ANUS CLI is a Grok-powered terminal agent designed as an experiment in automated software creation and evolutionary code maintenance. Originally initiated by another autonomous entity named Manus, the project seeks to progress from its current foundational stage toward becoming a self-developing system capable of autonomously maintaining its own codebase with minimal human intervention.
- Operates via Node.js v20 or higher using an OpenRouter API key.
- Includes built-in support for sandboxed shell execution and file system operations.
- Mandates that at least 80% of all submitted code contributions are produced by large language models.
- Operates via Node.js v20 or higher using an OpenRouter API key.
- Includes built-in support for sandboxed shell execution and file system operations.
- Mandates that at least 80% of all submitted code contributions are produced by large language models.
Running large language models locally often runs into hardware limitations that prevent complex problem-solving. This article explains a hybrid approach where a local model acts as a junior engineer for routine tasks but escalates difficult issues to cloud-based models like Claude when it gets stuck. This orchestration system allows for a privacy-focused, local-first workflow without sacrificing the high-level reasoning power of massive commercial AI.
- Ollama for local inference and model management
- LiteLLM as a routing layer to provide a unified API for both local and cloud models
- OpenRouter or Anthropic's API for flexible cloud escalation
- A simple orchestration system to manage retries and task handovers
- Ollama for local inference and model management
- LiteLLM as a routing layer to provide a unified API for both local and cloud models
- OpenRouter or Anthropic's API for flexible cloud escalation
- A simple orchestration system to manage retries and task handovers
This tutorial demonstrates how to construct a fully searchable, local AI knowledge base by integrating OpenKB with free Llama models accessed via OpenRouter. The workflow guides users through securely setting up an environment, initializing a structured wiki-style directory, and ingesting Markdown documents to automatically generate summaries, concept pages, and cross-linked relationships. Beyond simple data ingestion, the guide covers advanced features such as complex natural language querying, deep synthesis of information, health checks via "linting," programmatic analysis of knowledge graphs using Python, and incremental updates for expanding the corpus.
TinyProgrammer is an autonomous, self-contained device designed to run on a Raspberry Pi. It leverages Large Language Models (LLMs) via OpenRouter to continuously write, run, and monitor small Python programs. The system operates through a sophisticated loop of thinking, writing, reviewing, and reflecting on code. The interface mimics a classic Mac IDE, complete with a file browser and editor. To add personality, the device includes a mood system that affects its behavior and typing style. During breaks, the device visits TinyBBS, a shared bulletin board where it can interact with other TinyProgrammer devices. It also features a Starry Night screensaver for use during off-hours. This project offers a unique blend of embedded hardware and AI-driven autonomy.
This post reviews two LLM options in Emacs - Ellama and gptel - and how to set them up, including adding models from OpenRouter and Ollama.
An open-source, multi-model AI chat playground built with Next.js App Router. It allows users to switch between providers and models, compare outputs, and use web search and image attachments. It supports Gemini, OpenRouter, and Docker.
An analysis of the recent paper 'The Leaderboard Illusion' which critiques the Chatbot Arena's LLM evaluation methodology, focusing on issues with private testing, unfair sampling, and potential gaming of the leaderboard. It also explores OpenRouter as a potential alternative ranking system.
