Intelligent LLM gateway and VRAM-aware router for Ollama, llama.cpp, and OpenAI with semantic caching and auto-failover.
150·LLM Ops·Open source
Alternative to
hermes-claude-code-local
Open sourceRun Hermes Agent and Claude Code locally on llama.cpp with zero API costs.
29
Run Hermes Agent + Claude Code locally on llama.cpp — zero API costs. A 4h / 7M-token session that would have cost $94 on Claude Opus 4.7
Pros
- +Zero API costs for agentic coding
- +Full local control and privacy
- +Supports Telegram integration for remote control
- +Optimized for dense models with MTP decoding
Cons
- −Requires powerful local hardware for good performance
- −Setup complexity with multiple components (llama.cpp, LiteLLM)
- −Claude Code bridge has token overhead and context limitations
Target audience: Developers and AI enthusiasts who want to run autonomous coding agents locally without cloud API costs.
Related tools
Other open-source tools that share tags with hermes-claude-code-local.
tightwad
MIT
Self-hosted mixed-vendor GPU inference cluster manager with speculative decoding proxy for faster LLM serving.
33·Self-Hosted AI·Open source
granitepi-4-nano
Apache-2.0
Run IBM Granite 4.0 locally on Raspberry Pi 5 with Ollama.This is a privacy-first AI. Your data never leaves your device
11·Self-Hosted AI·Open source
LocalAI
MCPMIT
Open-source AI engine to run LLMs, vision, voice, image, video on any hardware, no GPU required.
49k·Self-Hosted AI·Open source
Alternative to
93+ production-ready AI projects with tutorials on LLMs, RAG, and agents.
37k·Developer Tools·Open source
QwenPaw
MCPApache-2.0
QwenPaw: Your personal AI assistant, deployable locally or in the cloud, with memory, multi-agent support, and multi-cha
34k·AI Agents·Open source
Alternative to