1. Conduid
  2. Data
  3. Local Model Gateway
MCP server · Data

Local Model Gateway

by · github.com/vstep1/local-model-gateway

Lightweight local AI workstation management for local agents and LLM apps.

Unclaimed agentsai-agentsgpu-residencygpu-schedulinglaunchdllama-cpplocal-llmlocal-modelsmcpmcp-servermodel-context-protocolmodel-gatewaymodel-servingopenai-apiopenai-compatibleruntime-managementsqlitetypescript
InstallView source
28Low

Scored 11 hours ago · breakdown

About Local Model Gateway

Local Model Gateway is an MCP server published by vstep1 in the Data category: lightweight local AI workstation management for local agents and LLM apps.

The repository has 2 stars and 0 forks, with the last commit a month ago. Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/vstep1/local-model-gateway

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Local Model Gateway

Powered by Claude

Ask about Local Model Gateway — answers draw on its README.

Security checks

6 checks have not been run yet.

Releases

v0.4.0v0.4.0 · 31 May 2026Added Added durable runtime timeline events for queued work, runtime load/unload, cancellation, timeout, and failure history. Added dashboard Recent Work filters and a Runtime Timeline panel. Added the read-only MCP `runtime_history` tool.
v0.3.0v0.3.0 · 23 May 2026Added Added stop-command cancellation for OpenAI-compatible requests, so commands such as `stop` and `cancel generation` cancel matching in-flight local work instead of starting another GPU request. Added runtime telemetry support for…
v0.2.0v0.2.0 · 19 May 2026Highlights Added an agent-led install contract in `AGENTS.md` and a detailed install/debug runbook in `docs/agent-install.md`. Upgraded `local-model-gateway doctor` with `--json`, `--fix-plan`, gateway endpoint checks, sibling gateway…
v0.1.0v0.1.0 · 19 May 2026First public source release of Local Model Gateway. Highlights: OpenAI-compatible `/v1/chat/completions`, `/v1/responses`, and `/v1/models` routes. Streamable HTTP MCP endpoint at `/mcp` with setup and runtime tools. SQLite-backed GPU work…
Questions

About Local Model Gateway

How do I install Local Model Gateway?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Local Model Gateway safe to use with an AI agent?

Its trust score is 28 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Local Model Gateway still maintained?

Yes — the latest release is v0.4.0 (31 May 2026), and the last commit was a month ago. The repository has 2 stars.