When you open a file in your project and wonder which script generated it, which AI agent wrote it, or which command produced its contents, you are facing the file lineage problem. File lineage is the practice of tracing a file back to its origin — the exact script, notebook, data source, shell command, or AI agent that created or modified it. Without this trace, teams lose visibility into how their code and data evolved, creating compliance risks, debugging nightmares, and audit failures. Emerging open-source tools like trace-file-lineage, the Agent Trace specification, and academic frameworks like PROV-AGENT now make it possible to answer this question with evidence and honest uncertainty. ...

Ponytail Improved is an AI agent skill that teaches coding agents to think like the laziest senior developer on your team — the one who writes the minimum viable solution, reuses existing code, and delivers faster with fewer bugs. By enforcing a six-rung laziness ladder before any code is written, Ponytail reduces AI-generated code by 54% on average while keeping 100% of safety guards intact, making your agent cheaper, faster, and more reliable. ...

Introduction — The Rise of Kotlin-Specific AI Coding Benchmarks For years, AI coding benchmarks have been dominated by Python and TypeScript. SWE-bench, HumanEval, and MBPP all lean heavily on these languages, leaving Kotlin developers wondering how well AI agents actually handle JVM-based code, Android development, and Kotlin-specific idioms. In July 2026, JetBrains changed that by releasing the official Kotlin Benchmark for AI Coding Agents — a rigorous, open-source evaluation framework built on Multi-SWE-bench infrastructure that measures how well AI coding agents resolve real-world Kotlin software engineering tasks. ...

The open-source AI developer tools ecosystem in 2026 has matured to the point where every proprietary AI service — from GitHub Copilot to Pinecone to ChatGPT — has a viable, production-ready open-source alternative. This directory covers 18+ categories of open-source AI devtools, including coding agents, local inference engines, agent frameworks, vector databases, RAG pipelines, evaluation platforms, and observability tools, with maturity badges and direct comparisons to the closed-source tools they replace. ...

Scientific computing is undergoing a fundamental transformation as agentic AI systems take on increasingly complex roles in research software development. OpenAI’s July 2026 field report on eight agent-assisted scientific computing projects demonstrates that coding agents like Codex and Claude Code can modernize legacy research libraries, automate simulation workflows, and free scientists to focus on verification and discovery rather than implementation. This shift promises to accelerate research across life sciences, materials science, and beyond. ...

Introduction — The $0/Month AI Company Is Real Yes, you can run a full fleet of AI agents on Google’s Gemini 2.5 Flash free tier at absolutely zero monthly cost. A solo developer in Taiwan proved this by building a 4-agent company — CEO, Social Media Manager, Security Monitor, and Advisor — that executes 105 automated tasks every day using only 7% of the free tier’s 1,500 daily request limit. With total infrastructure costs of roughly $5 per month (Vercel Hobby plan and Firebase free tier), this architecture demonstrates that a one-person AI-powered business is not a futuristic fantasy but a practical reality available today. ...

Introduction — Why Source-Backed Research Matters for AI Agents A product deep research agent skill is a reusable capability that equips AI coding agents like Claude Code, Cursor, and Windsurf to autonomously gather, verify, and synthesize information about products, companies, and markets from real sources — producing structured, citation-backed output instead of hallucinated summaries. Without source-backed research, AI agents cannot be trusted for production-grade competitive analysis, due diligence, or market intelligence, because they default to generating plausible-sounding but unverifiable claims. This guide explains how to build such a skill from the ground up. ...

What is Mem-Port and Why Portable Agentic Memory Matters Mem-Port is an open-source MCP (Model Context Protocol) memory server that gives AI coding agents persistent, portable long-term memory using an embedded SurrealDB database. Unlike traditional memory solutions that lock agent context to a single machine or tool, Mem-Port lets you carry your AI agent’s entire memory — facts, episodes, skills, and entity relationships — between machines, copilots, and teams as a single portable JSON bundle. Think of it as a thumb drive for your AI’s brain. ...

What Is an Agent Scanner for GitHub AI Agent Detection? An agent scanner for GitHub AI agent detection is a security tool that scans repositories to identify, inventory, and assess the security posture of autonomous AI agents, their skills, MCP server configurations, and tool permissions. These scanners emerged rapidly in 2026 after the ClawHavoc campaign planted over 1,200 malicious skills into agent marketplaces, and the market has since grown to over 95 open-source tools on GitHub. They serve as the first line of defense for organizations adopting AI agents at scale, enabling teams to detect shadow AI, enforce compliance with regulations like the EU AI Act, and prevent supply-chain attacks on agent ecosystems. ...

BrowserAct is an open-source browser automation platform purpose-built for AI agents, offering anti-detection capabilities, persistent session management, parallel execution, and a SkillHub marketplace with over 100,000 reusable skills. Unlike traditional testing frameworks or data extraction tools, BrowserAct solves the “last mile” problem of AI agents: actually executing actions inside real, protected, and dynamic web interfaces without getting blocked, losing state, or breaking on every page change. What Is BrowserAct? — The Browser Layer for AI Agents BrowserAct positions itself as a new category of infrastructure: the browser layer for AI agents. While most AI agent frameworks focus on reasoning, planning, and tool calling, they consistently fail at the execution layer — actually navigating real websites that employ Cloudflare, reCAPTCHA, Datadome, login walls, and session timeouts. ...