50 repos · updated October 10, 2026
Model providers, proxies and local models for Hermes Agent
Hermes Agent works with Nous Portal, OpenRouter, OpenAI, Anthropic, local endpoints and many other providers, and you switch with one command. These projects add routers, API proxies, local model servers and cost tools that sit between Hermes and the model.
Top 12 models by GitHub stars
jundot
oMLX
LLM inference server for Apple Silicon with continuous batching and SSD caching, run from the menu bar
ccusage ccusageCLI that reports token usage and costs from local coding agent data, including Hermes Agent
mnfst Manifest LLM GatewayOpen-source LLM gateway with one OpenAI-compatible endpoint, model routing, fallbacks and cost tracking
lemony-ai cascadeflowIn-process runtime that routes agent model calls by cost, latency, quality and policy
Soju06 codex-lbLoad balancer and proxy that pools ChatGPT accounts behind OpenAI-compatible endpoints with a dashboard
Javis603 Token MonitorDesktop widget that tracks token usage and costs across 43+ AI coding tools, including Hermes Agent
xiufengsun TokenTrackerLocal-first dashboard for AI token usage and cost across dozens of coding tools, with native apps
landingbj LinkMindAI middleware for model routing, RAG and OpenAI-compatible APIs, with Hermes Agent sync hooks
humantonylee free-routerTerminal tool that pings free AI models and writes the best one into OpenCode, OpenClaw or Hermes Agent
VasiHemanth TokenTelemetryLocal dashboard for token usage, cost and tool calls across coding agents, with a dedicated Hermes Agent view
soulduse AI Token MonitorMenu bar and system tray app that prices your AI coding tool usage from local logs, Hermes Agent included
y13sint FreeQwenApiLocal OpenAI-compatible proxy that exposes a Qwen Chat web account as an API for tools such as Hermes Agent
All 50 models repos
Click a column to sort| jundot/omlxLLM inference server for Apple Silicon with continuous batching and SSD caching, run from the menu bar | Python | 22,670 | Oct 9, 2026 |
| ccusage/ccusageCLI that reports token usage and costs from local coding agent data, including Hermes Agent | Rust | 18,936 | Oct 10, 2026 |
| mnfst/llm-gatewayOpen-source LLM gateway with one OpenAI-compatible endpoint, model routing, fallbacks and cost tracking | TypeScript | 7,567 | Oct 9, 2026 |
| lemony-ai/cascadeflowIn-process runtime that routes agent model calls by cost, latency, quality and policy | Python | 3,965 | Sep 25, 2026 |
| Soju06/codex-lbLoad balancer and proxy that pools ChatGPT accounts behind OpenAI-compatible endpoints with a dashboard | Python | 3,319 | Oct 9, 2026 |
| Javis603/token-monitorDesktop widget that tracks token usage and costs across 43+ AI coding tools, including Hermes Agent | JavaScript | 2,707 | Oct 10, 2026 |
| xiufengsun/TokenTrackerLocal-first dashboard for AI token usage and cost across dozens of coding tools, with native apps | JavaScript | 2,012 | Oct 10, 2026 |
| landingbj/LinkMindAI middleware for model routing, RAG and OpenAI-compatible APIs, with Hermes Agent sync hooks | Java | 467 | Sep 30, 2026 |
| humantonylee/free-routerTerminal tool that pings free AI models and writes the best one into OpenCode, OpenClaw or Hermes Agent | TypeScript | 396 | Jul 15, 2026 |
| VasiHemanth/tokentelemetryLocal dashboard for token usage, cost and tool calls across coding agents, with a dedicated Hermes Agent view | Python | 377 | Oct 8, 2026 |
| soulduse/ai-token-monitorMenu bar and system tray app that prices your AI coding tool usage from local logs, Hermes Agent included | Rust | 349 | Oct 1, 2026 |
| y13sint/FreeQwenApiLocal OpenAI-compatible proxy that exposes a Qwen Chat web account as an API for tools such as Hermes Agent | JavaScript | 332 | Jun 30, 2026 |
| bitrouter/bitrouterLocal Rust model router with an OpenAI-compatible API that learns routing policies for agent workflows | Rust | 235 | Oct 10, 2026 |
| icoretech/codex-poolerSelf-hosted gateway that fronts Codex accounts with stable Pool API keys for agents and teams | Elixir | 222 | Oct 10, 2026 |
| EfficientContext/ContextPilotContext reuse layer that cuts redundant tokens before they reach the model | Python | 141 | Oct 8, 2026 |
| dyedd/lensSelf-hosted multi-protocol LLM gateway with one base URL across many providers | Python | 132 | Oct 8, 2026 |
| Socialpranker/agentburnLocal profiler that shows which 5-hour window burned your usage, and where tokens went | Python | 112 | Oct 5, 2026 |
| SouthpawIN/turbofitAdaptive local-inference provider that fits the best sustainable model to your hardware | Python | 107 | Oct 8, 2026 |
| tuxevil/tuxevil-rotatorOpenAI-compatible proxy that rotates free-tier LLM accounts with per-model quota routing | TypeScript | 70 | Oct 5, 2026 |
| piyush-tyagi-13/llm-keypoolFree-tier LLM API key pool with rotation, 429 cooldowns and a local OpenAI-compatible proxy | Python | 66 | May 5, 2026 |
| InfiniteWhispers/HermesAgent-MultiModelFully local multi-model setup for Hermes Agent with Ollama, Mixture-of-Agents routing and a tuning guide | — | 59 | Jul 13, 2026 |
