Excalibur adds cost controls to an open-source coding agent
Excalibur is an open-source tool that lets product engineers hand coding tasks to an and manage the whole flow from planning to review. The Core version is released under the and can be installed with npm, then run inside a user’s own . Before writing code, it checks scope, evidence, and risk so the work can be built, validated first, or dropped.
Users can choose how much control to give it, from answering questions and suggesting small patches to building a change in a separate branch or running a more automatic workflow. Larger jobs can be split across several AI agents, with each part worked on separately and checked by tests and review before merging. For cost control, Excalibur keeps a full run history, lets users restart from an earlier step, and aims to reuse unchanged earlier work from cache instead of running everything again.
It supports services, Anthropic, Ollama, and other providers, and can use stronger models for hard parts while using cheaper models for lighter text work. A local dashboard shows tasks, live progress, cost information, and run history, while writes, commands, and pushes require approval; it also includes sandboxing, secret blocking, and local audit logs.
Key points
- Core is Apache-2.0 and after npm installation.
- The tool tries to avoid waste by checking whether a task is worth building before code is written.
- Run history and cache reuse are meant to avoid paying again for unchanged earlier steps.
- Large tasks can be divided among several AI agents and checked with tests before merging.
- Multiple s are supported, so expensive models can be saved for harder work.