by ise-uiuc · Agent Tool · ★ 167
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
KNighter: Transforming Static Analysis with LLM-Synthesized Checkers Table of Contents About Getting Started Docker Setup (Recommended) Manual Environment Setup (Alternative) Running KNighter Architecture Documentation About KNighter is an innovative checker synthesis tool that leverages Large Language Models (LLMs) to automatically generate static analysis checkers from historical patch commits. Key Features 🤖 LLM-Powered Generation: Automatically synthesizes static analysis checkers using state-of-the-art language models 📊 Multi-step Pipeline: Employs a sophisticated generation → refinement → triage workflow for high-quality results 🔍 Historical Learning: Learns from real-world patch commits to understand common bug patterns ⚡ LLVM Integration: Built on top of LLVM for robust static analysis capabilities 🐧 Linux Kernel Focus: Specialized for finding bugs in large-scale C/C++ codebases like the Linux kernel The detected bugs 🐛 can be found [here](https://docs.google.com/spreadsheets/d/1WzUhbUK0JE9QahywsfEB
| Stars | 167 |
| Forks | 19 |
| Language | C++ |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 71.791175196575/100 |
| Open Issues | 5 |
| Last Updated | 2025-10-26 |
| Created | 2025-03-07 |
| Est. Tokens | ~1815k |
Looking for a KNighter alternative? If you're comparing KNighter 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.
EVA is an AI-assisted penetration testing agent that enhances offensive security workflows by providing struct
Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools,
🔔 Cross-platform smart notifications plugin for Claude Code. 6 types. Click-to-focus. 1 line installation. In
Open-source earning-focused swarm intelligence engine. Self-governing AI collectives (queen, workers, quorum v
Shell and coding agent on mcp clients
Structured deep research skill for Claude Code/Open Code/Codex with human-in-the-loop control
Explore other popular agent tool tools:
KNighter is [SOSP'25] Automatic checker synthesis for system-level static analysis. It is categorized as a Agent Tool with 167 GitHub stars.
KNighter is primarily written in C++. It covers topics such as linux, llm-agent, static-analysis.
You can find installation instructions and usage details in the KNighter GitHub repository at github.com/ise-uiuc/KNighter. The project has 167 stars and 19 forks, indicating an active community.
KNighter is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to KNighter on Agent Skills Hub include EVA, mcp-client-for-ollama, claude-notifications-go. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.