Repository History
58 repositories tagged with AI Agents
HarnessRouter: Unified Interface for AI Agent Harnesses
HarnessRouter Community Edition provides a self-hosted, Apache-2.0 licensed unified interface for various AI agent harnesses like Codex, Claude Code, and Hermes. It allows users to run multiple agents through a single API, offering features such as sessions, streaming, file handling, and cancellation. The project implements the open-standard Unified Harness Protocol (UHP), ensuring users maintain control over their keys and infrastructure.
AREX-Skill: A Skill Library for Automated Machine Learning and Auto-Research
AREX-Skill is a powerful skill library designed to advance automated machine learning and auto-research. It distills over 5,000 executable skills from more than 1,000 popular GitHub repositories, making complex ML knowledge directly usable by coding agents. This project significantly enhances agent performance in various research tasks by providing structured, validated operating knowledge.
Agentic Engineering: Documentation-First Development for AI Coding Agents
Agentic Engineering introduces a documentation-first development framework designed for AI coding agents. It effectively addresses the core challenges of agent statelessness and context collapse by providing a structured chain of documentation and verification skills. This suite serves as a robust harness layer, enabling long-running, loop-driven AI development workflows with persistent memory and clear contracts.
Coven: Local-First Runtime for AI Coding Agent Sessions
Coven is a powerful local-first runtime designed for managing project-scoped AI coding agent sessions. It provides durable state, robust authority boundaries, and seamless interoperability with multiple coding harnesses like Codex, Claude Code, and GitHub Copilot CLI. This tool enables developers to safely launch, observe, and coordinate AI agent work directly within their local project environments.
Open Index: A Deterministic Memory Layer for Your AI Agents
Open Index is a powerful tool for building domain-specific, accurate, and structured data that AI agents can effectively operate on. It enables the creation of a "brain," a searchable and continuously improving context graph tailored to any domain. This system ensures agents have access to reliable, up-to-date information, enhancing their capabilities and decision-making processes.
AgentShield: Python Firewall for AI Agent Spend Control
AgentShield is a pure Python library designed to prevent runaway AI agents from exceeding budget limits. It offers 10 composable spend rules, evaluated in under 1ms, providing robust cost control. Although its core development has transitioned to sipi.bot, the AgentShield Python package remains available for existing users and its test fixtures are open-source.
session-to-skill: Automate AI Agent Skill Creation from OpenCode Sessions
session-to-skill is a powerful tool designed to transform OpenCode shared sessions into fully validated, reusable, and publishable AI agent skills. It automates the process of extracting patterns, applying TRACE validation and security checks, and packaging the skill into a ZIP file, streamlining development for platforms like SkillHub.
SandBase Harness: Local-First AI Agent Runtime with Sandboxed Sessions
SandBase Harness is a local-first, self-hosted runtime for AI agents, offering sandboxed sessions, memory, and credentials. This TypeScript-based project provides a robust infrastructure for managing and observing AI agents, ensuring auditability and secure execution on your own machine or infrastructure.
DA-Forge: Streamlining Declarative Agent Creation for Copilot Notebooks
DA-Forge is a Python-based tool by Microsoft designed to automate the creation and deployment of Declarative Agents for Copilot Notebooks. It significantly reduces the manual effort and time required to set up AI assistants with specific grounding references, transforming an 85-minute process into just a few minutes. This tool is essential for developers and researchers working with Copilot Notebooks and Declarative Agents.
DeclarAgent: Declarative Runbook Executor for Safe AI Agent Workflows
DeclarAgent is an innovative declarative runbook executor specifically designed for AI agents. It enables agents to validate, dry-run, and safely execute multi-step YAML workflows. This tool provides a structured, auditable, and secure way for LLM agents to interact with real CLI workflows, enhancing their operational safety and reliability.
Curie: Automated and Rigorous Scientific Experimentation with AI Agents
Curie is an innovative AI-agent framework designed for automating rigorous scientific experimentation. It streamlines the entire research lifecycle, from hypothesis formulation to result interpretation, ensuring precision, reliability, and reproducibility. This empowers scientists to accelerate their research processes significantly.
Skill Recorder: Turn Screen Recordings into AI Agent Skills
Skill Recorder is a desktop application that captures your on-screen work sessions, including clicks and app switches. It leverages the GitHub Copilot CLI to analyze these recordings, reconstructing them into an intent and ordered steps. This process allows users to generate reusable AI agent skills or automations for platforms like Microsoft Scout, Copilot Cowork, or Copilot Studio.