HERMES
Safetensors
English
modernbert
llm-routing
model-chooser
intelligent-orchestration
fine-tuned
cma-es
federated-learning
cost-optimization
open-source
production-ai
model-dispatch
prompt-routing
multi-model
ensemble-decision
human-readable-decisions
federated-llm
evolution-strategy
ai-infrastructure
llm-inference
prompt-classification
model-selection
intelligent-dispatch
cost-effective-llm
production-routing
free-llm-api
openrouter
transformer-based
classifier
v1.3.0
fugusashi
eulogik
self-hosted
on-device
cpu-inference
low-latency
22ms-inference
3-model-classes
gpt-oss
lfm
149m-params
cross-entropy-training
cosine-scheduler
differential-privacy
federated-averaging
multi-agent
task-orchestration
grpo-reinforcement-learning
human-in-the-loop
explainable-ai
xai
interpretable-ai
natural-language-explanation
confidence-scoring
fallback-strategy
ensemble-ai
mlops
ai-orchestration
llmops
prompt-engineering
token-efficiency
aiops
llm-observability
model-governance
open-ai-compatibility
chat-completion-api
openai-compatible
v1-chat-completions
streaming
function-calling
agentic-ai
rag-routing
enterprise-llm
startup-llm
healthcare-llm
code-assistant
creative-writing-ai
math-reasoning
factual-qna
llm-gateway
smart-proxy
model-proxy
ai-gateway
inference-optimization
gpu-saving
cost-saving
latency-optimization
real-time-inference
edge-ai
on-device-inference
embedded-llm
edge-deployment
mobile-friendly
cpu-only
no-gpu-needed
