Show HN: Plasma Wiki – a CLI for maintaining agent-edited Markdown wikis
Plasma Wiki is a CLI tool for maintaining agent-edited Markdown wikis. It allows users to manage wiki content through a command-line interface, enabling automated editing and organization of markdown files.
Background
- **Plasma Wiki** is an open-source command-line tool (CLI) that lets AI agents (like large language models) create, read, and update Markdown wikis directly from the terminal. It is designed for developers who want AI assistants to autonomously maintain project documentation or knowledge bases.
- In the current AI ecosystem, most "agent" tools are chat interfaces; Plasma Wiki instead gives an agent a persistent, structured file system of notes, treating the wiki as a database the agent can modify over time.
- It is built by **Plasma AI** (a startup) and hosted on GitHub. The project targets the growing trend of "AI agents" — programs that act on behalf of users, not just answer questions.
- Key relevance: As AI agents become more capable, tools like this address the problem of **agent memory and persistence** — without them, an agent starts fresh each time and cannot accumulate shared knowledge.
Max Weinbach says he had early access to OpenAI's new model GPT-5.6 Sol, calling it his favorite model by far. He highlights that it never gives up and will keep reasoning until it's done. OpenAI announced that GPT-5.6 Sol, along with Terra and Luna, will launch publicly on Thursday, with preview access expanding globally now.
The US government ordered Anthropic to suspend access to its Fable 5 and Mythos 5 models for all customers, citing a potential jailbreak technique that involved asking the model to review a codebase for vulnerabilities—a capability Anthropic says is available in other public models. Access was abruptly cut off on June 12.
Andrej Karpathy announces the release of Claude Fable 5, the same underlying model as Mythos but with added safeguards. He calls it a major step forward, particularly for long problem-solving sessions on difficult tasks, and describes it as state-of-the-art on nearly all benchmarks with exceptional performance in software engineering, research, and vision.
Roman Storm warns that the legal theory in his case could set a precedent making open-source developers liable for how others use their code, potentially criminalizing the mere publication of privacy, messaging, or crypto tools. He notes that developer Michael Lewellen cannot publish lawful code due to prosecution fears, and argues this chilling effect extends beyond any single case.
Meta's engineering culture is deteriorating under Mark Zuckerberg and Scale AI CEO Alexandr Wang, who have introduced keyboard tracking, reassignments to data labeling, and AI-centric performance metrics. Critics argue this incentivizes performative AI use, drives away experienced engineers, and contributed to a major Instagram hijacking incident caused by AI-written and AI-reviewed code.