Lightweight, cross-platform process sandboxing powered by OpenAI Codex's runtime. Sandbox any command with file, network, and credential controls.
Repository Index
132,241 visible repositories in the index
73–96 of 103 · Most stars
[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization
- efficient-inference
- large-language-models
- llm
- model-compression
[CVPR 2024] MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
- computer-vision
- multimodal-large-language-models
- long-video-understanding
- llama
Evidence-first local memory for AI agents with temporal versions, admission policies, citations, explainable recall, MCP, and audit tooling.
- ai
- llm
- memory
- memory-management
Turn papers, code, and docs into presentation-ready, natively editable PPTX in Codex / Claude Code. Native charts and equations, speaker notes, click-build animations, and an independent critic review before delivery. Comes with a visual-language template library, updated continuously.
Claude Code LSP: enhance your Claude Code experience with non-IDE dependent LSP integration.
An open-source AI Text Detector for identifying AI-generated content in essays, articles, and documents. Supports document-level and sentence-level detection, with Human, AI, and Mixed content classification, explainable results, and multilingual model development.
- ai-text-detector
- ai-content-detection
- agent-tools
- codex-skill
On-device AI for Flutter — Gemma and other LLMs, multimodal, function calling, embeddings, RAG and speech on Android, iOS, Web, macOS, Windows and Linux.
- dart
- edge-ai
- embeddings
- flutter
基于Golang/go-zero的AIoT物联网平台与SaaS开发底座,融合AI智能体、RAG知识库、记忆和工具调用。支持多租户、多应用、项目管理、设备管理、物模型、场景联动、告警、组态及3D数字孪生。提供MQTT/CoAP/HTTP/TCP接入及阿里云、腾讯云、涂鸦云对接,支持MySQL/PostgreSQL。借助Skills/CLI快速开发,适用于智慧能源、楼宇、停车、家居、农业与工业。
- go
- golang
- aiot
- vue3
Official Codebase for "Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights" (ICML 2026 Spotlight)
- ensemble-learning
- large-language-models
- llm
- lora
A minimal, fast, graphical UEFI boot manager written in C. no external dependencies — just a config file :)
- bootloader
- bootmanager
- ricing
- ricing-linux
~97% token reduction for AI coding sessions — zero deps, 38 languages, MCP server
This repository provides programs to build Retrieval Augmented Generation (RAG) code for Generative AI with LlamaIndex, Deep Lake, and Pinecone leveraging the power of OpenAI and Hugging Face models for generation and evaluation.
- chroma
- chromadb
- gpt-4o-mini
- gpt4-omni
Threat modeling for AI coding agents: point Claude Code, Codex or any agent at your repo and get an evidence-traced threat model. 36 architectures, 29 methods, MIT.
Fast, exact inference for StartLux-Decision models on NVIDIA GPUs: the released GGUF files on int8 and 4-bit tensor cores, behind the /v1/systemone API, with up to 5.3× lower latency than vLLM in FP8 and bit-identical answers.
- calibration
- cuda
- cuda-graphs
- decision-making
AI Vim/Neovim code generation plugin (OpenAI, ChatGPT, and more)
AI Agent Identity and Access Management and Inference Firewall
- agent-identity
- ai-audit
- ai-firewall
- ai-gateway
Pure-Rust inference engine for Qwen GGUF models (Qwen3 to Qwen3.8, dense and MoE up to 770B+). CUDA and Vulkan (NVIDIA, AMD), hybrid CPU+GPU experts, MTP speculative decoding, OpenAI and Anthropic compatible server. Up to ~1.7x llama.cpp decode on a 12 GB RTX 3060.
Local-first web & document ingestion engine in Rust — HTTP/browser capture, layout-aware PDF/Office/OCR parsing, persistent sync, verifiable data graphs, and evidence-grounded AI context.
- ai-agents
- browser-automation
- data-extraction
- firecrawl
Self-hosted, multi-tenant agent harness for SRE incident diagnosis — risk-gated tool approvals, durable resumable runs, audit trail, model gateway, MCP tools, and a native desktop chat client. Written in Go.
Calibrated internal-state modulation, readout, and neural observability for local dense language models.
- activation-steering
- affective-computing
- embodied-ai
- gemma
VisSearch-Bench is a benchmark of 204 human-written tasks that test how well multimodal agents find, organize, and use visual evidence across multiple steps of web search.
DecisionPivot: a diagnostic benchmark for decision models in LLM systems. Contrast pairs that differ in one decisive detail, generators with independent solvers, scorer and runners.
- benchmark
- calibration
- decision-making
- evaluation
BLA blinds your agent. LASIK gives it its sight back. Static de-blinding CLI + MCP server that undoes BLA (Blind LLM Agents) hardening so coding agents and REA can read the real code again. Never executes the target.
- ai-agents
- anti-bla
- bla
- claude-code