Item detail

hadihonarvar/flock

Flock is an Apache-2.0 self-hosted LLM gateway that turns Macs and Linux boxes into a private inference cluster with OpenAI- and Anthropic-compatible APIs, per-user keys, quotas, audit logs, and routing across Ollama, vLLM, MLX-LM, or llama.cpp-RPC.

Score8.6
Popularity44.0
Riskconditional
TierGold
Score breakdown
Usefulness9.0
Novelty7.0
Momentum7.0
Maturity7.6
Open-source/build8.4
Evidence7.2
Workflow potential9.7
Setup ease4.2

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for teams that want one internal model endpoint instead of a pile of separate local runtimes: wire one existing app or coding agent to it first, then test routing, quotas, and failover before treating it as shared infrastructure.

Who should use it

self-hosting teamsdevelopers running local modelsAI platform engineersprivacy-conscious organizations

Who should skip it

Skip if the source link, docs, or setup requirements do not match your workflow.

Risk explanation

It centralizes internal model traffic and user keys behind one endpoint, so treat it like production infrastructure and lock down network exposure, quotas, and audit-log access.

Evidence links

Closest alternatives / related signals

llm-gatewayself-hostedinferenceopenai-compatibleprivate-ai