Agent inventory
Decawork keeps a company-wide registry of internal agents so IT can see what is live, who owns it, and what it can reach.
Decawork is an internal AI agent control plane for IT teams. It lets organizations approve agents built in different tools, scope their access, and review every action.
Decawork is an internal AI agent control plane for IT teams. It is designed for organizations where teams build agents in different tools, but IT needs a single place to approve them, control what they can access, and review every action.
The product centers on three controls: each agent gets its own identity, access is scoped to the task, and sensitive or new activity waits for approval before go-live. The site shows Decawork managing a mix of agents across marketing, recruiting, HR, legal, finance, support, engineering, and customer success, which suggests it is meant for company-wide oversight rather than a single department.
Decawork keeps a company-wide registry of internal agents so IT can see what is live, who owns it, and what it can reach.
Each agent has its own identity instead of borrowing a person’s login, with scoped permissions and short-lived credentials for the systems it needs.
Sensitive actions wait for review, and IT approval is required before an agent goes live.
All tool calls are routed through the Decawork gateway and recorded so actions remain attributed to the specific agent that made them.
The interface groups management around agents, access, approvals, audit, integrations, and settings so IT can operate the control plane in one place.
An IT team can review the agents different departments have already launched, see who owns each one, and decide which agents are allowed to stay live.
Security teams can monitor tool calls, inspect attributed logs, and pause or retire agents whose access expires or whose integrations fail.
People ops, recruiting, and HR teams can run internal assistants while keeping credentials scoped and requiring approval before live deployment.
Finance, legal, and support teams can use agents for tasks such as reconciliation, contract review, or escalation handling while keeping sensitive actions reviewable.
Engineering and platform teams can manage build-time and run-time agents across different frameworks while IT keeps a single approval and audit layer.
Decawork is an internal AI agent control plane for IT teams. The source describes it as a way to approve agents built in any tool, control what they can access and do, and see every action.
The trust center says Decawork completed a SOC 2 examination covering Security, Availability, and Confidentiality, and the security page says each agent gets its own identity, scoped access, approval before go-live, and attributed tool calls through the gateway.
The site says Decawork can manage agents built in any tool and shows examples including ChatGPT, Claude, n8n, Microsoft Copilot, Microsoft Agent Framework, OpenAI Agents SDK, LangGraph, CrewAI, Gemini, Cursor, and Codex.
The booking page invites teams to bring an agent they built or agents already running across the company. It positions the demo around IT approving agents, granting scoped access, and reviewing every action.
The pricing page is currently a 404 and redirects visitors back to the home experience and demo booking flow, so the site does not publish pricing details in the collected source.
CreateOS Sandbox is an isolated compute environment for running code and agent workloads inside Firecracker micro-VMs. It is designed for workflows that need machine-level isolation, private networking between sandboxes, and programmatic control through SDK, CLI, or MCP.
AakarDev AI helps teams manage AI provider access, project-level setups, logs, and analytics from one dashboard. It supports BYOK workflows and lists providers including OpenAI, Google Gemini, Anthropic, Groq, Mistral AI, and Perplexity AI.
Trigger.dev chat agent is a durable AI chat backend for developers building stateful conversations that can survive refreshes, crashes, and long-running turns. It connects with the AI SDK `useChat` flow and runs on managed infrastructure with no timeout on a turn.
ByteAsk is a terminal-first AI coding agent for C and C++ that edits repositories and verifies changes with the real compiler, debugger, sanitizers, and tests before showing a diff. It offers a free tier plus paid plans, with editor connectors and zero-retention handling described in the source.
PromptScout tracks how ChatGPT, Gemini, Google AI Overviews, and Perplexity mention your brand or competitors, then pairs those results with source analysis and website audits. It helps teams decide what to fix in content, positioning, or site readiness next.
Sleek Analytics is a privacy-friendly web analytics tool with real-time visitor tracking, Core Web Vitals, and revenue attribution. It helps site owners understand traffic and conversions without cookie banners or a heavy setup.