NanoClaw, a new open-source agent platform, aims to address the security concerns surrounding platforms like OpenClaw by utilizing containers and a smaller codebase. The project, started by Gavriel Cohen with the help of Anthropic's Claude Code, focuses on isolation and auditability, allowing agents to operate within a contained environment with limited access to system data.
AI agents are increasingly deployed to execute important tasks. While rising accuracy scores on standard benchmarks suggest rapid progress, many agents still continue to fail in practice. This discrepancy highlights a fundamental limitation of current evaluations: compressing agent behavior into a single success metric obscures critical operational flaws. Notably, it ignores whether agents behave consistently across runs, withstand perturbations, fail predictably, or have bounded error severity.
Key contributions:
> 1. A formal taxonomy and metric suite: We translate qualitative safety-critical principles into computable metrics, enabling evaluation of agent reliability independently of task success.
>2. A comprehensive reliability profile of modern agents: A detailed mapping of where state-of-the-art agentic models succeed and fail, isolating consistency and predictability as the dimensions requiring immediate research focus.
Key contributions:
> 1. A formal taxonomy and metric suite: We translate qualitative safety-critical principles into computable metrics, enabling evaluation of agent reliability independently of task success.
>2. A comprehensive reliability profile of modern agents: A detailed mapping of where state-of-the-art agentic models succeed and fail, isolating consistency and predictability as the dimensions requiring immediate research focus.
ClawWork is an AI coworker framework that transforms AI assistants into agents capable of completing real-world professional tasks and earning income. It features a live economic benchmark, multi-model competition, and rigorous LLM evaluation. The project provides tools for standalone simulation and integration with openclaw/nanobot.
MimiClaw is an AI agent that runs on a $5 ESP32 board and delivers an OpenClaw-like experience, putting a private assistant in your pocket. It operates as a bare-metal AI agent, storing data in text files and interacting with the real world through GPIO pins.
AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries
A review of Google's Auto Browse agent, testing its ability to perform various online tasks, from playing web games to managing playlists and scanning emails. The agent shows promise but requires significant supervision and struggles with certain tasks, particularly those involving prolonged monitoring or complex interfaces.
Create executable demo documents that show and prove an agent's work. Showboat helps agents build markdown documents that mix commentary, executable code blocks, and captured output. These documents serve as both readable documentation and reproducible proof of work. A verifier can re-execute all code blocks and confirm the outputs still match.
This guide documents the setup of OpenClaw on a Raspberry Pi 5 w/ 8GB RAM and how to give it access to a TFT display, temperature/pressure sensor, USB camera, and NeoPixels. It uses eSpeak text-to-speech and Whisper Small speech-to-text to enable speech based communication with the bot.
LlamaAgents Builder allows users to build document agents using natural language, generating agent workflows for tasks like classifying financial statements, extracting data from resumes, and creating multi-document summarization pipelines. It offers a balance between low-code ease of use and the flexibility of custom development, generating Workflows that can be deployed on LlamaCloud or self-hosted.
The awesome collection of OpenClaw Skills. Formerly known as Moltbot, originally Clawdbot.
