mgasparin67-cmd/Agent-verification_Assure
Independent assurance plane for AI agents: policy-enforcing gateway, deterministic assertions, model benchmarks. No LLM-as-judge.
Theo dõi tốc độ tăng trưởng và hoạt động, không chỉ tổng số stars.
Independent assurance plane for AI agents: policy-enforcing gateway, deterministic assertions, model benchmarks. No LLM-as-judge.
Curated V100 SXM2 pin maps, two- and four-GPU NVLink connection plans, and connector-only KiCad resources toward an open-source carrier board.
Mission control for AI coding agents — every PR lands on the architecture map, and you talk to your agents on the diagram.
The AI that really does things. Any OS. Any Platform. The lobster way. 🦞
Most AI models won't tell you when they can't know. A dataset of numbers whose primality can't be judged by looking, and a pre-registered test of eight models.
The open-source AI workbench for scientific research
Terminal-first AI coding agent with hosted no-nannying models
Open your Character.AI data export in the browser — read your characters and chats offline. Nothing is uploaded.
A Python library for AI providers.
Browser extension to increase the visibility of AI Generated Content Disclosures in the Steam store.
Durable semantic state inference engine for local, multimodal AI. Keeps intent, authorized work, artifacts and reviews connected in inspectable response frames. Runtime contracts and recorded evidence govern completion, repair and continuation.
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
Let formal specs test AI implementations
Deterministic code dictionary for LLMs and developers: tree-sitter + SQLite, no AI. Cuts Claude Code token use by answering code questions from an index.
Turn Rex into a harness for your coding agent: see what it changed, review it in Neovim, send comments back. Claude Code, Codex, OpenCode, Pi.
Passwordless authentication via DID signatures. No passwords. No sessions. Nothing to breach.
Learn how to design systems built on LLMs. Prep for the system design interview. Includes Anki flashcards.
Official code repo for the O'Reilly Book - "An Illustrated Guide to AI Agents"
Shipvo: build once, publish for people and AI agents. Open-source React Native framework with signed OTA updates, a built-in admin, an agent-usable simulator over MCP, and measured simulator-vs-device parity.
See what's left of your flat-rate AI subscriptions every time you open a terminal. One POSIX sh script for Claude, ChatGPT/Codex, Copilot, Gemini, OpenCode Go and Freebuff.