alvaropaco/haif
Production-ready microservices framework for AI inference over RPC. It provides a Gateway for client requests, an Orchestrator that schedules work, a Registry for model metadata, Workers that run inference, and a full observability stack (Prometheus, Grafana, Loki, Jaeger) — all wired together with Docker Compose.
Supports both CPU and GPU inference with model streaming via Hyperswarm's RPC transport; uses OpenTelemetry for unified metrics and distributed tracing across all Node services. Includes an HTTP Bridge for easy client integration, Postgres for orchestration state, and Redis for lightweight coordination—all with pre-built Grafana dashboards tracking throughput, latency (P95), and inference-specific metrics.
No commits in the last 6 months.
Stars
14
Forks
1
Language
TypeScript
License
Apache-2.0
Category
Last pushed
Oct 07, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/alvaropaco/haif"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
nikrich/hungry-ghost-hive
Hive is a Multi Agent Orchestrator modelled after Agile Teams
joryeugene/keephive
A knowledge sidecar for Claude Code. It captures what you learn, verifies it stays true, and...
hivemoot/hivemoot
Framework for AI agent teams that build real software on GitHub — governance, roles, and CLI included.
hivemoot/hivemoot-agent
Run autonomous AI agents that contribute to your GitHub repos — code, reviews, discussions, and PRs.
Zyling-ai/ZyHive
🐝 引巢 · ZyHive | AI 团队操作系统 — 为 AI 成员注入灵魂，可视化管理多智能体团队。Self-hosted AI Team OS · Go + Vue 3 ·...