LLM 模型排行

To implement LLM as a services.

Ollama Zig library

LLM-powered code auditor for GitHub repos.

Your AI terminal companion

🚀 Lightweight Python library for building production LLM applications with smart context management and automatic token optimization. Save 10-20% on API costs while fitting RAG docs, chat history, and prompts into your token budget.

Open-source Codex plugin for Sol-governed multi-agent coding, bounded AI code review, model routing, and LLM cost optimization

Methodology + templates for a trustworthy, traceable, self-growing AI data-analyst agent: metrics-first, independent read-only validation, and a self-growing rule library.

Outside-in replication of Anthropic's Mythos Preview / Project Glasswing — open-source agentic vulnerability-discovery scaffold on Claude Opus 4.7. Eight-phase sink-guided pipeline, ~$1/run, OSS self-scan and coordinated disclosure.

A browser game to learn prompt engineering by playing — explore a world and solve challenges by writing prompts. Techniques from OpenAI, Anthropic, Google & xAI, each cited.

DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling

Turn any website into clean, LLM-ready data. Open-source web crawler with stealth mode, distributed crawling, real-time WebSocket progress & Markdown output. Power your AI apps with GcrawlAI.

This repo contains evaluation code for the paper "MileBench: Benchmarking MLLMs in Long Context"

A Go toolkit for building AI agents and applications across multiple providers. Unified LLM client, agent framework with handoffs, tool calling, streaming, structured output, MCP integration, and cost tracking.

Carbon Limiting Auto Tuning for Kubernetes

Eve Agent V2 Unleashed — local-first autonomous AI coding agent powered by Ollama

Self-hosted PCAP analysis platform with LLM-powered incident triage, signature-based threat detection, and AI-generated incident narratives. Features network change monitoring across captures, deep packet inspection via nDPI, and automated Wireshark filter generation. Runs fully offline with local LLMs (Ollama, LM Studio).

A Chat Client for LLMs, written in Compose Multiplatform.

Connect to MCP servers right from your shell. Plugin for simonw/llm.

CareerDesk: Your Personal Career Assistant

Cortex is a fast, private desktop AI assistant for running local Large Language Models with Ollama. Everything stays on your device: no cloud, no external servers, and no third parties.