repository

A repository for a zero-trust execution boundary that sits between AI agents and real system actions. It evaluates policy, approval, scope, freshness, replay, and evidence before allowing operations to proceed.

Relaymux is a tmux-backed harness for running local coding agents, with Telegram as the remote control interface and support for iMessage/SMS in beta.

A GitHub Copilot port of Anthropic’s vulnerability discovery harness, with Copilot skills for threat modeling, scanning, triage, patching, and an autonomous sandboxed pipeline for C/C++ memory-safety bug discovery and remediation.

Drawgent is a coding agent that works on a live Excalidraw canvas, aimed at turning sketches and diagrams into code. The page shows a real project with a README-driven quick start, demo section, setup command, and detailed notes on how the agent interacts with diagrams and code.

A curated GitHub list and benchmark leaderboard for ultra-lightweight, zero-dependency AI engines in C/C++/Rust/Assembly, covering local LLMs, vector search, memory, GEMM, and agent tooling.

A GitHub repository for a custom llama.cpp backend that runs Qwen3-0.6B GGUF models on an Axera AX8850 NPU accelerator, with build/run notes, environment flags, architecture details, and test status.

A lightweight SQLite FTS5 memory layer and MCP server for Google Antigravity agents, with CLI tools for storing, searching, and syncing facts.

A DeepSeek Harness plugin that uses an LLM to verify and rank candidate outputs with select, compare, track, and rollout tools.

Aakit is a developer tool for measuring and tracking assumptions made by coding agents, linking each assumption to supporting code and flagging which ones fail. The repo includes a clear explanation of the idea, prior art, and early experiment results.

An open-source project for running a small LLM and limited agent workflows on ESP32-P4 hardware, with model details, architecture notes, examples, and setup instructions.

A Python tool manager for AI agents that uses an LLM-tools.txt registry to install, pin, describe, and execute tools with one predictable contract.

A skill for coding agents that routes slash commands and trigger phrases to zerostack, a lightweight CLI coding agent for coding, planning, reviewing, and orchestration tasks.

An agent skill and Python builder that turns Markdown note folders from Obsidian or gbrain into an interactive HTML knowledge map with a force graph, growth timeline, filters, and note detail panels. The repo includes a prebuilt demo for quick inspection and supports use in Claude Code, OpenAI Codex, Cursor, and simila

An experimental autonomous bare-metal OS agent that uses an LLM, VirtualBox, and screenshot inspection to iterate on low-level code, boot a VM, and refine behavior from execution results.

A metadata-first trust control plane for authorized security workflows, evidence retention, release trust, and business-flow proof. The repository includes role-based docs, quick-start commands, safety boundaries, and release-trust materials.

A GitHub example that audits LangChain’s RAG quickstart with retrieval-quality metrics, flags off-topic and out-of-distribution queries, and surfaces ranking and calibration issues with charts and results files.

A drop-in CLAUDE.md style section that changes how Claude writes prose. The repo includes a clear install path, the style rules themselves, and notes on when the patch works best or degrades.

Public evaluation code for an Agent Memory Leaderboard, including answer-generation and scoring contracts for comparing LLM agent memory systems.

A repository of Claude Code and Codex skills for evaluating and designing multi-agent systems, centered on an /agent-architect skill for auditing, reviewing, and designing agent setups.

Attestor is a TypeScript control plane for high-risk AI-driven operations. It sits between an AI-generated request and the real system action, applying policy, approval, scope, freshness, replay, and evidence checks before returning admit, narrow, review, or block.

Open-source repo for Muse’s “chief of staff” workflow: it coordinates specialist agents, preserves per-agent memory, and builds a private Office app for tracking projects, team, customers, reports, and notes.

A GitHub repo that teaches users how to write and debug evals through an agent-guided skill called learn-evals. It includes setup steps, exercises, examples, and a path to install the skill in other projects.

A GitHub repo for SHOVE, a turn-based CLI tactics puzzle created by Claude Fable 5 and iterated through six play sessions until it was judged fun. The page includes a brief, writeup, source code, logs, and the main game script.

A prompt-based medieval fantasy text adventure for LLM chats, with character creation, combat, companions, inventory tracking, and a main quest to find four mysterious items.