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 prime-radiant-inc · Agent Tool · ★ 100
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is serf safe to install? View the security audit →
Serf A non-interactive coding agent. Give it a prompt, it does the work. Serf uses the LLM's native tool-calling to read files, write files, run commands, and search code in a loop until the work is complete. It supports OpenAI, Anthropic, and Google models. For how the code is organized — modules, layout, and the build workspace — see docs/architecture.md. Build Build the standalone one-shot client (no agent loop): Build the multi-session web orchestrator: Usage The prompt can be passed as arguments or piped via stdin: llmcall (One-Shot LLM Client) This repo also includes , a minimal CLI wrapper around the unified library for single “throwaway” calls. Properties: Exactly one LLM call (no agent loop). Tool calls are forbidden (). If the model returns tool calls, fails. No system prompt by default. You can optionally provide one, or force-disable with . Build: Examples: bash ./llmcall --provider openai --model gpt-5-mini-2025-08-07 "Write a haiku about build pipelines." JSON mode: parses a
| Stars | 100 |
| Forks | 4 |
| Language | Go |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 68.7604406035938/100 |
| Open Issues | 65 |
| Last Updated | 2026-08-18 |
| Created | 2026-02-10 |
| Platforms | cli, go |
| Est. Tokens | ~18k |
These tools work well together with serf for enhanced workflows:
Looking for a serf alternative? If you're comparing serf 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.
Any Agent × Any Provider × Anywhere. Connect Cursor, Claude Code, OpenCode, or Codex to Slack, Telegram, Disco
Persistent memory for AI coding agents
✋ Interactive CLI tool for selecting and bundling code into a single, LLM-ready output file
Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI
Aser is a lightweight, self-assembling AI Agent frame.
Build big projects with Claude. Chief breaks your work into tasks and runs Claude Code in a loop until they're
Explore other popular agent tool tools:
serf is A non-interactive coding agent: give it a prompt and it reads, writes, runs commands, and searches code in a loop until the work is done, using native tool-calling across OpenAI, Anthropic, and Google. It is categorized as a Agent Tool with 100 GitHub stars.
serf is primarily written in Go. It covers topics such as ai-agent, cli, coding-agent.
You can find installation instructions and usage details in the serf GitHub repository at github.com/prime-radiant-inc/serf. The project has 100 stars and 4 forks, indicating an active community.
serf is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to serf on Agent Skills Hub include golembot, omega-memory, codegrab. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: