#327 · Primary category: AI Agents & Automation

kungfu

agent agent-framework agent-memory agent-orchestration

Your agents don’t hand off the work. Kungfu keeps the same Work moving across Codex, Claude, OpenCode, and your own execution surface.

Project last updated:08/29/26

GitHub Stars

4.5K

Forks

1.3K

Contributors

69

License

Apache-2.0

Why we included this project

Switching between AI coding assistants usually means re-explaining decisions and wondering what got lost in the transfer. Kungfu puts the work itself into a persistent layer that tracks the objective, progress, evidence, and next action, so a different agent can continue where the previous one stopped. You can keep using your current assistant and let it drive that work layer, or start a session through Kungfu's own console. The immediate payoff is saving time on handoffs, but the bigger gain shows up over days when failed attempts, context loss, and restarts no longer force you to redo things. Teams mixing Codex, Claude, OpenCode, and custom tooling get a practical way to keep agent-driven work repeatable and auditable.

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