Reading
An intelligent agent orchestration tool written in Go, which implements automated workflow management for task planning, execution, verification, and submission through the Plan-Do-Check-Act cycle.
Section 01
An intelligent agent orchestration tool written in Go, which implements automated workflow management for task planning, execution, verification, and submission through the Plan-Do-Check-Act cycle.
Section 02
With the rapid development of AI coding assistants and autonomous agents, how to effectively manage and orchestrate the workflows of these agents has become a new technical challenge. Existing solutions often have the following problems: messy working directories, difficulty in tracking task status, unpredictable agent execution results, and lack of standardized verification and submission processes.
Development teams need a tool that ensures transparent, reliable, and recoverable agent work—not only to manage agent execution but also to ensure that every change is properly isolated, verified, and recorded.
Section 03
Norma is an autonomous agent workflow orchestrator developed by the NormaHQ team and written in Go. It bridges the gap between high-level task management and low-level code execution through a strict Plan → Do → Check → Act (PDCA) cycle.
Norma's design philosophy emphasizes transparency and reliability: every agent operation is recorded, every change is isolated in a Git worktree, and the entire runtime state is directly persisted to the task backlog. This design makes agent workflows auditable, recoverable, and collaborative.
Section 04
Norma's core is the classic PDCA quality management cycle, applied to the workflow orchestration of AI agents:
Section 05
Refine high-level goals into specific work plans and acceptance criteria. Norma analyzes the task description, generates a structured execution plan, and clarifies the expected output of each step.
Section 06
Agents execute the plan in an isolated workspace. Norma creates an independent Git worktree for each task to ensure that agent modifications do not pollute the main working directory.
Section 07
Evaluate the content of the workspace against the acceptance criteria and generate a PASS/FAIL verdict. This step ensures that only changes that meet quality standards can proceed to the next stage.
Section 08
If the check passes, Norma automatically merges and commits the changes to the main branch using the Conventional Commits specification; if it fails, the cycle continues or preparation for re-planning is made.
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.
Folkering OS is the world's first AI-native bare-metal operating system, entirely written in Rust no_std without relying on Linux, POSIX, or libc. It can generate commands from scratch, compile them into WASM, and run them in 10 seconds, achieving true self-evolution.
This project explores how to use Large Language Models (LLMs) to detect logical vulnerabilities in Ethereum smart contracts, especially business logic flaws that are difficult for traditional static analysis tools to capture, such as economic manipulation and execution order errors.
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.