WikiSkill (arXiv:2608.27454) for Hermes Agent — self-evolving agent skills via a persistent knowledge wiki. Faithful Algorithm 1 implementation with real agent runs, isolated skill gating, and a documented live run log.
Agent Skill evaluation harness for paired variants, trace artifacts, and runner adapters
The open-source company brain. Run your entire company with AI agents, skills, and a self-improving context.
A symbiotic AI agent that remembers everything, challenges you, and extends your cognition.
A kit for building with AI agents and also the engineering patterns around it.
Multi-Agent Harness for Production AI
Research and scraping agent skeleton: tool loop, loadable skills, fallback chains. No data included, configured via .env.
Complete AI Agent System for OpenClaw — memory, self-healing, self-improvement, voice, automation
Opinionated AI coding agent and dev environment automation for macOS
Single source of truth for AI coding agent configuration — skills, commands and rules shared across OpenCode and Pi.
The theory of LLM wikis, running as one. A framework for agent-operated knowledge: typed, linked, review-gated markdown your agents execute.
DeepBot is a system-level AI assistant built for both personal productivity and enterprise workflows — one-click setup, seamless experience, and native Feishu integration.
Agentic personal OS to automate high-leverage workflows with Codex, Claude Code, Pi, OpenClaw and other coding agents/ runtime platforms.
Multi-agent harness that runs Claude Code and Codex together as one system
Create production-ready skills and agents for OpenClaw. 4-level memory, auto-improvement, 22 battle-tested pitfalls.
A human-governed AI coding workflow that distills ephemeral session context into persistent project memory—making work traceable, reviewable, and resumable.
Durable single-Agent Harness for TypeScript: recoverable Threads, context continuity, explicit side effects, and a native TUI.
A lightweight agent harness you bolt onto your app so an LLM can operate it — safely, and cheaply.
Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.
Run a task with AI as a flow of steps you keep, reuse, and refine, not a one-off chat.
Agentic coding framework powered by AGENTS.md: systematic, test-first workflows with quality gates for Cursor, Codex, Gemini CLI, and AI coding agents.
AI agents now operate with authority. Authority without discipline is how complex systems fail. Nuclear’s control loop, ported to AI-assisted software engineering.
Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-first methods, powered by TypeScript and Bun.
A structured 3-agent AI dev team — Architect, Builder, Reviewer. Built from production use. Token-optimized. Works with Claude Code, VS Code, Cursor, and any AI that supports context files.