristic or ML model)"],"input_types":["task description (text)","task metadata (JSON: model requirements, external services, complexity estimate)"],"output_types":["cost estimate (numeric, in USDC)","budget approval decision (boolean)","remaining budget after task (numeric)"],"categories":["planning-reasoning","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-blockrunai--franklin__cap_5","uri":"capability://code.generation.editing.code.execution.with.payment.integration","name":"code-execution-with-payment-integration","description":"Executes arbitrary code (JavaScript/TypeScript) in a sandboxed runtime while integrating payment execution for external service calls. When code invokes paid services (e.g., API calls, model inference), the agent automatically handles payment negotiation and execution. Provides a code execution environment where payment is a first-class primitive alongside standard I/O.","intents":["I want my agent to run custom code that calls paid APIs and automatically handle payments","I need to execute complex workflows that mix computation and external service calls with seamless payment","I want to write agent logic in TypeScript without manually managing payment flows"],"best_for":["developers building complex agent workflows with custom logic","applications requiring flexible task execution beyond pre-built capabilities","teams integrating agents into existing TypeScript codebases"],"limitations":["Sandbox isolation is incomplete — no guarantee against resource exhaustion or side-channel attacks","Code execution latency adds 100-500ms per execution depending on code complexity","No built-in timeout enforcement — long-running code can block agent execution","Debugging sandboxed code is difficult — limited visibility into runtime errors and stack traces"],"requires":["Node.js 18+ runtime","TypeScript compiler or ts-node for code execution","Sandbox library (e.g., vm2, isolated-vm, or custom implementation)","Agent wallet with USDC balance for payment execution"],"input_types":["TypeScript/JavaScript code (string)","execution context (JSON: variables, function bindings, payment config)"],"output_types":["code execution result (any JSON-serializable type)","payment transactions executed (array of transaction hashes)","execution logs and errors (string)"],"categories":["code-generation-editing","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-blockrunai--franklin__cap_6","uri":"capability://automation.workflow.agent.to.agent.payment.and.delegation","name":"agent-to-agent-payment-and-delegation","description":"Enables agents to pay other agents (identified by wallet address) to perform subtasks or delegate work. One agent can transfer USDC to another agent's wallet with a task specification, and the receiving agent executes the work and returns results. Implements a marketplace-like protocol where agents negotiate fees and service levels.","intents":["I want my agent to delegate complex tasks to specialized agents and pay them for the work","I need to build a network of agents that can trade services and payments with each other","I want agents to collaborate on tasks by splitting work and sharing revenue"],"best_for":["multi-agent systems with specialized capabilities","agent networks requiring inter-agent economic coordination","applications building agent marketplaces or DAOs"],"limitations":["No built-in service level agreements (SLAs) — agents can accept payment and fail to deliver without recourse","Task specification format is unstandured — requires manual protocol definition per agent pair","No escrow or dispute resolution mechanism — payment is irreversible once sent","Agent discovery is manual — no built-in registry of available agents and their capabilities"],"requires":["Wallet addresses for both delegating and receiving agents","Task specification schema (JSON or custom format)","USDC balance in delegating agent's wallet","Receiving agent must be running and listening for payment events"],"input_types":["recipient agent wallet address (0x... format)","task specification (JSON)","payment amount (numeric, in USDC)"],"output_types":["payment transaction hash (string)","task execution result (varies by task type)","execution status and logs (JSON)"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-blockrunai--franklin__cap_7","uri":"capability://safety.moderation.spending.policy.and.guardrails.enforcement","name":"spending-policy-and-guardrails-enforcement","description":"Enforces configurable spending policies that limit agent autonomy based on rules like maximum per-transaction amount, daily spending caps, blacklisted recipients, and approval thresholds. Policies are evaluated before each payment execution, and violations either block the transaction or escalate to human review. Supports policy versioning and audit logging of all policy decisions.","intents":["I want to limit how much my agent can spend per transaction to prevent catastrophic failures","I need to enforce compliance rules like not paying certain addresses or services","I want to require human approval for large transactions while allowing small ones to execute autonomously"],"best_for":["enterprise deployments requiring financial controls and compliance","teams managing agents with significant budgets","regulated industries requiring audit trails and approval workflows"],"limitations":["Policy evaluation adds 50-200ms latency per transaction depending on rule complexity","No built-in policy conflict detection — overlapping rules may produce unexpected behavior","Approval workflows require external integration (e.g., Slack, email) — no built-in notification system","Policy changes are not retroactive — existing transactions cannot be reversed based on new policies"],"requires":["Policy configuration file (JSON or YAML)","Approval system integration (webhook, email, or manual review interface)","Audit log storage (database or file system)","Policy versioning system (git, database, or manual tracking)"],"input_types":["payment transaction details (JSON: amount, recipient, service type)","policy configuration (JSON schema)"],"output_types":["policy evaluation result (boolean: approved/denied)","policy violation details (JSON: rule violated, reason)","audit log entry (JSON: timestamp, decision, policy version)"],"categories":["safety-moderation","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":37,"verified":false,"data_access_risk":"high","permissions":["TypeScript runtime (Node.js 18+)","Wallet with USDC balance (testnet or mainnet)","RPC endpoint access (Alchemy, Infura, or self-hosted)","Agent framework integration (Franklin agent runtime)","Pre-configured spending policy and budget limits","API keys for at least one provider (OpenAI, Anthropic, etc.)","Model configuration schema defining capabilities and costs per model","TypeScript runtime with async/await support","Network access to provider APIs or local Ollama instance","Blockchain RPC endpoint (Ethereum, Polygon, or Solana)"],"failure_modes":["Blockchain transaction finality introduces 12-60 second latency per payment depending on network congestion","USDC availability limited to Ethereum, Polygon, and Solana mainnet/testnet — no L1 Bitcoin or other chains","No built-in spending prediction or cost estimation — requires manual configuration of price feeds per service","Transaction costs (gas fees) can exceed micropayment amounts on Ethereum mainnet, making small payments uneconomical","No automatic model capability detection — requires manual configuration of which models handle which task types","Latency variance across providers (OpenAI ~500ms, local Ollama ~2-5s) can cause unpredictable total execution time","Context window limits vary by model — no automatic context truncation or summarization across provider boundaries","No built-in cost prediction accuracy — estimates based on token counts may diverge from actual billing","Wallet recovery and key management are developer responsibilities — no built-in key rotation or secure enclave support","On-chain identity is pseudonymous — no built-in KYC/AML integration for regulatory compliance","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.3397511258612244,"quality":0.26,"ecosystem":0.6000000000000001,"match_graph":0.25,"freshness":0.75,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.1,"match_graph":0.28,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:21.549Z","last_scraped_at":"2026-05-03T13:57:09.058Z","last_commit":"2026-05-03T09:57:17Z"},"community":{"stars":499,"forks":35,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=blockrunai--franklin","compare_url":"https://unfragile.ai/compare?artifact=blockrunai--franklin"}},"signature":"xQt93lFndl3UdjvcwFx8AeQigynHlHmzbJmBKx0TPfHqi69ZTBXxr5FMqzBI4zX/BeYPA5gp0jFV1Yf/Zl4ZDg==","signedAt":"2026-06-20T18:48:08.711Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/blockrunai--franklin","artifact":"https://unfragile.ai/blockrunai--franklin","verify":"https://unfragile.ai/api/v1/verify?slug=blockrunai--franklin","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}