by sheet0 · Agent Tool · ★ 229
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
pip install npiaiTaken from the project's README on GitHub.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 229 |
| Forks | 11 |
| Language | Python |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 65/100 |
| Open Issues | 6 |
| Last Updated | 2025-03-31 |
| Created | 2024-04-01 |
| Platforms | browser, python |
| Est. Tokens | ~290k |
NPI [!WARNING] NPi is currently under active development and the APIs are subject to change in the future release. It is recommended to use the command line tool to try it out. NPi is an open-source platform providing Tool-use APIs to empower AI agents with the ability to take action in virtual world! 🛠️Try NPi Online: Try NPi on online Playground (🚧Under Construction).
Looking for a npi alternative? If you're comparing npi 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.
This is the repository for the Tool Learning survey.
The Open Assistant API is a ready-to-use, open-source, self-hosted agent/gpts orchestration creation framework
Flock is a workflow-based low-code platform for rapidly building chatbots, RAG, and coordinating multi-agent t
Command-line interface for ChatGPT, Claude and Bard
Shell and coding agent on mcp clients
Semantic layer on top of a graph database to provide an LLM with a set of robust tools to interact with the da
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: