Awesome AI AgentsAI Developer Toolkit

omnuron/omniclaw

⭐ 577 Python repository created 2026-02-23

OmniClaw is infrastructure that lets autonomous agents and applications spend money without being handed unrestricted control of a wallet. Its centre is a financial policy engine that evaluates every payment request against configured budgets, approval requirements, trust checks and execution controls before anything is signed, backed by a ledger, idempotency keys, simulation mode and payment-intent records so spending can be audited and replayed safely. Agents reach it either through a Python buyer SDK, where a call such as pay on an OmniClaw object issues a payment, or through a command line client offering pay, inspect-x402 and can-pay subcommands, the last of which answers whether a proposed spend would pass policy without executing it. Two payment rails are supported. The circle_transfer rail performs direct transfers from Circle Developer Wallets, and the x402 rail pays HTTP endpoints that advertise the x402 paid-request scheme, with the engine choosing internally between a Circle Gateway nanopayment and the standard x402 flow based on what the seller accepts, the buyer configuration and the available Gateway balance. Helper code covers Gateway funding and readiness checks. Configuration is split so that stable policy lives in a JSON file while generated wallet state is written separately, and the reference deployment runs the engine in Docker with agent and owner tokens separating the party that requests a payment from the party that authorises the rules. The repository deliberately scopes itself to the buyer side and excludes seller-side paid endpoint hosting and settlement services. It is aimed at developers wiring agents into machine-to-machine commerce who need spending limits, human approval gates and an audit trail between the agent and the funds. Payments settle in USDC on supported networks.

https://github.com/omnuron/omniclaw

ai-agentsai-paymentsautonomous-agentsagent-economyx402payment-policyusdcmcp-serverspython

Also in AI Developer Toolkit

Leonxlnx/taste-skill

Taste Skill provides portable AI Agent Skills designed to enhance the quality of AI-generated frontends and image-based design references, aiming to eliminate generic UI outputs.

unslothai/unsloth

Unsloth is a toolkit for fine-tuning and reinforcement learning of large language models, enabling faster training with significantly reduced VRAM usage across various advanced models and tasks.

reworkd/AgentGPT

AgentGPT is an open-source platform that allows users to assemble, configure, and deploy autonomous AI agents in a web browser to pursue custom goals by generating and executing tasks independently.

Gitlawb/openclaude

OpenClaude is an open-source command-line interface (CLI) coding-agent that supports various cloud and local model providers for unified AI-driven development workflows.

virgiliojr94/book-to-skill

A command-line tool that converts technical books, document folders or globs into structured agent skills in the open SKILL.md format, so coding agents load only the chapter relevant to a question.

google/adk-python

An open-source Python toolkit by Google for building, evaluating, and deploying sophisticated AI agents with flexibility, modularity, and integration within the Google ecosystem.

can1357/oh-my-pi

Oh My Pi is an AI coding agent for the terminal featuring hash-anchored edits, an optimized tool harness, LSP integration, and support for Python, browsers, and subagents.

millionco/react-doctor

React Doctor is an intelligent agent designed to diagnose and fix issues within React codebases, leveraging AI to improve code quality and developer efficiency.