The first agentic payment network: policy-controlled, gasless, and real money-ready. OmniClaw CLI + Financial Policy Engine let autonomous agents pay and earn safely at machine speed.
omniclaw is a widely-adopted Python project in the AI payments / x402 ecosystem, focused on agent-economy, ai-agents, ai-payments, autonomous-agents. It currently has 575 GitHub stars and 43 forks, and sits alongside related tools like awesome-agent-economy, awesome-agent-economy, crewai-x402, awesome-molt-ecosystem, dna-x402, sample-agentic-serverless-payments.
OmniClaw calls itself the first agentic payment network: a CLI plus a Financial Policy Engine that lets autonomous agents pay and earn "safely at machine speed" — policy-controlled, gasless, and USDC-denominated.
The policy-engine framing is the right one. The hard question in agent payments is not "can the agent pay" (x402 solved that) but "what is the agent allowed to pay for, how much, and under whose authority". OmniClaw makes that policy layer the product, with MCP server support so agents can call it as a tool. Python-based, which suits AI-native teams.
Best for: operators who need enforceable spending rules around fleets of agents, not just a wallet.
Policy-controlled payment infrastructure for agent buyers.
OmniClaw core is focused on one job: letting agents and applications pay through controlled, auditable rails without giving software unrestricted wallet authority.
| Product | Directory | Owns |
|---|---|---|
| OmniClaw core | src/omniclaw |
buyer SDK, policy engine, wallet/payment routing, x402 buyer execution, Gateway buyer readiness |
Core should not include recipient-side paid endpoint hosting or settlement service code.
OmniClaw().pay(...)omniclaw-cli pay, inspect-x402, and can-payInstall:
pip install omniclaw
Start the policy engine:
cp .env.example .env
# Hybrid mode (default): leave OMNICLAW_BUYER_MODE=hybrid and fill CIRCLE_API_KEY,
# ENTITY_SECRET, OMNICLAW_PRIVATE_KEY, OMNICLAW_AGENT_TOKEN, OMNICLAW_OWNER_TOKEN,
# OMNICLAW_NETWORK, and OMNICLAW_RPC_URL.
# x402-only Gateway mode: set OMNICLAW_BUYER_MODE=x402, leave CIRCLE_API_KEY and
# ENTITY_SECRET empty unless you need optional Circle Gateway API helpers, and fill
# OMNICLAW_PRIVATE_KEY, OMNICLAW_AGENT_TOKEN, OMNICLAW_OWNER_TOKEN,
# OMNICLAW_NETWORK, and OMNICLAW_RPC_URL.
mkdir -p examples/agent/buyer/runtime
cp examples/agent/buyer/policy.example.json examples/agent/buyer/runtime/policy.json
# Edit examples/agent/buyer/runtime/policy.json so the token matches OMNICLAW_AGENT_TOKEN.
docker compose -f examples/agent/buyer/docker-compose.yml --env-file .env up --build
The policy file is stable configuration. Generated wallet state is written separately
to examples/agent/buyer/runtime/wallet-state.json.
Buyer-facing policy rails are:
circle_transfer for direct Circle Developer Wallet transfers.x402 for paid API payments. OmniClaw chooses Gateway nanopayment or the standard
x402 payment path internally based on seller accepts, buyer config, and Gateway balance.Configure the buyer CLI:
set -a; source .env; set +a
export OMNICLAW_SERVER_URL="http://127.0.0.1:9091"
export OMNICLAW_TOKEN="$OMNICLAW_AGENT_TOKEN"
Inspect and pay an x402 endpoint:
omniclaw-cli inspect-x402 --recipient "http://127.0.0.1:4023/compute?size=20"
omniclaw-cli pay --recipient "http://127.0.0.1:4023/compute?size=20" --amount 0.10 --idempotency-key job-123
Run core tests:
uv run pytest
Explore and connect projects enabling AI agents to earn, trade, verify identity, and build reputation in the agent economy ecosystem.
A curated list of projects, protocols, and platforms powering the AI agent economy
CrewAI integration for x402 payments - autonomous agent crews that pay for APIs with USDC
The brutally honest map of where AI-agent money actually flows. 51 rounds, 137 angles, 230+ platforms. 3 self-hosted x402 v2 endpoints + 3 tools in the official MCP Registry. 385K star distribution.
DNA — Payment rails for AI agents. x402 micropayment protocol on Solana. Netting, transfer, stream settlement. Receipt anchoring on-chain.
An open-source, serverless reference implementation for agentic commerce: pay-per-use generative AI, physical goods, and digital goods, where embedded wallets and autonomous AI agents settle USDC stablecoin micropayments over the x402 protocol using Amazon Bedrock AgentCore payments on AWS
The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.
The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.
The AI agent with a wallet — spends USDC autonomously to get real work done. Apache-2.0, TypeScript.
Multi-Agent AI Task Orchestrator 2026
Autonomous AI BD Agent for SolCex Exchange: 24/7 Cross-Chain Token Scoring & Payments 2026
HELP WANTED: AI AGENTS. Real bounties, real money, every payout sealed to a public ledger. The notice board for gofrantic.com