Delegate tasks to DeepSeek right inside your Claude Code / Codex sessions.
Track work, verify results, carry memory, and sync tools across coding agents. Local files, no daemon.
Open-source tools for bounded AI-agent handoffs: explicit file packets, evidence receipts, controller-side verification, and a native Hermes plugin.
A control plane for bounded agentic development loops, providing local workflow state, context handoffs, and strict human review gates for AI coding agents.
Verify what survives when one AI agent hands work to the next.
This repository contains small, focused examples built while learning the OpenAI Agents SDK. The examples use openai-agents with an OpenAI compatible Gemini endpoint, and show how to build single agents, agents with tools, agents with memory, and multi agent systems.
A durable memory protocol for long-running AI agents with evidence-backed state, resumable handoffs, decision logs, provenance and validation.
Voice-enabled corporate IT help desk built with five OpenAI agents, Streamlit, and FastAPI. Supports employee verification, simulated account recovery, guided troubleshooting, ticket escalation, and call reviews, with audio transcription and persistent SQLite conversation state.
WRF protocol: AI workflow security infrastructure with dangerous command sentry alerts, context handoff, multi-task pause/resume, and human-AI contribution evidence.
Install Claude Code on your machine with one click to use DeepSeek models via domestic mirrors without needing a VPN.
To associate your repository with the agent-handoffs topic, visit your repo's landing page and select "manage topics."