CANBAN // DOCS // AGENTS
24 Built-in Agent CLIs, Herdr PTYs & CLI
Canban runs native coding agent CLIs inside persistent Herdr PTY terminals (herdr-core) rendered with libghostty-vt, preserving every tool's native TUI, MCP servers, skills, permissions, and conversation resume.
Zero-interference native TUI, MCP & skill preservation
Rather than reimplementing provider chat wrappers or injecting fragile Stop hooks, Canban launches your chosen CLI inside a herdr-core (hc) supervised PTY:
- Native TUIs & Controls: Interact directly with the agent's own terminal UI via
libghostty-vt(rendered in native AppKit/CoreText on macOS and GTK4 on Linux, with SGR/pixel mouse reporting, OSC 8 hyperlinks, and 17 dark themes including Monokai). - MCPs, Skills & Permissions Intact: Because the real CLI binary executes in the Card worktree with your home configuration, existing MCP servers, custom skills, sandbox flags, and auth logins work unchanged.
- Restart-Safe PTYs & Exact Resume: Closing Canban, restarting
canband, or live-upgrading the app leaves runningherdr-coresessions alive. Finished sessions can resume exact provider conversation IDs (--resume,--session, or--conversation) when supported. - Global Scheduler Budget: Automatic workflow steps share a configurable concurrency limit (
scheduler.max_agents, default8), while manual shells andscriptsteps run outside the agent budget.

All 24 built-in CLI agents
Canban's catalog (crates/profiles/src/catalog.rs) includes 24 official interactive CLI presets matching Herdr's terminal detector and resume planner, plus custom profiles in config/agents.json and dynamic herdr:<template> profiles:
| ID | Agent | Binary | Exact Resume | Model / Effort Args |
|---|---|---|---|---|
codex | Codex | codex | Yes (resume) | -m, reasoning effort |
claude | Claude Code | claude | Yes (--resume) | --model, --effort |
agy | Antigravity | agy | Yes (--conversation) | --model, --effort |
gemini | Gemini CLI | gemini | Yes (--resume) | -m |
opencode | OpenCode | opencode | Yes (--session) | -m, --variant |
cursor | Cursor Agent | cursor-agent | Yes (--resume) | --model |
pi | Pi | pi | Yes (--session) | --model, --thinking |
omp | Omp | omp | Yes (--resume=) | --model |
copilot | GitHub Copilot | copilot | Yes (--resume=) | --model |
droid | Droid | droid | Yes (--resume) | -m |
amp | Amp | amp | Fresh launch | — |
kimi | Kimi | kimi | Yes (--session) | --model |
kiro | Kiro | kiro-cli | Fresh launch | --model |
qwen | Qwen Code | qwen | Yes (--resume) | -m |
devin | Devin | devin | Yes (--resume) | — |
cline | Cline | cline | Fresh launch | — |
grok | Grok | grok | Yes (--resume) | -m |
hermes | Hermes | hermes | Yes (--resume) | -m |
kilo | Kilo | kilo | Yes (--session) | -m |
qodercli | Qoder | qodercli | Yes (--resume) | --model |
letta | Letta | letta | Yes (--conversation) | -m |
mastracode | Mastra Code | mastracode | Yes (--thread) | --model |
maki | Maki | maki | Fresh launch | — |
muse | Muse | muse | Fresh launch | — |
Interactive takeover with canban card adopt
When you start exploring a Backlog Card in an interactive terminal or @mention session and decide to move ahead with implementation in that same conversation, the agent does not need to lose its context or spawn a duplicate session:
"$CANBAN_CLI" card update --file "$CANBAN_RUN_DIR/card.md"
"$CANBAN_CLI" card adopt --stage developcard adoptautomatically passes inheritedHC_TERMINAL_IDandHC_SESSIONcontext toAppServer.AppSerververifies the Core, machine, live PTY, Profile, and Card workspace, transitions the Card todevelop(reason: "agent_adopted_stage") without launching a second Agent, and binds the existing live PTY directly to theWorkflowRunstep.- When the agent later runs
canban report --state completed, the workflow proceeds seamlessly toReviewandQueue Merge.
Injected canban CLI reference
Canban injects CANBAN_CLI, CANBAN_ENDPOINT, CANBAN_HOME, CANBAN_CARD, CARD_ID, CANBAN_PROJECT, CANBAN_PROFILE_ID, and CANBAN_RUN_DIR into every launched session:
# Inspect or update the current Card
"$CANBAN_CLI" card show --fields number,title,body,stage,revision
"$CANBAN_CLI" card update [--title 'Updated title'] --file "$CANBAN_RUN_DIR/card.md"
# Report execution outcome (completed | backlog | blocked | failed | working)
"$CANBAN_CLI" report --state completed --message 'Summary' --file "$CANBAN_RUN_DIR/report.md"
# Reply to a follow-up question without ending the active task
"$CANBAN_CLI" reply --to <QUESTION_ID> --file "$CANBAN_RUN_DIR/reply.md"
# Stage local diff review comments without publishing directly to GitHub
"$CANBAN_CLI" review draft --file "$CANBAN_RUN_DIR/review_draft.json"
# Call any AppServer JSON-RPC method
"$CANBAN_CLI" call card.list '{"project_id":"<PROJECT_ID>","stage":"develop","limit":50}'For the full command matrix, Agent-first --fields / request_key contract, and --human examples, see Canban CLI, Agent Optimization & --human.