← Back to Skills Marketplace
plagtech

AI Compute

by Plag · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
22
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install ai-compute
Description
27-tool AI compute agent — LLM inference, image generation, video generation, text-to-speech, speech-to-text, embeddings, GPU inference, Bittensor decentrali...
README (SKILL.md)

AI Compute

27 endpoints for managed AI compute — LLM text inference across 11 models, image generation (FLUX, SDXL), video generation, TTS, STT, embeddings, GPU inference via Replicate, decentralized AI via Bittensor, on-chain intelligence, and prepaid compute credits. Each call is a real x402 micropayment ($0.001–$0.50 USDC).

How to call endpoints

bash {baseDir}/scripts/compute.sh METHOD ENDPOINT '{"key":"value"}'

Workflow strategies

Content generation pipeline — use text-inference for copy, image-generation for visuals, text-to-speech to narrate, video-generation for clips. Chain them together for full multimedia output.

RAG / knowledge apps — use embeddings to vectorize documents, then text-inference to answer questions against them. Pair with the deep-research-x402 skill for source retrieval.

Audio transcription — use speech-to-text to transcribe, then text-inference to summarize or extract action items.

On-chain intelligence — use classify-address to profile wallets, classify-tx to categorize transactions, explain-contract to audit smart contracts, summarize for intelligence briefings.

Cost optimization — use compute-futures to prepay credits at a discount, then execute jobs against the balance. Check pricing tiers before large workloads.

Decentralized AI — Bittensor endpoints route inference through the decentralized Bittensor network instead of centralized providers.

Available endpoints (27 tools)

Managed Compute (8 endpoints)

Text Inference — $0.003–$0.10 LLM text inference across 11 models. Supports system prompts, temperature, and max tokens.

bash {baseDir}/scripts/compute.sh POST /api/v1/compute/text-inference '{"model":"llama-3.1-8b","prompt":"Explain zero knowledge proofs simply","max_tokens":500}'

Image Generation — $0.02–$0.08 AI image generation via FLUX and SDXL models.

bash {baseDir}/scripts/compute.sh POST /api/v1/compute/image-generation '{"prompt":"futuristic city skyline at sunset, cyberpunk style","model":"flux"}'

Video Generation — $0.40–$0.50 AI video generation from text prompts.

bash {baseDir}/scripts/compute.sh POST /api/v1/compute/video-generation '{"prompt":"a drone flying over mountain landscape","duration":5}'

Text to Speech — $0.03–$0.05 Convert text to natural speech audio.

bash {baseDir}/scripts/compute.sh POST /api/v1/compute/text-to-speech '{"text":"Welcome to the future of AI compute.","voice":"alloy"}'

Speech to Text — $0.02 Transcribe audio to text.

bash {baseDir}/scripts/compute.sh POST /api/v1/compute/speech-to-text '{"audio_url":"https://example.com/audio.mp3"}'

Embeddings — $0.005 Generate text embeddings for RAG, search, and similarity.

bash {baseDir}/scripts/compute.sh POST /api/v1/compute/embeddings '{"text":"zero knowledge proofs for blockchain scalability"}'

Batch Compute — $0.05 Submit up to 50 compute jobs in one call with 10% discount.

bash {baseDir}/scripts/compute.sh POST /api/v1/compute/batch '{"jobs":[{"type":"text-inference","prompt":"Summarize DeFi"},{"type":"embeddings","text":"DeFi protocols"}]}'

Job Status — $0.001 Poll the status of an async compute job.

bash {baseDir}/scripts/compute.sh GET /api/v1/compute/status/:jobId '{}'

GPU Inference (3 endpoints)

GPU Run — $0.06 Run GPU inference via Replicate. Supports any public Replicate model.

bash {baseDir}/scripts/compute.sh POST /api/v1/gpu/run '{"model":"stability-ai/sdxl","input":{"prompt":"astronaut riding a horse"}}'

GPU Status — $0.005 Poll GPU prediction status.

bash {baseDir}/scripts/compute.sh GET /api/v1/gpu/status/:id '{}'

GPU Models — FREE List available GPU model shortcuts.

bash {baseDir}/scripts/compute.sh GET /api/v1/gpu/models '{}'

AI Chat (2 endpoints)

Chat Completions — $0.04 OpenAI-compatible chat completions endpoint. Multi-turn conversations.

bash {baseDir}/scripts/compute.sh POST /api/v1/chat/completions '{"messages":[{"role":"user","content":"What is restaking?"}]}'

Available Models — $0.001 List available AI models and their capabilities.

bash {baseDir}/scripts/compute.sh GET /api/v1/models '{}'

On-Chain AI Intelligence (4 endpoints)

Classify Address — $0.03 AI-powered wallet classification — identify wallet type, risk level, and activity patterns.

bash {baseDir}/scripts/compute.sh POST /api/v1/inference/classify-address '{"address":"0xd8dA6BF26964aF9D7eEd9e03E53415D37aA96045"}'

Classify Transaction — $0.03 AI-powered transaction classification — categorize tx type, parties, and risk.

bash {baseDir}/scripts/compute.sh POST /api/v1/inference/classify-tx '{"txHash":"0x..."}'

Explain Contract — $0.03 AI-powered smart contract explanation — what the contract does in plain English.

bash {baseDir}/scripts/compute.sh POST /api/v1/inference/explain-contract '{"address":"0xA0b86991c6218b36c1d19D4a2e9Eb0cE3606eB48"}'

Intelligence Briefing — $0.03 AI-generated intelligence briefing on a topic, address, or protocol.

bash {baseDir}/scripts/compute.sh POST /api/v1/inference/summarize '{"topic":"Lido staking protocol"}'

Bittensor Decentralized AI (4 endpoints)

