Your AI team's command centre.
conduct-cli connects your terminal to the Conduct platform — run agents, manage projects, enforce AI usage policies with ConductGuard, and switch workspaces in one command.
pip install conduct-cliPython 3.10+ · MIT licensed · v0.4.67
One CLI: run agents, enforce Guard policies, and switch workspaces — your rules travel with you.
What's included
One package. Three capabilities.
conduct-cli ships the platform CLI, the ConductGuard MCP server, and atomic workspace switching — everything your team needs to run agents safely from the terminal.
conductConduct CLI
Run agents, manage projects, switch workspaces, show runs. The daily driver for every developer on the Conduct platform.
conductguard-mcpConductGuard MCP
MCP server that enforces AI usage policies set by your team lead. Every tool call Claude makes passes through Guard first.
conduct switch <workspace>Guard Policy Sync
Switch workspace and instantly re-sync Guard policies. No manual reconfiguration across multiple config files.
Example use cases
See the difference on real tasks.
These are actual patterns from everyday development workflows — not synthetic demos.
Running an agent from the terminal
You want to run the “github-pr-review” agent on a new PR without opening the browser.
2 min → 8 sec
time saved
Without CLI
- ✕Open browser and navigate to Conduct
- ✕Find the agent, fill in params, click Run
- ✕Wait for the browser to show output
2 minutes of context-switching
With conduct-cli
- ✓conduct run github-pr-review --pr 142
- ✓Agent fires immediately from the terminal
- ✓Live output streams to your terminal, done
8 seconds from idea to result
Claude Code Plugin
Install as a Claude Code Plugin.
conduct-cli is available as an official Claude Code plugin. One slash command installs the CLI, wires the ConductGuard MCP server, and you're live.
Install via Claude Code
/plugin marketplace add sseshachala/conductai
conduct CLI
Wires the conduct binary so you can run agents, switch workspaces, and check run history directly from Claude Code.
ConductGuard MCP
Registers conductguard-mcp as an MCP server — policy enforcement fires on every tool call Claude makes.
Policy sync
Guard policies sync automatically when you switch workspaces. No manual config edits required.
Then verify the install
conduct whoami
Shows your active workspace, Guard status, and Booster status in one command.
Plugin is pending review at the Anthropic plugin directory. Until then, install directly from GitHub.
conduct sessions
Your entire AI fleet in one command.
Stop flying blind across terminal windows. conduct sessions shows every active Claude Code and Codex session — context usage, tokens, Guard status, agent runs, and team activity — all in one place.
conduct sessions
Instant snapshot of every active Claude Code and Codex session — project, model, context window usage, tokens, turn count, and Guard status. No API key needed, reads local session files.
CLI Reference
Every command, and when to use it.
Most of the time you only need three: conduct run, conduct switch, and conduct whoami.
conduct run <agent>Daily
Run a named agent. Streams output to terminal.
conduct list agentsExploring
List all agents available in the active workspace.
conduct list runsDebugging
Show recent runs with status and duration.
conduct switchContext switch
List workspaces (current marked with *).
conduct switch <name>Context switch
Switch workspace + re-sync Guard policies atomically.
conduct whoamiBefore any run
Show workspace, server, Guard status, Booster status.
conduct guard statusDebugging
Show Guard hook wiring, policy count, last sync time.
conductguard-mcpAuto
MCP server started by Claude Code. Enforces policies on every tool call.
conduct-mcpAuto
Conduct platform MCP server — exposes run/list/status as MCP tools.
Guard Insights
See what every developer's AI is doing.
Every blocked tool call logged with who, what, and when
Coverage table: which developers have Guard wired
Events feed: real-time stream of policy enforcement
Also by Conduct
More free tools for AI coding
Agent Booster
60–90% token savings on AI coding
AST-level symbol routing, semantic vector search, and MCP integration. Routes only the relevant symbols and functions to the model instead of full files.
pip install agent-boosterSecurity Loop
Automated AI security scanning for every push
CLI emitter → Guard → API → Security dashboard → draft agents → Slack. Continuous policy enforcement wired into your CI loop.
All tools are free, MIT licensed, and live on GitHub. See the full list at /tools.
Your terminal. Your team's rules. One CLI.
Run agents, enforce policies, switch workspaces, and know exactly what context your terminal is operating in — all from a single command.
pip install conduct-cliPython 3.10+ · MIT licensed