#887 · Primary category： AI Agents & Automation
AgentHandover
What if OpenClaw, Claude Code, Codex etc. knew how to do your work without you saying it? AgentHandover observes you, learns and teaches your agents with self-improving skills.
Project last updated：06/08/26
GitHub Stars
698
Forks
56
Contributors
1
License
Apache-2.0
Why we included this project
AgentHandover is a local-first macOS app that records how you work and turns those routines into reusable Skills for AI agents. You do a task once while the app watches, and it captures not just the steps but the reasoning behind them, including your strategy, selection criteria, guardrails, and writing voice. Those Skills connect to agents like Claude Code, Codex, or OpenClaw with a single command, and because agents report back after every run, the Skills keep improving on their own. A local knowledge base with vector search lets agents find the right workflow by meaning rather than by title. It's a good fit for anyone on a Mac who runs repetitive research, support triage, community engagement, or ops checklists and wants their agents to inherit the judgment behind the routine, not just the sequence.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
hermes-agent
The agent that grows with you
n8n
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
deepseek-harness
DeepSeek Harness: Everything is a Plugin.
AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.