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 The-Pocket · Agent Tool · ★ 11.1k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is PocketFlow safe to install? View the security audit →
English 한국어 <a href="https://discor
| Stars | 11,093 |
| Forks | 1,209 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 54.9570329645942/100 |
| Open Issues | 72 |
| Last Updated | 2026-07-26 |
| Created | 2024-12-24 |
| Platforms | python |
| Est. Tokens | ~18k |
These tools work well together with PocketFlow for enhanced workflows:
Looking for a PocketFlow alternative? If you're comparing PocketFlow 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.
Multi-agent systems, memory, planning, reasoning loops
Comprehensive resources on Generative AI, including a detailed roadmap, projects, use cases, interview prepara
Sim is the collaborative workspace to build, deploy, and monitor AI agents and workflows. Used by 100,000+ bui
An event-driven framework designed to build and orchestrate multi-agent AI systems. It enables seamless integr
The Ruby-native AI framework. Chats, agents, tools, images, audio, and video through one consistent API, in pl
Harness LLMs with Multi-Agent Programming
Explore other popular agent tool tools:
PocketFlow is Pocket Flow: 100-line LLM framework. Let Agents build Agents!. It is categorized as a Agent Tool with 11.1k GitHub stars.
PocketFlow is primarily written in Python. It covers topics such as agentic-ai, agentic-framework, agentic-workflow.
You can find installation instructions and usage details in the PocketFlow GitHub repository at github.com/The-Pocket/PocketFlow. The project has 11.1k stars and 1209 forks, indicating an active community.
PocketFlow is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to PocketFlow on Agent Skills Hub include AI-Agents-Projects-Tutorials, generative-ai, sim. 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: