vibepanel Agent Console

A self-hosted web console for supervising parallel coding-agent sessions across multiple projects.

Stars
★ 29
Last updated
5d ago
License
NOASSERTION
Primary language
Go

At a glance

Works with
Universal · cross-platformCodex · Claude Code
You'll need
tmuxLinux or macOS for the interactive installera web browserShell / CLINetwork accessLocal filesystem
Typical use
A developer running Claude Code, Codex, or other terminal agents in several repositories can see which sessions are active, waiting for input, or exited from one project sidebar.
Main limitation
Current releases use PolyForm Noncommercial 1.0.0 with attribution conditions; internal company use, hosted offerings, and product bundling require a separate commercial license.
Source review
85/100 · Good

What does this agent do, and when should you use it?

vibepanel is a self-hosted web console that organizes terminal-based coding agents into projects and sessions. A dedicated system service and tmux keep terminal processes alive, while the browser handles naming, ordering, status, and interaction, so closing the page or restarting the panel does not terminate active work. Its desktop and phone interfaces combine session monitoring with a file manager, notebook, scratch terminal, token-usage reporting, and machine-load views. The same capabilities are exposed through an authenticated API, while optional Telegram, Feishu, and personal WeChat integrations can relay questions and permission requests to private chats. It ships as a single Go binary, terminates its own TLS, and supports password or passkey access, making it a fit for developers who want persistent agents reachable from multiple devices.

Users register development directories as projects and create sessions from the web interface or with POST /api/sessions; command is an argv array, and omitting it creates a shell. The backend uses a dedicated service and tmux to preserve terminals and agent processes, while the UI reports whether each session is working, waiting, or finished. A side panel manages files and notes, including copy-and-paste transfer of files and images, and the bottom scratch terminal lets users inspect files or run commands without interrupting an agent. An installable hook supports Claude Code, Codex, Kimi Code, zcode, and opencode, detecting actual completion or requests for attention, previewing what it will write, and backing up the target file first. Optional Telegram, Feishu, and WeChat integrations send numbered session prompts to private chats and route replies back; Telegram and Feishu also expose Allow and Deny actions. The product can also publish agent-authored share pages for status screens, phones, laptops, or televisions.

  1. A developer running Claude Code, Codex, or other terminal agents in several repositories can see which sessions are active, waiting for input, or exited from one project sidebar.
  2. A solo developer with a workstation left at home or in the office can use the phone interface to inspect terminals and respond to agent questions while away from the desk.
  3. Someone running long-lived builds, migrations, or coding tasks can rely on tmux and the dedicated terminal service to preserve work across browser closure, panel upgrades, or application-layer crashes.
  4. An engineering team integrating agent sessions into internal automation can create and control them through the Bearer-token API, including POST /api/sessions.
  5. A user who needs a wallboard for session status, token consumption, or project output can publish an agent-authored page and open its share link on a large display.

How do you install or deploy this agent?

The interactive installer is documented for Linux and macOS:

curl -fsSL https://raw.githubusercontent.com/jiangmuran/vibepanel/main/install.sh | sh

For restricted networks, the author-operated GitHub mirror can be used; its first run presents a terminal prompt for a browser-based check:

curl -fsSL https://github.muran.tech/https://raw.githubusercontent.com/jiangmuran/vibepanel/main/install.sh -o vibepanel-install.sh \

|| curl -sSL https://github.muran.tech/https://raw.githubusercontent.com/jiangmuran/vibepanel/main/install.sh

sh vibepanel-install.sh --mirror

Manage the installation with:

vibepanel service status
vibepanel service start
vibepanel service stop
vibepanel service restart
vibepanel service logs
vibepanel service token
vibepanel service upgrade
vibepanel service uninstall

User and system services, unattended installation, CLI creation of the first account, Docker, and source builds are documented as available, but their complete commands are not included in the supplied material.

How do you use this agent?

