{
  "generated": "2026-10-31T00:00:00Z",
  "query": "Hermes Agent local LLM free tier",
  "total": 15,
  "buckets": {"HOT": 3, "FOUNDATIONAL": 10, "NOISE": 2},
  "items": [
    {"index": 1, "url": "https://hermes-agent.nousresearch.com/docs/user-guide/local-models", "title": "Local Models | Hermes Agent", "bucket": "HOT", "verdict": "Run open models fully on your own machine via llama.cpp; free inference, no hosted token bill.", "evidence": "Hermes downloads and manages the inference engine (llama.cpp) and picks the right build per hardware."},
    {"index": 2, "url": "https://hermes-agent.nousresearch.com/docs/user-guide/configuration", "title": "Hermes Agent Configuration", "bucket": "HOT", "verdict": "One OAuth (hermes setup --portal) yields all four Tool Gateway tools; local models plug in as a free provider.", "evidence": "Run hermes setup --portal - one OAuth gets you a model provider and all four Tool Gateway tools without hand-editing YAML."},
    {"index": 3, "url": "https://build.nvidia.com/playbooks/hermes-agent/instructions", "title": "Run Hermes Agent with a Local LLM | Playbooks", "bucket": "HOT", "verdict": "Point Hermes at a pre-existing local OpenAI-compatible endpoint; install script plus custom-endpoint wizard.", "evidence": "curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash; choose Custom endpoint (enter URL manually)."},
    {"index": 4, "url": "https://github.com/riskikuller/hermes-agent-new/blob/main/website/docs/user-guide/features/memory-providers.md", "title": "memory-providers.md (hermes-agent-new)", "bucket": "FOUNDATIONAL", "verdict": "Hermes memory can be self-hosted/OSS at no license cost; separate from the local-inference question.", "evidence": "Cost: Free (open-source, AGPL-3.0); self-hosted or OSS; requires hermes plugins install mem0."},
    {"index": 5, "url": "https://github.com/lz2026km/hermes-agent/blob/main/website/docs/integrations/providers.md", "title": "providers.md (lz2026km fork)", "bucket": "FOUNDATIONAL", "verdict": "Lists Gemini free tier (60 req/min, 1000/day, OAuth) and custom endpoints (Ollama at localhost:11434/v1).", "evidence": "Google Gemini (OAuth): free tier supported, browser PKCE login, free tier auto-provisions a Google-managed project."},
    {"index": 6, "url": "https://www.getorchestra.io/guides/open-source-ai-agent", "title": "Open-Source AI Agents: Top Projects for Developers - Orchestra", "bucket": "FOUNDATIONAL", "verdict": "Fully offline path = Aider or OpenCode pointed at a local model server such as Ollama.", "evidence": "OpenCode lists local models via Ollama, LM Studio, llama.cpp and Atomic Chat among 75+ providers."},
    {"index": 7, "url": "https://www.kdnuggets.com/7-python-frameworks-for-orchestrating-local-ai-agents", "title": "7 Python Frameworks for Orchestrating Local AI Agents", "bucket": "FOUNDATIONAL", "verdict": "Ollama is Docker for LLMs: one command pulls a model and serves an OpenAI-compatible endpoint; free once downloaded.", "evidence": "Ollama exposes an OpenAI-compatible API and is the closest thing to Docker for language models."},
    {"index": 8, "url": "https://www.ayautomate.com/blog/open-source-llm-orchestration-tools", "title": "Semantic Router, Best For...", "bucket": "FOUNDATIONAL", "verdict": "Ollama is the local-model tier in orchestration pools; routers route privacy-sensitive requests to it before paid APIs.", "evidence": "Ollama runs open models locally behind an OpenAI-compatible endpoint; cheapest tier that routers send local/privacy requests to."},
    {"index": 9, "url": "https://www.langchain.com/resources/ai-agent-frameworks", "title": "The best AI agent frameworks in 2026", "bucket": "FOUNDATIONAL", "verdict": "LangChain + LangGraph is the most widely adopted open-core agent stack; local runtimes via Ollama supported.", "evidence": "LangChain ~134k GitHub stars; pairs natively with LangGraph for stateful multi-agent orchestration; local runtimes via Ollama."},
    {"index": 10, "url": "https://www.sim.ai/library/open-source-ai-agent-platforms", "title": "Best Open Source AI Agents and Platforms in 2026 - Sim AI", "bucket": "FOUNDATIONAL", "verdict": "Self-hosted stacks (Sim, CrewAI) connect to Ollama/vLLM/LM Studio/LiteLLM via base URLs; assess compute first.", "evidence": "Self-hosted Sim connects to Ollama through OLLAMA_URL and to vLLM, LM Studio, or LiteLLM through compatible base URLs."},
    {"index": 11, "url": "https://infrabase.ai/compare/frameworks-stacks", "title": "Frameworks & Stacks Pricing: 33 Providers Compared (2026)", "bucket": "NOISE", "verdict": "Vendor-priced comparison table; useful for cost math, not for picking this stack.", "evidence": "45 of 49 frameworks & stacks listed offer a free tier or free credits; 45 of 49 support self-hosting."},
    {"index": 12, "url": "https://agnt.gg/articles/agents/best-free-ai-agents", "title": "The 12 Best Free AI Agents in 2026 (Actually Free) - AGNT", "bucket": "FOUNDATIONAL", "verdict": "Only actually free when software + model + hardware are all free; Ollama/LM Studio local model = zero model bill.", "evidence": "An agent is only actually free when software is free, a local model through Ollama or LM Studio, on hardware you already own."},
    {"index": 13, "url": "https://theagentsindex.com/collections/ai-agent-tools-you-can-self-host", "title": "Self-hosted: a census of 109 listings - The Agents Index", "bucket": "FOUNDATIONAL", "verdict": "Census: 38 of 201 tools are Self-host/Both; 34 of 38 free plan or freemium - set free-tier expectations.", "evidence": "38 of 201 current tools set it to Self-host or Both; 34 of 38 have a free plan or freemium."},
    {"index": 14, "url": "https://resources.rework.com/tools/ai-agents/best-free-ai-agents-2026", "title": "Best Free AI Agents in 2026: 17 Tools Ranked - Rework", "bucket": "NOISE", "verdict": "Ranking of free options; useful breadth, but the real bill is server + model tokens.", "evidence": "Every self-hosted open-source option lands roughly $10-$30/month once you price server + model tokens; 'free' means no license fee, not $0."},
    {"index": 15, "url": "https://github.com/DevAnimecx/free-ai-agent-stack/blob/main/data/llm-apis.yaml", "title": "llm-apis.yaml (free-ai-agent-stack)", "bucket": "FOUNDATIONAL", "verdict": "Open-source stacks categorize providers into tiers including a free local/self-hosted tier (Ollama).", "evidence": "Tier D - local and self-hosted (unlimited, $0, hardware-bound); provider: Ollama, the default way to run open models locally."}
  ]
}