NanoClaw vs PicoClaw

NanoClaw

Each session runs in an unprivileged Docker container and API keys stay in a credential gateway on the host, so a manipulated agent cannot read them. Inside the container the agent runs with permission prompts off, network egress is open by default, and it can message any chat it is wired to without approval.

PicoClaw

Self-hosted under the MIT licence, with 19 documented chat channels, scheduled and heartbeat tasks, and local file memory. The repository has had no commit since 19 August 2026 and no release since 3 July, and 15 CVEs are listed against it with no advisory or security policy from the project.

NanoClaw

1. Install with git clone and bash nanoclaw.sh. There is no registry package, and setup needs Docker, Node 22 or later and a Claude or Codex credential
2. Set NANOCLAW_EGRESS_LOCKDOWN=true before giving an agent credentials or an audience of strangers. The default leaves egress open
3. Put chats with different audiences in separate agent groups. Every session of a group shares one read-write workspace and memory tree
4. Turn on per-request approval for a secret in the gateway when its use should wait for a person. It is off unless configured
5. On OneCLI installs, move the gateway to 1.42.0 by the upgrade guide before updating to 2026.10.0. The updater stops until that is done

PicoClaw

1. Set allow_from to the owner's user ID on every channel before starting the gateway. An empty list accepts messages from anyone
2. Set tools.exec.allow_remote to false unless chats must run shell commands. The shipped default is true, whatever docs/guides/configuration.md says
3. Set isolation.enabled to true on Linux (needs bwrap) or run in a container. The deny patterns do not inspect child processes
4. Use PICOCLAW_KEY_PASSPHRASE for credential encryption. One docs page names PICOCLAW_CREDENTIAL_PASSPHRASE, which the source does not read
5. Treat the README's ClawdChat line (read a remote skill file and follow it) as untrusted third-party instructions