opik-openclaw plugs into OpenClaw to export detailed AI agent traces and usage data to Opik’s LLM observability platform, enabling deep insights into LLM calls and costs.
PycoClaw ports OpenClaw AI agents to MicroPython, enabling full conversational agents on $5 ESP32 chips with 8MB+ flash and 4MB+ PSRAM. It supports hybrid memory, subagents, cron, and multi-LLM compatibility.
SmallClaw is a TypeScript AI agent framework that uses a single LLM call for chat and tool invocation, designed for local models with a clean web UI and structured tools.
Snyk Agent Scan is a Python CLI tool detecting 15+ security risks in AI agent MCP servers and skills, using an interactive consent model for safe scanning.
sre-agent is a Python AI tool that automates incident diagnosis by analyzing AWS CloudWatch logs, inspecting GitHub code, and reporting to Slack. It includes a unique evaluation suite for diagnosis quality.
WriteHERE uses recursive task decomposition to dynamically break down and execute long-form AI writing tasks, with real-time visualization of the agent’s thought process. Supports GPT and Claude.
AGNT is a JavaScript-based local-first AI agent OS featuring a unique SkillForge system that evolves agent instructions from execution traces, supporting multi-agent workflows and plugin extensibility.
Explore how a hybrid pipeline using YOLOv8 layout detection, OCR, and LLMs automates messy bank statement PDFs for personal finance analysis with RAG and AI agents.
claude-memory-compiler automates capturing and compiling Claude Code conversations into a knowledge base, improving AI agent memory management with minimal setup.
OpenClaw Medical Skills offers 869 modular AI agent skills to transform Claude agents into specialized medical research assistants. Explore its architecture, strengths, and installation.
learn-harness-engineering offers a practical 5-subsystem harness framework to improve AI coding agent reliability, backed by industry research and starter templates for Claude Code and Codex.
memU Bot replaces flat memory with a semantic memory layer, cutting token use by 90%. It supports Telegram, Discord, Slack, and Feishu with quick setup and MCP integration.
oh-my-kiro enhances AI coding agents with 3-layer deterministic enforcement and a crash-recovering outer loop, improving reliability and reducing hallucinations.
Open Ralph Wiggum runs AI coding agents in an autonomous loop, using git history and file changes as implicit feedback to guide iterations until completion promises are detected.
OpenClaude is a TypeScript CLI coding agent that routes tasks across different LLMs by type, optimizing cost and performance with multi-provider support and a unified terminal interface.
RsClaw is a Rust-based AI agent engine featuring persistent three-layer memory across sessions, multi-agent delegation, and low resource usage in a single 15MB binary.
OpenClaw runs natively on Android via Termux using a Node.js patch that fixes Bionic libc issues, cutting boot time to ~2s and slashing RAM overhead. Here’s how it works.
Scarf is a Swift native macOS and iOS app that provides a GUI for the Hermes AI agent, featuring SSH connectivity, efficient image encoding, SQLite state sync, and real-time dashboards.
hermes-hudui provides a TypeScript-based web UI to interact with the Hermes AI agent, offering real-time data visualization and control. Setup requires Python 3.11+, Node.js 18+, and a running Hermes agent.
AIHawk offers an open-source AI agent that automates job applications. Its architecture balances open AI automation with the legal realities of third-party integrations.
