feed · watching · stats · help with your tokens
AI & LLMAgents & MCPSelf-hostedNetworkingSecurityDevOps & cloudData & databasesWebMobileTerminalDeveloper toolsLearningMusic & mediaHome & IoT
PythonTypeScriptJavaScriptGoRustCC++JavaC#SwiftKotlinPHPRubyShellHTMLZig
KKKKhazix/agent-autoloop · 28h
Agent Autoloop lets a command-line agent pick up work in the background and follow it through, asking for a decision only when something is uncertain.
It addresses command-line agents that only work while someone watches the terminal, so the job stops once the window is closed or the person walks away. A kernel of about 1650 lines of code with zero runtime dependencies coordinates the work.
GitHub · New on GitHub · 1,955 stars
claude-mem preserves context across coding-agent sessions by capturing tool usage and generating semantic summaries.
It stops an agent from forgetting a project between sessions by capturing tool observations, summarizing them and recalling them later. It runs as a local worker service with a web viewer and search endpoints, managed by Bun.
An agent skill that generates architecture diagrams with official logos from a one-sentence description of a tech stack.
It solves the problem of manually creating technical architecture diagrams by allowing developers to describe their stack in a sentence and automatically generating a visual diagram with official logos for documentation or sharing. It operates as an agent skill for Claude Code, Codex, and Cursor, fetching official logos from sources like svgl and devicon to render self-contained HTML, PNG, or React components.
GitHub · New on GitHub · 1,694 stars
That is everything from the last 30 days.