Nova vs Triggered Agents by Adaptive

Nova and Triggered Agents by Adaptive are both ai agent apps tracked by AIDiveForge. Below is a side-by-side comparison of pricing, capabilities, platforms, and ownership — sourced from each tool's live website and verified before publishing.

Nova

Nova runs 24 specialist agents on your own machine against your own API keys, storing everything in local SQLite. The pipeline is explicit — classify, decompose, prepare, then stop at a gate before anything publishes, sends, or spends. That gate is the differentiator. Where it strains: the roster of 24 agents with no hosted fallback means setup requires real technical lift, and the Bun + TypeScript stack narrows who can extend it. Teams that outgrow the built-in connectors or need agents to reason across domains the roster doesn't cover will find themselves writing custom system prompts before they expected to.

Triggered Agents by Adaptive

Adaptive lets you describe work in plain language — 'flag suspicious signup domains every morning' or 'draft weekly product updates from GitHub' — and deploys agents that loop through the steps, call connected tools, and surface results without waiting for you to click through each stage. Agents can run in parallel, so a sales pipeline workflow and a development update feed operate independently at the same time. The approval controls let you stay in the loop on sensitive steps without babysitting routine ones. Where it strains: teams with complex conditional branching across departments, or those who need fine-grained workflow versioning, will hit the ceiling of a conversational-first build surface faster than teams doing linear recurring tasks.

Attribute	Nova	Triggered Agents by Adaptive
Pricing	Free	Paid
Price	—	$20/month
Free trial	No	No
Open source	Yes	No
Has API	No	Yes
Self-hosted option	Yes	No
Platforms	Local machine, VPS, terminal, Telegram, Slack, Discord	Web-based with native iOS app
Released	—	2025-04
Pros	Two-phase execution with an explicit approval gate per action category, which means agents that connect to live ad accounts or email cannot publish or spend without you signing off — eliminating the class of 'it already fired' incidents that burn trust in agent tooling. All data — messages, memory, tasks, embeddings — lives in local SQLite computed on your own machine, so teams under data residency requirements or handling sensitive credentials get full perimeter control without building a custom storage layer. Provider-agnostic routing across Claude, Gemini, and Codex CLIs under your own API keys, with rate-limit fallback, so a provider outage or cost spike doesn't halt the operation — you change the route, not the architecture. Playbooks let you author a standard operating procedure once and re-run it with variables, so repeatable multi-step work (campaign launches, onboarding flows) doesn't require a human to re-orchestrate every instance. MIT license with full self-hosted deployment, which means there is no vendor dependency to negotiate and no pricing gate between you and the source code when you need to audit or modify agent behavior.	Plain-language agent creation from existing spreadsheets or documents, so non-technical operators build functional automations without writing a line of code or waiting on a developer. Parallel multi-agent execution, which means a sales outreach workflow and a GitHub update digest run simultaneously without one blocking the other — something a single-agent queue cannot do. Step-level human approval controls, so you sign off on sensitive actions like sending emails or processing payments while the surrounding routine steps run unattended. Connections to Gmail, Stripe, Square, and GitHub out of the box, which means agents pull from and write to the tools a small business already uses rather than requiring a custom integration build. Mobile management via iOS app, so an agent running overnight outreach or morning domain flagging can be reviewed and adjusted without being tied to a desktop.
Cons	The self-hosted-only model requires a working Bun + TypeScript environment before a single agent runs — teams without a developer who can own that setup will stall at installation, not at agent logic, and the absence of a hosted option means there is no fallback path. The 24-agent roster is the ceiling on built-in specialization: when a workflow needs a domain the roster doesn't cover, extending Nova means writing and maintaining custom system prompts with their own tooling and skills — at which point you are building an agent, not using one. Durable multi-day processes that wait on timers or external signatures depend on the self-hosted instance staying live; teams without reliable server infrastructure will lose in-flight processes on restart, and there is no managed persistence layer to absorb that failure. Teams that need a no-code interface for non-technical operators configuring automations will hit a wall immediately — the interface is chat-plus-terminal, and authoring playbooks or wiring connectors requires direct file or config editing; at that point they are evaluating hosted agent platforms with visual builders instead.	Workflows that require branching logic — 'if the lead replied yes, route to calendar; if no, wait three days and try again; if unsubscribe, update the CRM' — hit the limits of a conversational build surface quickly. Teams with more than two or three conditional paths end up describing workarounds to the agent rather than expressing the logic directly, which makes debugging opaque. No self-hosted option exists. Teams operating under data residency regulations, enterprise security policies, or air-gapped network requirements cannot deploy Adaptive at all — at that point they move to a self-hostable alternative like n8n or a custom stack regardless of how well the agent layer fits their workflow. Paid-only features gate the full agent capability for teams on the free tier, which means prototyping a multi-agent workflow and then discovering the parallel execution or advanced integrations require an upgrade — after the build time is already spent.

Bottom line

Nova is free while Triggered Agents by Adaptive is paid; Nova is open source; only Triggered Agents by Adaptive exposes a public API. Choose based on which difference matters most for your workflow.

Frequently asked questions

What is the difference between Nova and Triggered Agents by Adaptive?

Nova is Free and open source, while Triggered Agents by Adaptive is Paid. Compare pricing, free trial, API, platforms, and pros/cons in the table above on AIDiveForge.

Is Nova better than Triggered Agents by Adaptive?

It depends on your workflow. Use the side-by-side attributes (pricing, open source, API, self-hosted, platforms) to decide. AIDiveForge does not rank a universal winner — we publish verified facts so you can choose.