Reading
This article introduces the ClawDeFi Agent Skill open-source project, a modular DeFi skill set designed specifically for OpenClaw-compatible agents. It covers full-stack DeFi functions such as wallet management, DEX trading, perpetual contracts, lending, yield aggregation, options, and prediction markets, along with security strategies and pre-signature simulation mechanisms.
Section 01
This article introduces the ClawDeFi Agent Skill open-source project, a modular DeFi skill set designed specifically for OpenClaw-compatible agents. It covers full-stack DeFi functions such as wallet management, DEX trading, perpetual contracts, lending, yield aggregation, options, and prediction markets, along with security strategies and pre-signature simulation mechanisms.
Section 02
ClawDeFi Agent Skill is a distributed skill definition project (version 0.1.75) aimed at teaching local agents to interact with the DeFi ecosystem at a professional level. Its core capabilities cover the full life cycle of DeFi investment:
Section 03
The project adopts a highly modular script architecture, with independent adapter implementations for each DeFi category, facilitating on-demand combination and independent maintenance.
Section 04
The DEX module uses 0x Protocol as the main adapter, with 1inch as legacy support. Core scripts include:
This layered design decouples the four stages of quoting, building, simulating, and executing, ensuring both flexibility and that each link can be independently tested and audited.
Section 05
The perpetual contracts module is adapted to the Avantis protocol (Base chain) with the most complete functions, covering the full life cycle of position management:
Opening Position Flow: perps-open-quote.js → perps-open-build.js → perps-open-simulate.js → perps-open-execute.js
Closing Position Flow: perps-close-quote.js → perps-close-build.js → perps-close-simulate.js → perps-close-execute.js
Position Management: perps-modify-position-build/simulate/execute.js (modify position), perps-cancel-order-build/simulate/execute.js (cancel order), perps-risk-orders-build/simulate/execute.js (risk management order)
Query Functions: perps-position-list.js (position list), perps-pending-orders.js (pending orders)
Referral System: perps-referral-info.js, perps-referral-bind-build/simulate/execute.js
Section 06
The lending module is adapted to the Aave V3 protocol, providing standardized deposit, borrow, repay, and withdraw processes:
Section 07
The yield aggregation module is adapted to the Pendle protocol, supporting yield tokenization and fixed yield strategies:
Section 08
The options module is adapted to the Thetanuts protocol, providing structured options strategies:
Keep going with more reads from the same topic.
Splinter is a minimalist, high-performance key-value (KV) and vector storage system enabling zero-latency inter-process communication via shared memory and atomic operations. With only 766 lines of core code, it supports millions of operations per second and 768-dimensional vector storage, offering a new architectural approach for local LLM inference and data-intensive applications.
This article details how to quickly deploy a virtual machine equipped with 4 NVIDIA V100 GPUs on Azure using Terraform to enable local inference of large language models with over 70B parameters. It covers a complete practical guide from infrastructure deployment, Ollama/vLLM dual-engine comparison testing, to cost optimization and actual performance data.
LiteMind is a Python framework that provides developers with a unified API to integrate mainstream LLM providers such as OpenAI, Anthropic, Google Gemini, and Ollama. It supports multimodal input/output, tool calling, RAG enhancement, and agent construction.
OmniRoute is an open-source AI gateway that integrates over 67 large model providers through a single OpenAI-compatible endpoint. It offers intelligent routing, load balancing, automatic degradation, and quota management, helping developers get the most available AI services at the lowest cost.