Search

Autonomous DFIR agent: point it at disk images, memory dumps or log exports and get back an investigation that shows its work. Volatility 3, Plaso, YARA and any OpenAI-compatible LLM. Source-available, free for personal use and for evaluation of up to 31 days.

A short introduction to attention in deep neural networks is provided. The important components of the classical transformer architecture are discussed. Following this, a vision transformer (ViT) is implemented and briefly tested.

One agent skill, and the CLI behind it, for getting FSA training done: programmes, teaching material and assessments. Installs into Claude Code and Codex.

大模型调度、本地工具计算的心电图智能体：所有数值都能追溯到一次工具调用 | ECG Agent — an LLM agent for ECG interpretation where every number is traced to a tool call

Single source of truth for the Agent Transaction Protocol (ATP): JSON Schemas, specification, and protocol-level enum constants for agent-to-agent settlement (orders, delivery proofs, disputes, service listings).

Universal AI agent chatbot widget with expand/shrink modes and Shadow DOM isolation

Javascript library to display flowise chatbot on your website

Local-first code intelligence for AI agents (MCP). Self-contained — bundles its own runtime.

A docked multi-agent terminal deck for DeepSeek Harness

OrionBot CLI - High-performance agentic coding assistant with TypeScript React Ink UI and Rust core

BpCode — full-screen terminal AI coding agent.

Headless browser SDK for Supportwave chat agents: bring your own UI.

Extensible Terminal Multi-Agent Framework for Cloud Operations & DevOps Coding

Inspectable intent, affect, repair, uncertainty, and factored-action control for LLM responses

Generate adversarial test inputs with a coding agent; your pytest assertions judge them

Exploration-based, CLI-first automated bug reproduction with LLMs

Core Mvge agent loop, invocation types, state management, and spell execution

Standalone and remote terminal coding agent

Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 512K-token context window with up...

Durable, idempotent steps for LLM agents: retried or resumed runs never repeat side effects.