After starting the service, open the panel in a browser, complete first-account setup, add a project, and create a terminal or agent session under it. Ordinary shell sessions omit command; an agent session supplies its executable as the command argv. For programmatic access, create a token under Settings → API tokens, then run:

TOKEN=…
curl -sX POST https://panel.example.com:18443/api/sessions \
-H "Authorization: Bearer $TOKEN" -H 'Content-Type: application/json' \
-d '{"projectId":"…","title":"billing","command":["claude"]}'

Replace panel.example.com, projectId, and TOKEN with real values. The administrative CLI also exposes serve, project, session, hook, service, account, doctor, and version commands. To handle prompts remotely, configure and explicitly enable Telegram, Feishu, or WeChat in settings; the chat feature makes no external connection until a channel is enabled.

What are this agent's strengths and limitations?

Pros
  • Terminal state is independent of the browser: tmux and the dedicated service preserve active sessions through page closure, panel upgrades, and application-layer restarts.
  • One interface combines multi-project sessions, a mobile terminal, file management, notes, a scratch shell, token accounting, and per-session machine-load visibility.
  • Hooks explicitly support Claude Code, Codex, Kimi Code, zcode, and opencode and distinguish actual process completion from a merely quiet terminal.
  • A Bearer-token API exposes the same operations used by the front end, providing a documented path for automation.
  • The single Go binary handles TLS, passwords, and passkeys itself, and optional chat integrations remain offline until configured and enabled.
Limitations
  • Current releases use PolyForm Noncommercial 1.0.0 with attribution conditions; internal company use, hosted offerings, and product bundling require a separate commercial license.
  • Persistent session operation relies on tmux, creating a deployment dependency for environments standardized on another terminal multiplexer.
  • The interactive installer is only documented for Linux and macOS; the supplied material provides no evidence of a native Windows installation path.
  • Enabling remote chat necessarily sends relevant data through Telegram, Feishu, or WeChat infrastructure, subject to the boundary disclosed during setup.
  • The author describes the project as early, so adopters should expect its capabilities and operational behavior to continue evolving.

How does this agent compare with similar options?

Key facts side by side with the most closely related agents.

Agent Source review Stars Updated Language Full support on
vibepanel Agent Console This agent 85 · Good ★ 29 5d ago Go Codex · Claude Code
Happier 82 · Good ★ 1.7k today TypeScript Codex · Claude Code
Agent Session Manager Desktop 67 · Some gaps ★ 18 1d ago Go Codex · Claude Code
Collie 84 · Good ★ 1.1k today TypeScript

How does FollowAgents rate this agent?

FollowAgents source review · FARS-2.1
Good
85/ 100 5-point scale 4.3 / 5
Trust 25/29
Reliability 11/14
Adaptability 16/18
Convention 15/18
Effectiveness 12/13
Verifiability 6/8
Why each dimension lost points
Trust25 / 29 · 4.3/5

The evidence shows read-only contents permission in CI, public release automation, and SHA-256 verification. Chat channels are off by default; first enablement discloses the data path and waits for consent, unknown users must pair, and remote approvals are bound to the displayed request. Hooks are described as previewing writes and making backups. Deductions apply because the product can launch terminals, modify files, and expose remote access, while one installation path pipes curl into a shell. The supplied material does not fully document storage, encryption, rotation, or log redaction for passwords, tokens, and chat credentials, nor automatic rollback after an upgrade swap. Authorship, repository attribution, and notice requirements are explicit, justifying full source-attribution credit; unverified publisher identity is treated only as unknown.

Reliability11 / 14 · 3.9/5

The README, module file, and workflows consistently describe the Go/Node/tmux requirements, static build, test gates, and release process. Bidirectional API-document checks, real-tmux tests, and numerous focused checks support strong self-consistency. Dependency availability loses a point because operation and installation still depend on specific Go/Node versions, tmux, GitHub downloads, and optional certificate or messaging services. Failure handling includes doctor diagnostics, unknown-environment-variable warnings, checksum refusal, and service-log commands, but the supplied evidence does not show comprehensive user-facing handling for all runtime, network, authentication, and recovery failures.

