Open-source failure intelligence platform for LLM & agent systems. Adds failure memory, pre-flight warnings, pattern detection, and system health scoring.
A minimal kernel for agentic systems. Runtime-first architecture for programmatic tool execution. Inspired by Anthropic's Code Execution with MCP.
Lightweight Agent Framework for building AI apps with any LLM
📈 Experiment with LLM-assisted equity trading flows in a modular sandbox using MCP servers, trader agents, and a simple SQLite database for accounts.
Equity-Traders is an AI-powered trading assistant built using MCP servers and the OpenAI SDK. It simulates intelligent equity trading workflows, enabling market analysis, trade execution logic, and decision-making support for financial strategies.
End-to-end voice AI system demonstrating ASR, LLM-based planning, vector memory, and voice responses via Telegram.
A controlled, auditable implementation of agent memory that separates ephemeral state from persisted memory and exposes how policies govern state across runs.
Project for "Agent Systems and Applications" course of a University course.
Failure-first analysis of retrieval-augmented and agentic systems, focused on isolating and attributing failures across retrieval, planning, execution, memory, and policy layers.
Add a description, image, and links to the agent-systems topic page so that developers can more easily learn about it.
To associate your repository with the agent-systems topic, visit your repo's landing page and select "manage topics."