Agent Manager

Agent Manager is an open-source terminal-based agent harness and session orchestrator developed by Yoan Wai. It is built to run, monitor, and manage the execution of multiple command-line AI coding assistants from a unified control interface, tracking agent lifecycles across terminal panes. In daily use, Agent Manager acts as a supervisor over CLI agents such as Command Code (`cmd`), `pi`, and other terminal assistants. It continuously monitors TUI outputs using configured status rules, inspecting pane elements such as composer prompts, spinners, turn-completion markers, and approval dialogues. This allows the harness to automatically track state transitions across waiting, working, tool approval, and finished states without interfering with the underlying agent. What distinguishes Agent Manager is its resilient terminal state-matching engine and session tracking. Rather than requiring agents to conform to proprietary telemetry APIs, it uses live terminal capture parsers to detect tool approval prompts, error states, and rate limit banners, alongside an integrated SQLite-backed session store that supports reviving and resuming exact conversation threads across agent restarts. Agent Manager is open-source software distributed via GitHub. It is implemented with lightweight local dependencies, including local SQLite storage and clipboard integration, making it straightforward to run in terminal-first developer environments.

Tags: agent harness, cli, coding agent, developer tools, terminal

Visit Agent Manager

Key features

  • Terminal State Detection — Uses configurable status rules to track agent states (working, waiting, finished, error) by inspecting raw TUI pane captures. - Built-in Agent Tool Profiles — Includes built-in support and state rule configurations for CLI tools like Command Code (cmd) and pi. - Session Persistence and Revival — Tracks session IDs in an internal SQLite store to resume and continue conversations automatically. - Interactive Dialog Detection — Identifies tool execution approval prompts, trust dialogues, and navigation menus across agent interfaces. - Error and Limit Handling — Detects runtime errors and insufficient credit/rate-limit banners directly from terminal output buffers. - Multi-Agent Coordination — Provides structured coordination notes and subcommands across active coding agent sessions.

Use cases

Use Case: Supervising Long-Running Coding Agent Tasks A developer runs automated CLI agents like Command Code in the background while Agent Manager continuously observes the session state, identifying when a task finishes or stalls on an approval prompt without manual polling.

Use Case: Resuming Interrupted Terminal Agent Sessions A developer recovers a terminated coding session using Agent Manager's SQLite-backed transcript store, which references the historical session ID and executes the appropriate resume subcommand (e.g., cmd --continue).

Use Case: Coordinating Multiple CLI Agents A team orchestrates distinct terminal agents on different sub-tasks, relying on Agent Manager to normalize status updates and surface interactive approval dialogues from child panes.

Who it is for

Agent Manager is built for developers and automation engineers who actively use terminal-based AI coding agents (such as Command Code or Pi) and need a centralized harness to track execution status, approvals, and sessions. It is less suited for developers seeking all-in-one GUI environments or built-in IDE chat panels.

Install guide

Installation Clone the repository and build from source using Cargo (standard for Rust-based CLI tools with SQLite/clipboard dependencies): bash git clone https://github.com/YoanWai/agent-manager.git cd agent-manager cargo build --release Move the compiled binary to your system PATH: bash sudo cp target/release/agent-manager /usr/local/bin/

First Run Verify the installation and review available agent integrations: bash agent-manager --help Ensure that the supported CLI agents (such as cmd or pi) are installed and configured in your environment PATH.

Example Session Launch a managed agent session using a supported tool runner: bash # Start a managed session with Command Code agent-manager run cmd # Resume a previous conversation session from history agent-manager revive

Part of CLI Coding Agents

Categories: AI Coding Agents, Code Assistants, Developer Tools

Related CLI agents

  • Patapim — Patapim is an agent harness and orchestration environment built to wrap and extend CLI coding agents like Anthropic's Claude Code,…
  • Repomon — Repomon is an open-source developer harness and repository companion tool created by Ali Hamza Azam. Built with a Rust core…
  • Unpeel — Unpeel is a terminal multiplexer and agent orchestration harness designed for managing persistent developer tasks and AI coding agents. It…
  • Even — Even is an agent-native desktop workspace and orchestration environment developed by Todience, Inc. It integrates a native terminal, an embedded…
  • AgentCliMenu — Agent CLI Menu (binary `agent-cli-menu`, alias `acm`) is an open-source session manager and agent harness developed by Roy Padina. Designed…
  • Showagent — Showagent is an open-source terminal user interface (TUI) harness and session manager created by aytzey for developers who run multiple…
  • AI Tools
  • Categories
  • Industries
  • CLI Coding Agents
  • MCP Servers
  • MCP Categories