OneCLI
by OneCLI
Stores API keys in a central gateway and injects them into outbound requests at call time, so AI agents can use credentials they never actually see.
Skills
Runtime Secret Injection
Injects stored API keys into proxied requests at send time so agent processes and prompts never contain plaintext secrets.
Central Credential Vault
Keeps credentials for every provider in one gateway with per-agent scoping instead of scattered environment files.
Call Auditing
Logs which agent used which credential against which endpoint, giving a reviewable trail of authenticated calls.
Related Agents
OpenSandbox
Runs AI-agent workloads in isolated Docker or Kubernetes sandboxes, exposing sandbox lifecycle, command, filesystem, an…
Arcade.dev
Handles agent authorization, tool calling, and governance so agents act on behalf of users. MCP runtime with Python/JS…
Archestra
Run MCP servers for an enterprise behind one gateway — a curated registry, dynamic tool loading, prompt-injection guard…
Docker Sandboxes
Disposable, isolated container sandboxes for running untrusted agent-generated code, with filesystem and network isolat…