llm-apex-agents — security grade SAFE, quality 69/100

Security audit verdict: SAFE · quality 69/100

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 callawaycloud · Agent Tool · ★ 54

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

🔒 Is llm-apex-agents safe to install? View the security audit →

About llm-apex-agents

llm-apex-agents Run Large Language Model (GPT) agents in Salesforce apex. Watch Full Demo Here :shipit: What is an Agent? An “Agent” is a technique for instilling the ability for an LLM to “Reason” and take “Action”. This approach is introduced by the ReAct Paper (Reason → Act) and used in popular libraries like langchain and auto-gpt. Library Terminology : LLM/GTP model. Currently only OpenAI GPT Completion & Chat models are supported. : The communication "protocol" between the model & system. Currently only ReAct style prompts are supported. : A instance formed to solve a given objective. : The commands at the agents disposal : The act of invoking a tool Getting Started install in a scratch org () or to a developer edition () Warning Scratch & developer orgs have a limit of 5 chained queueable jobs, which will limit how much work the agent can do. Assign yourself to the permission set. Open Setup - Named Credential - External Credential - O

apexchatgptgpt-4llmopenaisalesforce

Quick Facts

Stars54
Forks26
LanguageApex
CategoryAgent Tool
LicenseMIT
Quality Score68.6808914517635/100
Open Issues7
Last Updated2023-04-26
Created2023-04-07
Est. Tokens~18k

Compatible Skills

These tools work well together with llm-apex-agents for enhanced workflows:

  • aiAgentStudio — semantic(0.31)+complementary+rare_topics+same_lang+similar_pop (60%)
  • MCP-Salesforce — semantic(0.48)+complementary+rare_topics+similar_pop (51%)
  • mcp-server-salesforce — semantic(0.46)+complementary+rare_topics+similar_pop (51%)

llm-apex-agents alternative? Top 6 similar tools

Looking for a llm-apex-agents alternative? If you're comparing llm-apex-agents 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.

  • ruby-nano-bots by icebaker · ⭐ 126

    Ruby Implementation of Nano Bots: small, AI-powered bots that can be easily shared as a single file, designed

  • aiAgentStudio by iamsonal · ⭐ 76

    Open-source framework for building AI agents in Salesforce, with built-in memory, tools, and security

  • unsaged by jorge-menjivar · ⭐ 253

    Open source chat kit engineered for seamless interaction with AI models.

  • openai-toolbox by cwandev · ⭐ 203

    📦️ A repository of OpenAI tools and resources to help developers more easily use OpenAI technologies and ser

  • c4-genai-suite by codecentric · ⭐ 173

    c4 GenAI Suite

  • the-great-gpt-firewall by samber · ⭐ 100

    🤖 A curated list of websites that restrict access to AI Agents, AI crawlers and GPTs

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Apex Agent Tools

Frequently Asked Questions

What is llm-apex-agents?

llm-apex-agents is Run Large Language Model "Agents" in Salesforce apex. It is categorized as a Agent Tool with 54 GitHub stars.

What programming language is llm-apex-agents written in?

llm-apex-agents is primarily written in Apex. It covers topics such as apex, chatgpt, gpt-4.

How do I install or use llm-apex-agents?

You can find installation instructions and usage details in the llm-apex-agents GitHub repository at github.com/callawaycloud/llm-apex-agents. The project has 54 stars and 26 forks, indicating an active community.

What license does llm-apex-agents use?

llm-apex-agents is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to llm-apex-agents?

The top alternatives to llm-apex-agents on Agent Skills Hub include ruby-nano-bots, aiAgentStudio, unsaged. 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