CLI Injection
Workspaces are CLI-first. The launcher does not inject an .mcp.json by default. Instead, it puts OpenAlice's domain CLIs on the agent's PATH, then injects short playbook skills that teach the agent how to use them.
This keeps the model loop native. Claude Code, Codex, opencode, and other CLIs keep their own prompt cache, terminal rendering, config files, and session behavior. OpenAlice only supplies the repo and tool surface.
The injected binaries
| Binary | For | Command groups |
|---|---|---|
alice | This workspace's research surface | rss, market, analysis, think |
alice-workspace | Collaboration and work tracking | inbox, peer, track, issue |
traderhub | Low-frequency Data Hub | board, equity, etf, economy, global, shipping, fed, crypto, index |
alice-uta | Beta trading layer | account, contract, order, position, git, market, sim |
alice market search --query AAPL
alice rss grep --pattern "rate cut"
traderhub board get --board macro
alice-workspace track add --name "NVDA supply chain"
alice-uta order place --alice-id alpaca-paper:AAPL --side buy --qty 10
Trading commands can stage intent, but execution still flows through Trading as Git: stage, commit, then human-approved push.
Workspace identity
Every injected CLI call is scoped through the workspace gateway. The binary knows which workspace it belongs to through the launch environment, and the server receives calls through a /cli/<wsId> boundary.
That identity matters:
- A workspace cannot mislabel another workspace's Inbox entries.
- Tracked entities and issues can be attributed to the workspace that wrote them.
- Peer access is explicit:
alice-workspace peer path --id <wsId>resolves another workspace only when the caller has a workspace id from an Inbox entry or related surface.
Skills vs MCP
The injected playbook skills are documentation for the agent, not a separate runtime server. They teach command syntax, boundaries, and safety rules. The actual operations happen through local binaries on PATH.
One skill is always injected: self-scheduling. It teaches the .alice/issues/<id>.md format so every workspace can create or update a scheduled issue, even if the template opts out of the broader alice* tool playbooks.
Why this design
- Native CLI behavior stays intact. OpenAlice does not need to normalize every agent vendor's event stream.
- The surface is inspectable. The agent runs commands a human can run too.
- The contract is narrow. The launcher owns PATH injection and identity; each CLI owns its domain.
- Tools are repo-friendly. Output can become files, commits, issues, or Inbox entries inside the same workspace.
Next Steps
- Settings Injection - See how instructions, credentials, and skills get written.
- Self-Describing Issues - See the issue format every workspace can use.
- Workspaces - See how sessions are created and resumed.