Results for “llm inference”

23 tools in the directory · Updated 2 Nov 2026

“llm inference”Ways to use: MCP serverBacked by Y CombinatorShowing 23 tools

LiteLLMby LiteLLMYC W23Open-source AI gateway that puts many LLM providers behind one API with spend caps and routingFreemium
Morphby MorphYC S23Hosted inference API for coding agents, with search, edit-apply, and compaction modelsUnknown
PostHog AI Observabilityby PostHogYC W20Trace, evaluate, and cost-track LLM calls inside PostHogFreemium
Langfuseby LangfuseYC W23Open-source platform for tracing, evaluating, and improving LLM and agent applicationsFreemium
Confident AIby Confident AIYC W25AI quality platform for evaluating, tracing, and monitoring LLM applications across teams.Freemium
Openlayerby OpenlayerYC S21AI governance platform to test, monitor, and control AI systemsFreemium
Ollamaby OllamaYC W21Run and build with open AI models locally or in the cloudFreemium
Graphitiby Zep AIYC W24Open-source framework for temporal context graphsFree
Tavus Conversational Video Interface (CVI)by TavusYC S21Real-time face-to-face AI video agents built on Tavus APIsUnknown
Supabase MCP Serverby SupabaseYC S20Connect AI assistants to your Supabase projects through MCP.Unknown
Demodeskby DemodeskYC W19AI sales agents that record calls, coach reps and update the CRM€25+/user/moFree trial
Roboflowby RoboflowYC S20Vision AI platform for building, training, deploying and monitoring computer vision applications.Freemium
Replicateby ReplicateYC W20Cloud API for running, fine-tuning and deploying AI modelsPay as you go
Firecrawlby FirecrawlYC S22Web data API that lets AI agents search, scrape, and crawl live web content, with a developer code and docs index.Freemium
Beamby BeamYC W22Persistent cloud VMs, sandboxes and GPUs for AI agentsPay as you go
Skyvernby SkyvernYC S23AI agents that run browser workflows on any websiteFreemium
Lingo.devby Lingo.devYC F24Localization engineering and translation-quality platform for product teams.Freemium
Laminarby LaminarYC S24Trace AI agents and find recurring failures across their runsFreemium
Mem0by Mem0YC S24Persistent memory layer for AI agents and appsFreemium
Reductoby ReductoYC W24Parse complex documents and extract structured data with citationsPay as you go
Sourcebotby SourcebotYC F25Self-hosted code search and AI codebase understanding for people and agents.Freemium
Notteby NotteYC S25Browser infrastructure and agent tools for web automation.Freemium
OpenWorkby OpenWorkYC X26Open-source AI workspace for working with models on your files.Freemium