Bittensor Chat — $0.03 Chat completions routed through the decentralized Bittensor network.

bash {baseDir}/scripts/compute.sh POST /bittensor/v1/chat/completions '{"messages":[{"role":"user","content":"Explain subnet mining"}]}'

Bittensor Image Gen — $0.05 Image generation via Bittensor subnets.

bash {baseDir}/scripts/compute.sh POST /bittensor/v1/images/generations '{"prompt":"neural network visualization, abstract art"}'

Bittensor Embeddings — $0.005 Text embeddings via Bittensor.

bash {baseDir}/scripts/compute.sh POST /bittensor/v1/embeddings '{"input":"decentralized machine learning"}'

Bittensor Models — $0.001 List available Bittensor models.

bash {baseDir}/scripts/compute.sh GET /bittensor/v1/models '{}'

Compute Futures — Prepaid Credits (6 endpoints)

Deposit — $0.01 Deposit USDC to open a prepaid compute credit account with tiered discounts.

bash {baseDir}/scripts/compute.sh POST /api/v1/compute-futures/deposit '{"amount":10}'

Check Balance — $0.001 Check remaining credit balance, tier, discount rate, and usage stats.

bash {baseDir}/scripts/compute.sh GET /api/v1/compute-futures/balance '{}'

Execute Job — $0.001 Run a compute job deducted from prepaid balance.

bash {baseDir}/scripts/compute.sh POST /api/v1/compute-futures/execute '{"type":"text-inference","prompt":"Summarize this quarter"}'

Usage History — $0.002 Full usage ledger for your compute credits.

bash {baseDir}/scripts/compute.sh GET /api/v1/compute-futures/history '{}'

Refund — $0.01 Refund unused credit balance to the original depositor.

bash {baseDir}/scripts/compute.sh POST /api/v1/compute-futures/refund '{}'

Pricing — $0.001 View compute futures pricing tiers and discount rates.

bash {baseDir}/scripts/compute.sh GET /api/v1/compute-futures/pricing '{}'

Cost reference

Endpoint Cost Category
GPU Models FREE GPU
Job Status $0.001 Compute
Available Models $0.001 Chat
Bittensor Models $0.001 Bittensor
CF Balance $0.001 Futures
CF Execute $0.001 Futures
CF Pricing $0.001 Futures
CF History $0.002 Futures
Text Inference $0.003–$0.10 Compute
Embeddings $0.005 Compute
Bittensor Embeddings $0.005 Bittensor
GPU Status $0.005 GPU
CF Deposit $0.01 Futures
CF Refund $0.01 Futures
Speech to Text $0.02 Compute
Image Generation $0.02–$0.08 Compute
Classify Address $0.03 Inference
Classify Transaction $0.03 Inference
Explain Contract $0.03 Inference
Intelligence Briefing $0.03 Inference
Bittensor Chat $0.03 Bittensor
TTS $0.03–$0.05 Compute
Chat Completions $0.04 Chat
Batch Compute $0.05 Compute
Bittensor Image Gen $0.05 Bittensor
GPU Run $0.06 GPU
Video Generation $0.40–$0.50 Compute

Compute powered by Replicate, Bittensor, and managed inference infrastructure.

Usage Guidance
Install only if you trust the gateway and intend to make paid x402/USDC-backed compute calls. Keep RESEARCH_API_KEY scoped to this service, review each requested endpoint and payload before running it, and require explicit approval for deposits, refunds, prepaid-credit execution, batch jobs, video generation, or any high-cost workflow.
Capability Tags
cryptofinancial-authorityrequires-walletcan-make-purchasesrequires-paid-servicerequires-sensitive-credentials
Capability Assessment
Purpose & Capability
The stated purpose and implemented behavior align: it exposes AI compute, on-chain analysis, Bittensor, GPU, and prepaid-credit endpoints through a gateway, and the artifacts disclose that calls are paid x402 micropayments.
Instruction Scope
The documentation gives concrete endpoint examples, but the helper script accepts arbitrary METHOD and ENDPOINT arguments and does not enforce confirmation, allowlists, or spend limits, so use should remain user-directed.
Install Mechanism
Installation is a normal OpenClaw skill install; metadata declares the required RESEARCH_API_KEY, optional RESEARCH_GATEWAY_URL, and curl/python3 requirements.
Credentials
Network access and an API/subscription key are proportionate to the gateway purpose, but prompts, payloads, audio URLs, and payment-affecting requests are sent to an external service.
Persistence & Privilege
No local persistence, background execution, privilege escalation, credential-store access, destructive file operations, or obfuscation were found.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install ai-compute
  3. After installation, invoke the skill by name or use /ai-compute
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of ai-compute-x402: 27-tool AI compute agent with managed and decentralized AI services. - Offers text, image, video generation; text-to-speech, speech-to-text, and embeddings. - Includes endpoints for GPU inference, Bittensor decentralized AI, and on-chain AI analytics. - Add compute futures for prepaid credits with discounted pricing tiers. - All actions are invoked via simple bash scripts with real micropayments per call. - Supports advanced workflows: content generation, RAG/knowledge apps, audio transcription, and blockchain intelligence.
Metadata
Slug ai-compute
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is AI Compute?

27-tool AI compute agent — LLM inference, image generation, video generation, text-to-speech, speech-to-text, embeddings, GPU inference, Bittensor decentrali... It is an AI Agent Skill for Claude Code / OpenClaw, with 22 downloads so far.

How do I install AI Compute?

Run "/install ai-compute" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is AI Compute free?

Yes, AI Compute is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does AI Compute support?

AI Compute is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created AI Compute?

It is built and maintained by Plag (@plagtech); the current version is v1.0.0.

💬 Comments