Personal Health Insights Agent (PHIA)

The live attention layer for Paperclip. Re-stacks approvals, issues, and agent signals into now, next, and ambient.

A framework for building multi-agent AI systems. Enables LLMs to collaborate through hierarchical organization, parallel task execution, and extensible tools.

Deterministic, lightweight behaviour trees for C#. JSON & DSL support. Built for game AI, real-time agents, and rapid iteration.

[ANON for Submission]

Open-source failure intelligence platform for LLM & agent systems. Adds failure memory, pre-flight warnings, pattern detection, and system health scoring.

Benchmarked agent execution runtime for Python. Sub-10ms cold starts, real-time streaming, time-travel debugging, and self-growing tool libraries. Compare 3 sandbox backends: Docker (OpenSandbox), MicroVM, and in-process AST.

An open, neutral protocol for generating standardized intent metadata across apps, agents, and AI systems.

PROMPT™ is a human-first framework for structuring AI prompts and human-AI interactions. Beneath its approachable surface, PROMPT™ functions as a structured interaction schema for AI agents, LLM solutions, retrieval systems, and agentic workflows.

Lightweight Agent Framework for building AI apps with any LLM

This repo contains the original JADE code from the SVN of Telecom Italia

Documentation for Swarms — the multi-agent AI framework. This repo is the source for the docs site, built with Mintlify.

Observability and influence tracing infrastructure for multi-agent AI systems.

Open infrastructure modules for reliable and governable agent systems.

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.

Prompt Cloud Intent Compression

SAGE — Self-improving Autonomous Generation Engine. Prompt → production software using coordinated AI agents. Local-first multi-agent coding pipeline with planning, coding, execution, and self-healing debugging.

Deterministic-first agent execution system focused on bounded autonomy, auditability, replayability, and operational reliability.

Compile structured intent into reliable AI workflows — no prompt engineering required

📈 Experiment with LLM-assisted equity trading flows in a modular sandbox using MCP servers, trader agents, and a simple SQLite database for accounts.