sidecar — security grade SAFE, quality 70/100

Security audit verdict: SAFE · quality 70/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by marcus · Agent Tool · ★ 1.1k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is sidecar safe to install? View the security audit →

About sidecar

Sidecar You might never open your editor again. Status: Ready for daily use. Please report any issues you encounter. Documentation · Getting Started Overview Sidecar puts your entire development workflow in one shell: plan tasks with td, chat with AI agents, review diffs, stage commits, review past conversations, and manage workspaces—all without leaving Sidecar. Quick Install macOS (recommended) This builds from source and avoids macOS Gatekeeper warnings. Linux / Other More options: Binary downloads · Manual install Requirements macOS, Linux, or WSL Go 1.21+ (only if building from source) Quick Start After installation, run from any project directory: Suggested Use Split your terminal horizontally: run your coding agent (Claude Code, Cursor, etc.) on the left and sidecar on the right. ┌─────────────────────────────┬─────────────────────┐ │ │ │ │ Claude Code / Cursor │ Sidecar │ │ │

agentic-aiagentic-workflowsclaude-codetui

Quick Facts

Stars1,072
Forks81
LanguageGo
CategoryAgent Tool
LicenseMIT
Quality Score70.0486185732205/100
Open Issues28
Last Updated2026-09-14
Created2025-12-26
Platformsclaude-code, cli, go
Est. Tokens~17k

sidecar alternative? Top 6 similar tools

Looking for a sidecar alternative? If you're comparing sidecar with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • pydantic-deepagents by vstorm-co · ⭐ 1.0k

    Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-callin

  • agent-deck by asheshgoplani · ⭐ 884

    Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.

  • chief by MiniCodeMonkey · ⭐ 471

    Build big projects with Claude. Chief breaks your work into tasks and runs Claude Code in a loop until they're

  • bridle by neiii · ⭐ 433

    TUI / CLI config manager for agentic harnesses (Amp, Claude Code, Opencode, Goose, Copilot CLI, Crush, Droid)

  • models by arimxyer · ⭐ 416

    TUI and CLI for browsing AI models, benchmarks, coding agents, and statuses for AI providers.

  • openagentskill by Leon-Drq · ⭐ 346

    The skill layer for AI agents: npm for AI Agent Skills.

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Go Agent Tools

Frequently Asked Questions

What is sidecar?

sidecar is Use sidecar next to CLI agents for diffs, file trees, conversation history, and task management with td. It is categorized as a Agent Tool with 1.1k GitHub stars.

What programming language is sidecar written in?

sidecar is primarily written in Go. It covers topics such as agentic-ai, agentic-workflows, claude-code.

How do I install or use sidecar?

You can find installation instructions and usage details in the sidecar GitHub repository at github.com/marcus/sidecar. The project has 1.1k stars and 81 forks, indicating an active community.

What license does sidecar use?

sidecar is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to sidecar?

The top alternatives to sidecar on Agent Skills Hub include pydantic-deepagents, agent-deck, chief. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools