Get This Tool
Nova
Pricing
- Model
- Free
Summary
Most automation tools that touch your email, calendar, and ad accounts treat the 'are you sure?' step as an afterthought — a confirm dialog that ships with the first version and breaks in the third. Nova is a self-hosted agent team built around the opposite assumption: nothing consequential executes until you approve it.
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.
Bottom line: Nova earns its place when your operation needs agents that touch live accounts but you cannot hand credentials to a SaaS — and it shows its limits the moment you need an agent type the 24-specialist roster doesn't include and you aren't ready to write one.
Community Performance Report Card
No community ratings yet. Be the first to rate this tool!
Community Benchmarks Community
Sign in to submit a benchmarkNo community benchmarks yet. Be the first to share a real-world data point.
Pros
Sign in to edit- 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.
Cons
Sign in to edit- 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.
Community Reviews
Sign in to write a reviewNo reviews yet. Be the first to share your experience.
About
- Platforms
- Local machine, VPS, terminal, Telegram, Slack, Discord
- API Available
- No
- Self-Hosted
- Yes
- Last Updated
- 2026-07-26T04:18:08.304Z
Best For
Who it's for
- Teams needing self-hosted agentic workflows
- Operations with approval requirements for actions
- Users wanting local data and custom models
What it does well
- Marketing campaign launch with landing pages, emails, and ads
- Event-driven business automations via webhooks and connectors
- Document extraction and structured data processing
- Multi-agent board deliberations for strategic decisions
Integrations
Discussion Community
Sign in to commentNo discussion yet. Sign in to start the conversation.
Spotted incorrect or missing data? Join our community of contributors.
Sign Up to ContributeCommunity Notes & Tips Community
Sign in to contributeBe the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.
Frequently Asked Questions
- Is Nova free?
- Yes — Nova is fully free to use. There is no paid tier.
- Is Nova open source?
- Yes. Nova is open source.
- Can I self-host Nova?
- Yes. Nova supports self-hosting on your own infrastructure.
- What platforms does Nova support?
- Nova is available on: Local machine, VPS, terminal, Telegram, Slack, Discord.
Hours Saved & ROI Stories Community
Sign in to contributeBe the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."
Curated lists that include this category
The pitch for AI agents usually dissolves the first time one fires off an email without asking. Nova’s entire architecture is a response to that failure: 24 specialist agents backed by an automation layer that reacts to webhooks, connector events, and metrics, but holds every consequential action — publishing, sending, spending — behind an explicit approval card (Approve, Revise, or Cancel) delivered to wherever you chat: Telegram, Slack, Discord, or terminal. Classification runs cheapest-first, with a pattern cache for repeat requests so only genuinely new complex asks pay for LLM classification. Complex requests decompose into subtasks with dependency order, independent branches run in parallel, and the full plan is visible before execution begins.
The trust model is the feature that sets Nova apart from workflow tools that bolt on permissions later. OAuth tokens are AES-256-GCM encrypted at rest, webhook signatures are verified, and every consequential action lands in an audit ledger. Spend caps, approval matrices, and PII checks are described as first-class policy objects — not settings buried in a config file. Embeddings are computed locally, and the data never leaves the machine. For teams that must keep credentials and message history inside their own perimeter, this is the architectural foundation that makes that possible without a major DIY build.
Nova fits operations that run repeatable work — marketing campaign launches, document extraction pipelines, multi-day approval flows — where the person in charge wants agents doing the preparation and humans signing off before anything ships. The connector list (Stripe, Shopify, Zendesk, HubSpot) covers common business stacks. The ceiling appears at customization: the 24-agent roster is fixed outside of writing new system prompts, the stack is Bun + TypeScript which limits who can extend it without friction, and there is no hosted option, so every deployment is a self-managed infrastructure decision. Teams that need a specialist the roster doesn’t include, or who want managed hosting, will be building or moving before the first sprint ends.