by kekzl · Agent Tool · ★ 124
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
git clone https://github.com/kekzl/imp.git && cd impTaken 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 | 124 |
| Forks | 5 |
| Language | C++ |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 63/100 |
| Last Updated | 2026-10-30 |
| Created | 2026-02-23 |
| Platforms | docker |
| Est. Tokens | ~20k |
From-scratch CUDA inference engine for the NVIDIA RTX 5090 (sm120a). The best single-GPU backend for agentic AI — tool calling, long-context loops, reasoning and concurrent sub-agents, on top of the fastest single-user inference on the 5090: faster decode than llama.cpp (+37–72% dense GGUF), at-or-ahead of vLLM on NVFP4, and the only engine running native NVFP4 on consumer Blackwell.
These tools work well together with imp for enhanced workflows:
Looking for a imp alternative? If you're comparing imp 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.
An offline coding agent for local models. One command sets up the best model your GPU can run, and on 24 GB+ R
An environment where open models work as agents: a first-level harness with routing, skills, memory and sandbo
🐋 Run 284B DeepSeek-V4-Flash (<59GiB RAM, 44.4 tok/s pp, 9.1-14.7 tok/s) & 30B MoEs (25-111 tok/s) on a pure
Self-hosted LLM gateway. One Go binary turns your Macs and Linux boxes into a private inference cluster — mult
The fastest inference engine for Qwen3.8-27B on the NVIDIA RTX 5090: up to 500 tokens/s for one agent and up t
Frontier-class open models on a free Kaggle TPU v5e-8: GLM-5.3-Flash 320B MoE (~64 tok/s, our own JAX engine)
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: