Developer creates standalone SearXNG CLI+MCP for open-source coding agents
A developer built a standalone SearXNG CLI and MCP tool that enables open coding agents (like OpenCode, pi coding agent) to perform agentic web search without relying on proprietary APIs or running SearXNG as a standalone Python service. The tool is portable and harness-independent, addressing a key limitation in open-source coding agents.
Entities
Related
Agent Harness Engineering shared on Hacker News
A post titled 'Agent Harness Engineering' was shared on Hacker News on July 12, 2026, linking to addyosmani.com. The post discusses engineering aspects of agent harnesses, but no further details are provided in the excerpt.
Collection of 48 working AI agent examples in Python and TypeScript
A curated repository of 48 functional AI agent implementations covering common patterns like research, code review, SQL, data analysis, and web scraping. Each example is designed to be cloned and run immediately, solving the problem of broken or incomplete agent tutorials for developers building AI systems.
Developer shares an agent in 100 lines of Lisp
A developer posted a minimal agent implementation in 100 lines of Lisp on Hacker News, sparking discussion about lightweight agent design. The post received 82 points on July 7, 2026, highlighting community interest in compact, interpretable agent code.
Enola: engineering intelligence layer for AI coding agents
Enola is an open-source engineering intelligence layer that helps AI coding agents understand existing codebases. It answers questions about change impact, dependency reachability, safe module deletion, refactoring priorities, and architecture drift. The tool uses LLMs to analyze code context and provide insights that reduce mistakes from both humans and AI agents.
WebSwarm: a progressive recursive multi-agent system for deep-and-wide web search
WebSwarm is a new multi-agent web search system that addresses the limitations of single ReAct-style agents in handling deep and wide search tasks. It uses progressive recursive collaboration among agents to improve depth, coverage, and evidence-grounded expansion. The system is described in a paper posted on arXiv on July 9, 2026.