Adaptability16 / 18 · 4.4/5

The intended audience and scenarios are precise, covering multiple projects and sessions, desktop and mobile use, remote chat, an API, user or system services, Docker, and restricted-network installation. Commands, environment precedence, session addressing, and the required ok before advanced remote typing provide strong trigger precision. Capability boundaries lose a point because this is a network-accessible console capable of arbitrary terminal commands, while the supplied material does not fully define project isolation, filesystem boundaries, API-token scopes, or the multi-user authorization model.

Convention15 / 18 · 4.2/5

The README is well structured and routes readers to installation, feature, and API documentation. It covers interactive and mirror installation, unattended use, Docker, source builds, and lifecycle commands. VIBEPANEL_* validation and bidirectional API/router checks support naming stability. The full license clearly defines commercial restrictions, attribution duties, and the boundary for older MIT releases. Deductions apply because examples are present but no actual FAQ content is supplied; some limitations are disclosed, including the project's early state and browser checks being a local gate, but there is no consolidated comprehensive limitations section; tagged releases are described without a separate changelog; and a maintainer name and contact exist without a maintenance policy, response expectations, succession, or governance information.

Effectiveness12 / 13 · 4.6/5

The product combines persistent tmux sessions, status and ordering, file handling, mobile access, notifications, approvals, and an API into an actionable interface, providing clear marginal value for developers operating agents in parallel. Session states and numbers, Allow/Deny cards, screenshots, and monitoring views are directly usable outputs. Cost-benefit loses a point because deployment and maintenance of tmux, TLS, authentication, and optional messaging integrations add complexity and security burden, while the noncommercial license limits organizational adoption without a separate agreement.

Verifiability6 / 8 · 3.8/5

Important claims are tied to concrete mechanisms or named checks, including the fixed toolchain, SHA256SUMS, CI gates, API/router consistency checks, and a claimed default-offline chat test. LICENSE, go.mod, and both workflows corroborate multiple README statements, earning full cross-source-corroboration credit. Traceability is reduced because the referenced feature, installation, and API documents and the test implementations are not included here, so all security and privacy assertions cannot be followed to source. The README also mixes verifiable statements with subjective claims such as being stable, private, and pleasant without consistently separating fact from inference.

Risks and how to mitigate them
  • This is a low-confidence static assessment; the application, tests, installer, and upgrade flow were not executed.
  • Deployment enables remote control of terminals and files. Independently review authentication, TLS, API-token scopes, session isolation, audit logging, and credential storage before exposing it publicly.
  • Avoid piping the installer into a shell until the revision-pinned install.sh has been reviewed; verify the release tag, SHA256SUMS, and download origin.
  • Enabling Telegram, Feishu, or WeChat creates external data flows. Confirm the exact transmitted content, provider retention, administrator visibility, and revocation process.
  • The PolyForm Noncommercial terms generally restrict internal company business use; obtain an appropriate license and legal review before commercial or enterprise deployment.
Evidence confidence: Low Reviewed Sep 24, 2026 Reviewed revision 1ea6ba5b6314
See the full review method →

FAQ

Is it free for commercial teams?
Current releases use PolyForm Noncommercial 1.0.0. Personal, educational, research, and other noncommercial uses are allowed subject to the stated attribution and notice requirements; use inside a company, as a hosted service, or bundled into a product requires a separate license. Releases through v1.20.1 were published under MIT, and copies already obtained under MIT retain that license.
Will closing the browser or upgrading the panel kill an agent?
No. The terminal service and tmux own the running sessions, and the documentation explicitly says page closure, reloads, panel upgrades, and panel restarts do not terminate them.
Does it require Claude Code?
No. It is designed around terminal agents and explicitly documents hooks for Claude Code, Codex, Kimi Code, zcode, and opencode. The API accepts a command argv, and omitting command starts a regular shell.
Do the chat features contact outside services by default?
No. The chat subsystem is documented as making no external connection until a channel is configured and enabled. On first activation, the panel describes what will pass through which servers and waits for consent.
Can an old chat approval authorize a newer command?
No. Each Allow action is tied to the specific request shown to the user, so an old card cannot approve a new command. An unknown person messaging the bot receives only a pairing code until pairing is completed in the panel.
View on GitHub ↗ Install ↓

Compare agents like this one

The same FARS review applied across the shortlist this agent qualifies for.

Related agents