Why frameworks win adoption
Defaults beat tutorials
Teams don’t stall on ‘which folder structure?’ — agentx new encodes OptimumAI’s production layout (nodes/, state/, schemas/, prompts/, utils/) so every repo looks familiar to reviewers and CI.
Products
From enterprise agent operations to interview coaching and research models — OptimumAI products keep humans in control of AI.
PreviewRecommended commercial flagship
Enterprise agent operations for BFSI, healthcare and document-heavy workflows. Strong evaluation & reliability layer — which agents are trustworthy, which prompts regressed, which tools fail, and how much each agent saves. Built on the open-source agentx-kit framework.
Build and configure agents for document, claims and policy workflows.
Test accuracy, task completion, regressions and model/cost trade-offs.
Trace tool calls, prompts, latency, tokens and spend.
Permissions, approvals, audit trails and policy enforcement.
Versioning, deploy, rollback, failure recovery and production monitoring.
MIT · PyPI · VS Code · MCP
agentx-kit is OptimumAI’s MIT-licensed, provider-agnostic framework and project scaffolder for LangChain and CrewAI. Builders pick a provider, agents, RAG, memory, MCP tools and skills — then get a ready-to-run uv project. The Control Plane is the enterprise ops layer on top; the kit is what communities and startups ship with day one.
v1.4.0 · MIT · Python ≥3.10, <3.15 · import agentx · CLI agentx
pip install "agentx-kit[all]" agentx new ext install OptimumAi.agentx-kit
agentx new (or the VS Code wizard) generates a structured uv project — nodes, state, schemas, prompts, RAG utils — not a single opaque script.
Swap OpenAI, Azure, Anthropic, Gemini, Bedrock, Ollama and more without rewriting agent graphs. Env vars and model catalogs are first-class.
Supervisor, sequential, or parallel orchestration; sub-agents as tools; deep agents with planning, sandbox tools, and optional critic loops.
evaluate_run, prompt analysis, PII guardrails, usage limits, caching and a Streamlit dashboard — the same primitives AgentX Control Plane surfaces at scale.
Scaffold, visualize, and run AgentX agentic projects (LangGraph / CrewAI) from VS Code. It shells out to the agentx CLI in your workspace .venv (or PATH) — no bundled Python, always the same toolkit as CI.
Marketplace ID OptimumAi.agentx-kit · v0.1.0
Install from MarketplaceChunk + embed with FAISS or Chroma, eight embedding backends (including local HuggingFace), loaders for PDF/Excel/CSV/Word, incremental re-index via manifest.
agentx flow turns a file or whole project into a call graph — static AST, live traces, Mermaid/DOT export, or an interactive 2D/3D viewer.
agentx mcp exposes the kit to Claude, Copilot and Codex so scaffolding and project ops live inside your coding agents.
agentx azure scaffolds and deploys AI pipelines to Azure ML, Container Apps, Cosmos, Service Bus and Key Vault templates.
Optional STT/TTS (faster-whisper / edge-tts) and Claw multi-channel webhooks for WhatsApp, Telegram, Slack and email.
agentx new --enterprise adds tracing, guardrails, FastAPI, Docker, CI, evals and caching — a production skeleton startups can fork.
One catalog, twelve backends — pick in the wizard, VS Code, or agentx providers.
Why frameworks win adoption
Teams don’t stall on ‘which folder structure?’ — agentx new encodes OptimumAI’s production layout (nodes/, state/, schemas/, prompts/, utils/) so every repo looks familiar to reviewers and CI.
Provider lock-in is a tax
A curated provider catalog plus resilient tool-call parsing for small/local models means you can cost-down to Ollama or scale up to frontier APIs without a rewrite sprint.
Ops starts in the kit
Token/cost estimates, LLM-judge evals, PII redaction and usage limits are not afterthoughts — they are Python APIs the enterprise Control Plane already consumes for BFSI and healthcare workflows.
Meet builders where they work
Ship from terminal, import agentx in notebooks, scaffold from the Command Palette, or let Claude/Copilot drive agentx mcp. Distribution breadth is how open frameworks become defaults.
Use the kit as your agent runtime and scaffolder. Stay vendor-neutral while you find product-market fit — graduate to AgentX Control Plane when you need fleet evals, governance and AgentOps.
MIT license, Python 3.10+, public docs and issues. Extend providers, RAG loaders, domains and VS Code commands; templates upgrade via agentx upgrade.
Interactive wizard + demos that run without API keys. Teach orchestration, RAG and evals with a single CLI students already know from pip.
Standardize agent project layout across squads. Validate with agentx validate, visualize with graph/flow, enforce guards before Control Plane promotion.
PreviewBuild, evaluate, observe, govern and operate production AI agents.
Open AgentX
LiveOpen-source agentic framework + VS Code — PyPI for builders & communities.
Explore the kit
LiveScenario-led AI mocks with Agency Score, delivery metrics, and a growth loop.
Open Interview Coach
BetaMeasures human cognition — not what you say, what you reveal.
Request Access
In DevMultimodal LLMs trained on agency, reasoning, and human intent.
Research Portal
LiveCompare frontier models across benchmarks, pricing, and context.
Open Dashboard