Nunchuk launches two open-source repositories to allow AI agents to manage Bitcoin wallets within predefined spending limits, while maintaining human control.
Nunchuk has released two open-source repositories designed to redefine the way artificial intelligence agents interact with Bitcoin wallets. The launch, which took place on April 8, 2026, introduces a model that limits AI agent autonomy while preserving human oversight over the most significant spending decisions.
The two published tools are Nunchuk CLI, a command-line interface for Bitcoin wallet management, and a complementary repository called “Agent Skills”, designed to allow AI systems to operate the CLI within the most common workflows. Both tools are distributed under the MIT license and are aimed at developers building automated financial systems on Bitcoin.
The core principle behind the proposal challenges a growing trend in AI wallet design. Rather than granting agents full control over funds with simple security measures, Nunchuk proposes a shared custody model in which agents operate within preset policy limits. Wallets are configured as group wallets with multiple keys: a user key, an agent key, and a policy co-signer work together to authorize transactions. The agent can initiate actions such as wallet creation, participant invitation, and transaction construction, but spending authority remains bound to rules defined at the policy level.
Policies define limits such as daily spending caps, approval requirements, and signing delays. Transactions that fall within the allowed parameters can proceed without human intervention, while more significant or sensitive actions require explicit user approval. Nunchuk thus separates custody from automation: the wallet structure governs ownership and control of funds, while policy layers define what an agent can execute. This distinction ensures that funding a wallet does not grant the agent broader authority than intended.
The CLI supports a range of functions including key generation, wallet creation, transaction flows, and policy configuration. It also allows users to export wallet descriptors and backups in standard formats, supporting portability and recovery outside the Nunchuk ecosystem.
Nunchuk positions this dual-repository approach as a response to two distinct challenges: execution and usability. The CLI acts as an execution layer connected to the Nunchuk API, while the skills layer focuses on how AI systems interact with that infrastructure. Potential use cases include human-agent shared wallets, automated bill payment systems, treasury management tools, and multi-agent coordination. While these applications are still in their early stages, the underlying model provides a framework for controlled experimentation in the field of Bitcoin security and signatures.
