mTarsier
Manage MCP servers, AI skills, and client configs locally across Claude, Cursor, VS Code, and Codex.
- AI Infrastructure & MLOps
- Free
- AI Agents
- Operations
- Productivity
The facts
- Category
- AI Infrastructure & MLOps
- Pricing
- Free. Free to use. No paid tier is required for the core product.
- Best for
- AI Agents, Operations, Productivity
- Website
- mtarsier.com
mTarsier alternatives
61 tools sit in AI Infrastructure & MLOps in the Cocoon directory. These are the closest to mTarsier.
Comet MLML experiment tracking and model monitoring. Compare runs, visualise metrics, and reproduce results across you…BentoMLOpen-source framework for building, shipping, and scaling AI applications. Package any model into a production…Fireworks AIBlazing-fast AI inference platform. Run open-source and custom models with the lowest latency and highest thro…Lightning AIFull-stack AI development platform. Build, train, fine-tune, and deploy models in one place. Home of PyTorch L…AnyscaleScalable AI compute platform built on Ray. Run distributed training, fine-tuning, and inference at any scale.ValohaiMLOps platform for automating ML pipelines. Version data, track experiments, and orchestrate training jobs acr…DatabricksUnified data lakehouse platform combining data engineering, ML/AI, and analytics with built-in governance and …FirecrawlTurns any website into clean LLM-ready Markdown or structured JSON for AI applications at scale. YC-backed.Monte CarloData and AI observability platform that monitors data quality, lineage, and anomalies across pipelines in real…TrueFoundryEnd-to-end ML platform for runtime LLM observability, deployment, and cost control in production environments.Upstage AIEnterprise AI platform providing the Solar LLM and Document Parse engine that transforms unstructured document…ModaProduct analytics platform designed specifically for AI applications to understand user interactions with AI f…
Learning to actually use this
Cocoon runs hands-on AI training across Sri Lanka and Asia. Picking a tool is the easy part; building it into how your team already works is the part people get stuck on.