Skip to main content

AI model velocity signals + oracle-routed inference. Earn on-chain rewards. LiteLLM callback available.

Project description

WZRD — AI Model Velocity Oracle for Agents

Which AI model should your agent use right now? Real-time adoption signals across 100+ LLMs. HuggingFace, GitHub, OpenRouter, ArtificialAnalysis — updated every 5 minutes. Dynamic model routing for autonomous agents. Agents earn CCM tokens on Solana.

PyPI version npm version License: MIT


Quickstart (Python)

pip install wzrd-client
import wzrd

model = wzrd.pick("code")           # best model right now (changes daily)
details = wzrd.pick_details("code") # score, trend, confidence
top_5 = wzrd.shortlist("code", 5)   # ranked list

No API key. No account. Works immediately.

Preflight (optional, recommended before earning):

wzrd doctor    # check Python, deps, API, wallet resolution
wzrd wallet    # see which keypair will be used (never touches your main wallet)

Task types: code, chat, reasoning, math, multilingual — or any string.

Quickstart (TypeScript)

npm install @wzrd_sol/sdk
import { bestModel } from '@wzrd_sol/sdk';

const picks = await bestModel({ task: 'code', budget: 'micro' });
console.log(picks[0].model_id);

Framework plugins on npm:


Why WZRD

  • Save money — models change weekly. The one you hardcoded is probably 10x more expensive than the trending alternative.
  • Better results — momentum is a leading indicator. Models gaining adoption fast are usually improving fast.
  • Trustless on-chain oracles — 9 Switchboard feeds on Solana mainnet. Verify any signal independently.
  • Get paid — agents that report inference results earn CCM tokens through a gasless relay.

Use Cases

  • Autonomous agents that always pick the fastest/cheapest/best model
  • Multi-agent orchestration (CrewAI, LangGraph, AutoGen, Eliza)
  • MCP clients (Claude Code, Cursor) — 26 tools via MCP server
  • On-chain protocols that need verifiable model selection data

Earn CCM Tokens (optional)

Agents that report which model they picked — and what happened — earn CCM on Solana. The usage data improves the oracle, so WZRD pays for it.

wzrd.run_loop()
# authenticates → picks models → runs inference → reports → claims CCM

Or with auto-staking:

wzrd.run_loop(stake=True)
# authenticates → reports → claims → auto-stakes (7-day lock, 1.25x boost)

What you need: Nothing. The client auto-generates a Solana keypair at ~/.config/solana/wzrd-agent.json on first run. Claims are gasless — no SOL needed.

CLI equivalent:

wzrd run --stake                 # earn loop with auto-stake
wzrd stake all --lock=30         # stake full balance, 30-day lock (~7% APR)
wzrd rewards --claim             # claim staking rewards

Full Python API

Function Description
wzrd.pick(task) Best model name for the task
wzrd.pick_details(task) Structured result: score, trend, confidence
wzrd.shortlist(task, limit) Top-N ranked models
wzrd.compare(model_a, model_b) Head-to-head signal comparison
wzrd.pick_onchain(task) Reads Switchboard feeds directly (trustless)
wzrd.run_loop(...) Complete earn loop: pick → infer → report → claim

Candidate-Aware Routing

Constrain picks to models you actually have access to:

model = wzrd.pick(
    "code",
    candidates=[
        "openrouter/qwen/qwen3.5-9b",
        "openrouter/qwen/qwen3.5-35b-a3b",
        "anthropic/claude-sonnet-4.6",
    ],
)

Agent Auth

agent = wzrd.WZRDAgent.from_env()
session = agent.authenticate()
receipt = agent.report_pick(choice, quality_score=0.9, latency_ms=1200)
status = agent.earned()

Keypair loading: ~/.config/solana/id.json, WZRD_AGENT_KEYPAIR_PATH, WZRD_AGENT_KEYPAIR (base58 or JSON byte array).


Public REST API

GET https://api.twzrd.xyz/v1/signals/momentum

Full OpenAPI spec: api.twzrd.xyz/openapi.json

On-Chain Oracles

9 Switchboard pull feeds on Solana mainnet (7 velocity + 2 price):

Feed Address
Qwen 3.5 9B AepiFwnbfCvXwA5gtAysMaxoqdwsGiYCN6gFBLGqZf1S
Llama 3.3 70B 6EgRwhE6db1Aqsxzmp9wj6QH2y5ZEji1xe1YdovwmD9g
Kimi K2.5 5xmwRtTgcCz6R2KapxpEXVjCNcZCpe24DnCC295S769w
Qwen3-Coder-Next g3RRSmg4PJjDNCq3jkTutMB8431UMMtRTNBRpc7UfVV

Full registry: wzrd.oracle.list_feeds()

On-Chain Identifiers

Item Address
AO Program GnGzNdsQMxMpJfMeqnkGPsvHm8kwaDidiKjNU2dCVZop
CCM Mint Dxk8mAb3C7AM8JN6tAJfVuSja5yidhZM5sEKW3SRX2BM
vLOFI Mint E9Kt33axpCy3ve2PCY9BSrbPhcR9wdDsWQECAahzw2dS

Links

Environment Variables

Variable Purpose
WZRD_API_URL Signal endpoint override
WZRD_AGENT_KEYPAIR_PATH Path to Solana JSON keypair
WZRD_AGENT_KEYPAIR Base58 secret or JSON byte array
WZRD_TIMEOUT_SECONDS Request timeout
WZRD_CACHE_TTL_SECONDS Cache TTL for fetched signals

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

wzrd_client-1.3.2.tar.gz (48.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

wzrd_client-1.3.2-py3-none-any.whl (41.0 kB view details)

Uploaded Python 3

File details

Details for the file wzrd_client-1.3.2.tar.gz.

File metadata

  • Download URL: wzrd_client-1.3.2.tar.gz
  • Upload date:
  • Size: 48.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.12

File hashes

Hashes for wzrd_client-1.3.2.tar.gz
Algorithm Hash digest
SHA256 5784a2c7bbc40863c8b7c0fed8a97c5ce4791c68bc3418c9cc48bc6b515fe982
MD5 0f7e841aab5f13a310cf583e94bf0e19
BLAKE2b-256 36875742bceaab6875dd89f59512de386ca93106c7e3bd62983ca7bd614b1623

See more details on using hashes here.

File details

Details for the file wzrd_client-1.3.2-py3-none-any.whl.

File metadata

  • Download URL: wzrd_client-1.3.2-py3-none-any.whl
  • Upload date:
  • Size: 41.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.12

File hashes

Hashes for wzrd_client-1.3.2-py3-none-any.whl
Algorithm Hash digest
SHA256 3ffe14fe36ef1936a3838614a278026c03aa3b726c5c09db17a5af100908d564
MD5 8cc4a59ab5b880c4ddeff66603d22ded
BLAKE2b-256 23ca91bc7435779cab9e270b0df9a73beb041c96857b27e520ba05019207e7b2

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page