#distributed-systems

Autonomous Agent Consistent Hashing Ring with Virtual Nodes for Bounded-Load Distributed Sharding

Autonomous Agent Consistent Hashing Ring with Virtual Nodes for Bounded-Load Distributed Sharding

A quantum prompt playground & macOS-native Rust coding agent: morphing fluid entropy into rigid execution checkpoints. Entropy cannot lie.

Open scheduling layer for AI-operated real machines, tools, desktops, jobs, and evidence

Scenery — one CLI tool for building, running, inspecting, and debugging Go backends. Local-first runtime, APIs, logs, traces, DB tools, generated clients, and AI agent skills included.

⚡ Crash-consistent Two-Phase Commit (2PC) & WAL engine for AI agent workflows. Zero dirty state, zero hallucinated rollbacks.

AI/ML & Software Engineering portfolio showcasing LLM systems, Agentic AI, RAG, ML infrastructure, distributed systems, and production AI projects

Reference implementation of a transport-agnostic protocol for signed, bounded, and verifiable delegation between autonomous agents.

Production-grade distributed ML inference platform — FastAPI gateway, Redis-backed worker pool with dynamic batching, WebSocket result streaming, and a live ops dashboard. Serves YOLO, Whisper, RAG and text models, with an MCP agent server and streaming chat.

Nimbus is a lightweight, pull-based edge AI workload orchestrator.

Ka-Tet for Orchestral Agentic AI - six AI agents and one human holding a single system upright, engineered on the structure of an epic quest cycle

Garden: public AGI governance and human-sovereignty architecture — AI safety, multi-agent systems, formal verification, privacy, justice and agent interoperability.

A self healing API service mesh, written in Rust on Tokio and Axum, that watches a topology of upstream services, detects failures with a debounced health checker, atomically reroutes traffic and rewrites its own routing config, and asks Claude (via the Anthropic Messages API with tool calling) to produce a structured incident report.

Zero-config orchestrator for distributed LLM inference on your LAN — splits a model across nodes by layer (pipeline parallelism) behind one OpenAI-compatible endpoint. Open-core (MIT).

A read-only MCP server exposing Slurm scheduler state to agents — allowlist enforced in code, not requested in a prompt, with progressive disclosure.

Resumable, exactly-once event-stream client for long-running agent sessions on iOS: cursor-based resume, ordering across parallel tool calls, backpressure, a command outbox where delivered != acknowledged, and an independent invariant checker.

Distributed search engine — Spring Boot, RMI, Lucene BM25, OpenAI