Results for “llm usage control”

204 tools in the directory · Updated 2 Nov 2026

“llm usage control”Runs on Self-hostedShowing 204 tools

RubyLLMby RubyLLMBuild model-powered applications and agents in RubyFree
Obot AI Control Planeby ObotGovern AI agents’ access to models, tools and company systemsFree
Manifest LLM Gatewayby ManifestAn open-source gateway for routing LLM requests, handling provider failures, and tracking inference use.Freemium
any-llmby Mozilla.aiSwitch LLM providers through a common Python interfaceFree
LLMWhispererby UnstractPrepare layout-preserved document text for language-model pipelinesFreemium
Opencontrollerby LyzrGovernance control plane for AI agents across clouds and frameworks$100K/yr
Deepchecks LLM Evaluationby DeepchecksProduction-grade LLM evaluation, testing, and monitoring platformPaid
vLLMby vLLMLLM inference and serving library.Free
LLM Compressorby IBMOpen-source Python library for quantizing and pruning LLMs to run faster in vLLMFree
AnythingLLMby AnythingLLMYC S22Private AI assistant that runs on your own computerFreemium
LiteLLMby LiteLLMYC W23Open-source AI gateway that puts many LLM providers behind one API with spend caps and routingFreemium
Otariby Mozilla.aiControl model routing, budgets and access through one AI gatewayUnknown
Fabric Gatewayby PostmanGoverned gateway for LLMs, MCP servers, and internal APIsFreemium
TrueFoundry Agent Gatewayby TrueFoundryControl layer for governing and observing AI agents in productionContact sales
Haystackby deepsetOpen-source Python framework for building RAG, agent, and multimodal LLM applicationsFreemium
Lunaryby LunaryMonitor LLM applications, review conversations and improve prompts$20+/user/mo
Bitoby BitoGovernor: an LLM router that grounds coding-agent requests in your codebase to cut token use and price per tokenContact sales
Langfuseby LangfuseYC W23Open-source platform for tracing, evaluating, and improving LLM and agent applicationsFreemium
Archestraby ArchestraOpen-source AI infrastructure for controlling agent access, tools, and model spendFreemium
Speakeasyby SpeakeasyGovernance control plane for enterprise AI agents and MCP serversPay as you go
Inference.netby inference.netInference infrastructure for serving, monitoring, and training LLMsFreemium
Prisma AIRS AI Gatewayby PortkeyAI gateway for routing, observing and governing LLM and agent trafficFreemium
Inferactby InferactProduction LLM inference platform from the creators of vLLMContact sales
Galileoby GalileoObservability, evaluation, and guardrails for LLM and agentic applications.Unknown