[NeurIPS 2026] Safety failures in coding agents and frontier LLMs. Reproducible workspaces for studying when AI agents generate unsafe data during task completion.
Repository Index
89,572 visible repositories in the index
313–336 of 714 · Most stars
🤖️ Cross-platform AI language practice app (跨平台AI语言练习应用)
Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory.
Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
- evaluation
- evaluation-framework
- evaluation-metrics
- huggingface
Voice AI SDK is a reusable Android library that gives any app a full voice-driven AI conversation pipeline in minutes. Voice Assistant + Android Voide AI + SDK + MVVM + Kotlin
AingDesk是一款简单好用的AI助手,支持知识库、模型API、分享、联网搜索、智能体,它还在飞快成长中。 AingDesk is a simple and easy-to-use AI assistant that supports knowledge bases, model APIs, sharing, internet search, and intelligent agents. It is still growing rapidly.
OCRFlux is a lightweight yet powerful multimodal toolkit that significantly advances PDF-to-Markdown conversion, excelling in complex layout handling, complicated table parsing and cross-page content merging.
The world's smartest system-wide grammar assistant; a better version of the Apple Intelligence Writing Tools. Works on Windows, Linux, & macOS, with the free Gemini API, local LLMs, & more.
- ai
- artificial-intelligence
- gemini
- grammar-checker
Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.
- deep-learning
- flax
- jax
- language-model
提示词小助手可以一键调用智谱、硅基流动、gemini、本地ollama、百度等大语言模型服务,实现提示词翻译、润色扩写、图片反推。支持提示词预设实现一键插入、历史提示词查找等功能。是一个全能型提示词插件。The Prompt Assistant enables one-click access to LLMs/VLMs for prompt translation, expansion, and image captioning. It also supports one-click preset insertion and historical prompt search.
- comfyui
- expand
- prompt
- tags
Antigravity Manager is a desktop application for managing the Google accounts used by Antigravity clients (including Classic, Antigravity IDE and agy CLI). View model quota in real time, switch client accounts seamlessly, and connect AI coding tools like Claude Code, Codex and OpenCode through a high-performance local API gateway.
- antigravity
- antigravity-ai
- antigravity-ide
- electron
A snappy, keyboard-centric terminal user interface for interacting with large language models. Chat with ChatGPT, Claude, Llama 3, Phi 3, Mistral, Gemma and more.
A fast Rust based tool to serialize text-based files in a repository or directory for LLM consumption
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with chat, music, voice, video generation.
- agent
- anthropic-api
- apple-silicon
- claude-code
An open-source Harness Engineering platform for coding agents—define harnesses as code, run controlled experiments, inspect evidence, and compare outcomes. Turn task evidence into actionable team and organization insights.
- agent-plugin
- claude-code
- codex
- cursor
Native iOS and Android client for Open WebUI, direct OpenAI-compatible, Ollama, and Hermes agents.
- ollama
- openwebui
- selfhosted
- ai-agents
τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
A Tool to Visualize Claude Code's LLM Interactions
the terminal client for LLMs
A unified interface for working with LLMs in Laravel
A curated, battle-tested AI-coding toolkit: Claude Code plugins, subagent orchestration, quality gates, and ready-to-copy prompts, extracted from real production use.
Seamlessly integrate LLMs as Python functions
AssetOpsBench - Industry 4.0: A unified benchmark and framework for building, orchestrating, and evaluating domain-specific AI agents for Industry 4.0 asset operations and maintenance, with 460+ scenarios, 5 specialist agents (IoT, FMSR, TSFM, Work Order,...), and multi-agent orchestration blueprints (MetaAgent, AgentHive) over MCP.
- llm-agents
- model-context-protocol
- time-series-forecasting
- condition-based-maintenance
Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery, updates, rollback, quarantine, and 17-platform distribution.