Spin up any open LLM on rented GPUs (vast.ai/RunPod), serve it with vLLM or llama.cpp, and drive it from Claude Code via Claude Code Router. Pay by the hour.
How fast jhammant/AIonDemandCluster is gaining stars, and where it lands on Trendshift and GitHub Trending
Activity and trending
Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending
Jun 2026 – Oct 2026
Stars +42in 5 months
0102030
24
Forks +7in 5 months
024
4
Merged PRs 10in 5 months
0510
10
Trendshift Trendingthe best rank each month, on any day it made the top 25
Not in the Trendshift top 25 in this period
Jun 2026Jul 2026Aug 2026Sep 2026Oct 2026
The left and right arrow keys step from month to month; Home and End go to the first and the last
Stars, forks, merged pull requests and best Trendshift Trending rank, by month
Month
Stars gained
Forks gained
Merged PRs
June 2026
+24
+3
10
July 2026
+18
+4
0
August 2026
+0
+0
0
September 2026
+0
+0
0
October 2026
+0
+0
0
Total
+42
+7
10
1#1 on the list
7Best rank that month
Not trending
Social mentions
Recent discussions about this repository across the web
2 posts
Claude Opus 4.8 is $25/1M output — so a 789B open model, self-hosted, came out cheaper per token. Opus is the better model; the point is running a giant open model yourself is now a $34 decision.…
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.
Source-available LLM router and AI cost optimizer. Routes simple prompts to cheap or local models and complex ones to premium models, automatically. Drop-in OpenAI-compatible proxy for Claude Code, Codex, Cursor and OpenClaw. Self-hosted, no middleman.
MCP server: delegate heavy-token tasks from Claude Code to DeepSeek, Kimi, GLM, Qwen, Grok, or any OpenAI-compatible model. Mix providers per task, cost receipt on every call. Zero dependencies.