| nujovich/hermes-telemetryBudget enforcement and observability plugin for Hermes Agent that stops runs before they overspend | Python | 45 | Oct 9, 2026 |
| open-world-project/model-routerHermes Agent plugin that routes each turn to the cheapest of five model tiers and escalates when needed | Python | 32 | May 10, 2026 |
| KaiFelixBennett/hermes-claude-code-localRun Hermes Agent and Claude Code on a local llama.cpp model with no API costs | Shell | 32 | Oct 5, 2026 |
| compnew2006/MetaAI-Free-Hermes-AgentSelf-hosted Go API that wraps Meta AI's Muse Spark as an OpenAI-compatible endpoint for Hermes Agent | TypeScript | 28 | Jun 24, 2026 |
| GumbyEnder/hermes-local-rig-accountingPer-token cost accounting for local LLM inference rigs in Hermes Agent | Python | 24 | Oct 1, 2026 |
| ArcticWinterSturm/opencode-compat-shimOpenAI-style streaming proxy that lets Hermes Agent use OpenCode's free-tier models | Python | 23 | Sep 28, 2026 |
| BlockRunAI/ClawRouter-HermesPlugin that adds BlockRun's ClawRouter LLM router to Hermes as one provider, paid per request | Python | 22 | Oct 5, 2026 |
| profbernardoj/morpheus-skillDecentralized AI inference skill with 30+ models via Morpheus, for OpenClaw, Hermes Agent and others | JavaScript | 21 | Sep 18, 2026 |
| moreoronce/hermes-zcode-glm-patchCompatibility patch that fixes misleading 429 code 1305 errors when Hermes Agent uses GLM-5.2 on Z.AI | — | 20 | Aug 3, 2026 |
| zeyxx/hermes-antigravityGoogle Antigravity and Cloud Code Assist inference provider plugin for Hermes Agent using OAuth sign-in | Python | 20 | Oct 8, 2026 |
| pooops15/muse-bridgeBridge that exposes the Muse agent as an OpenAI-compatible ms/muse model inside 9Router for Hermes | Python | 19 | Oct 7, 2026 |
| prasadus92/vertex-proxyLocal Anthropic, Gemini and OpenAI-compatible proxy that routes requests to Google Cloud Vertex AI | Python | 17 | Jul 11, 2026 |
| Shelpuk-AI-Technology-Consulting/kitty-bridgeLocal bridge that lets coding agents use any LLM provider, such as Claude Code with MiniMax | Python | 16 | Oct 5, 2026 |
| neerazz/hermes-antigravity-oauthRun Hermes Agent on a Google Antigravity plan through the official agy CLI, with SOUL.md as the persona | Python | 16 | Sep 28, 2026 |
| notwitcheer/portal-affordableHermes Agent profile for Nous Portal that pins side tasks to low-cost models to keep spend down | — | 15 | Oct 2, 2026 |
| Meapri/hermes-google-antigravity-pluginGoogle Antigravity OAuth provider for Hermes Agent, sign in with a Google account instead of an API key | Python | 15 | Jul 18, 2026 |
| toshipepe/tokimeterLocal-first usage and cost meter for AI coding agents including Claude Code, Codex and Hermes | JavaScript | 15 | Sep 17, 2026 |
| sssstwee/switch-plus-plusDesktop config switcher, model router and local gateway for Claude Code, Codex, Hermes and other agents | TypeScript | 14 | Sep 23, 2026 |
| angrysky56/hermes-headroomInstaller that routes Hermes Agent traffic through the Headroom compression proxy via OpenRouter | Python | 12 | Jun 12, 2026 |
| srikanthmx/hermes-cli-orchestratorHermes plugin that pools model providers and local AI CLIs and switches the primary model from Telegram | Python | 12 | Jul 10, 2026 |
| spacepirate15/quantum-hermes-free-router-kitStarter kit that routes Hermes Agent through a local LiteLLM proxy with free-tier models and fallback | Shell | 12 | Jun 10, 2026 |
| Adolanium/hermes-clinepassClinePass model provider plugin for Hermes Agent, with Kimi, GLM, DeepSeek and more | Python | 11 | Oct 9, 2026 |
| StrawCoding/hermes-cursor-agentHermes Agent model provider that routes chat requests to the local Cursor Agent CLI | Python | 11 | Jul 3, 2026 |
| photofanz/hermes-claude-proxy-v5OpenAI-compatible proxy that exposes a Claude Max subscription to Hermes Agent and other clients | JavaScript | 10 | Jun 30, 2026 |
| artemiimillier/hermes-codex-poolGateway that pools Claude, ChatGPT and Kimi subscriptions behind one local endpoint for Hermes Agent | Python | 10 | Sep 23, 2026 |
| Reedtrullz/hermes-antigravity-authHermes Agent plugin for Google Antigravity OAuth with Claude and Gemini models and account rotation | Python | 10 | Aug 21, 2026 |
| mrhisyammm/hermes-antigravity-authHermes Agent plugin and local proxy provider using Google Antigravity IDE OAuth for Gemini and Claude models | Python | 9 | Jun 23, 2026 |
| FloorIsGround/hermes-crofaiProvider plugin that adds CrofAI as a model provider in Hermes Agent | Shell | 2 | May 22, 2026 |
| Kosello/hermes-ollama-usage-monitorHermes plugin showing live Ollama Cloud usage, plan versus API cost and threshold alerts | Python | 1 | Oct 4, 2026 |
Models FAQ
Which models can Hermes Agent use?
Hermes is not tied to one provider. You can use Nous Portal, OpenRouter, OpenAI, your own endpoint and many others, and switch with the hermes model command.
Can I run Hermes Agent with a local model?
Yes. Point Hermes at a local, OpenAI-compatible endpoint. Several projects in this category package local model servers and proxies for that purpose.
Related guides: How to install Hermes Agent