Search

A service dependency injection, configuration and logging library.

AI-Powered Software Development tool — Multi-Methodology, CLI based

AIOS — The AI Operating System. An open-source AI OS built on Android/AOSP with on-device LLM inference (llama.cpp), 44 system tools, policy-controlled AI agents, and a conversational shell launcher.

AI agent powered by MCP, LangGraph, LangChain, RAG, OpenAI, and PostgreSQL

RETECO: A SemEval-2027 Shared Task on Reasoning-Oriented Retrieval

The Circuit Breaker & Safety Firewall for AI Agents. Stop infinite loops, block dangerous tool calls (rm -rf), and prevent API budget burn.

The Eternego codebase

Open protocol and TypeScript SDK for AI agent authority: identity, scoped delegation, enforcement before the action, and signed receipts.

Trust infrastructure for autonomous AI agents: decision assurance, action authorization, runtime controls, and verifiable lifecycle evidence.

Package AI agents into portable .agent files

Best-practice guide for AI agents — drop into any project and enjoy the magic.

Safety-gated multi-agent framework for authorized cyber operations and penetration testing

Agentic platform for physics lecture workflows with backend services and supporting client application.

Runtime defense against temporal backdoors in tool-using agentic LLMs

Framework-neutral gateway for AI Agents to safely call enterprise HTTP APIs with policy, approval, redaction, credential isolation, and audit logs.

The self-improving, self-learning open-source AI agent. Background Computer-Use, A2A Swarm, Vector Memory, Plugin System, Voice, Smart Approvals - 100/100 Score. Windows-native.

Deterministic contract enforcement for agent tool calls: gates the destination, not the tool. No LLM in the decision path.

Knowledge Tier Framework - A four-tier classification system for AI agent knowledge access

Workflow transpilation and execution framework - import LangChain, Airflow, GitHub Actions, Kubernetes, Docker Compose

Private-deploy AI agent platform with hybrid retrieval, code sandbox, and shared skill system. RAG + BM25 parallel search, safe execution, and multi-user workspace.