by synchopate · Agent Tool · ★ 72
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
git clone https://github.com/synchopate/llama-modchip.gitTaken 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 | 72 |
| Forks | 11 |
| Language | Python |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 60/100 |
| Open Issues | 2 |
| Last Updated | 2026-11-04 |
| Created | 2026-10-29 |
| Platforms | claude-code, python |
| Est. Tokens | ~18k |
♟️ llama-modchip Run 30B Sparse MoE LLMs on a pure CPU at 20–80 tok/s with a 256K context window in 14.35 GiB. Zero GPUs required. -d29922?style=flat-square) ⚡ Quickstart · 📊 Benchmarks · 🧠 How It Works · 🏆 CPU Leaderboard · 📄 Technical Paper · ❓ FAQ ⚡ Quickstart Clone the repository and run .
Looking for a llama-modchip alternative? If you're comparing llama-modchip 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.
LLM server for NVIDIA Blackwell only (GeForce RTX 50, RTX PRO). On one RTX 5090, Qwen3.8-27B one user: 96.3 to
Frontier-class open models on a free Kaggle TPU v5e-8: GLM-5.3-Flash 320B MoE (~64 tok/s, our own JAX engine)
Community registry of LLM serving-path traps that produce confidently wrong measurements: templates, tool pars
An offline coding agent for local models. One command sets up the best model your GPU can run, and on 24 GB+ R
🦀 Decoder-only LLM built from scratch in pure Rust using Candle — no Python, no PyTorch. Gated DeltaNet + spa
Local decision model with calibrated probabilities: send a state and yes/no, choice or score questions, get a
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: