loading
Loading content
Agent
A goal in full stride.
Give it a goal. It plans, composes containerized tool nodes into a graph, runs them on managed infrastructure, and queries the results.
Three modes. One visible graph.
Ask for answers, Plan for a reviewable graph, or Agent for end-to-end runs. The conversation and canvas stay in sync.
Scan every host for CVE-2025-53770 and triage the exposed ones.
Reading targets
Applying workflow changes: 5 nodes, 4 connections
$ trickest execute --watch
Presenting report: ToolShell exposure
Message the agent…
Memory you can see.
Mid-conversation, the agent searches vault memory, reads named sections, and writes learnings back to the workflow you are on.
Resume last week's staging recon. What scope and rate limits did we settle on?
Searching memory for "staging recon scope"
searchstaging recon scope3 sections
Reading "staging-recon-scope"
getstaging-recon-scopeproject
Recording a project learning
learnTRICKEST.md
Message the agent…
illustrative · sample memory transcript
Search in the thread
Semantic recall shows up as Memory tool calls in the chat timeline, next to every other action.
Learn on the workflow
Each graph keeps a project file: purpose, learnings, known issues. The next session starts informed.
Stays in your vault
Per-vault memory persists across sessions. Scope, constraints, and context survive the next chat.
Control you keep.
Authority to act never means acting unobserved. The graph stays yours to review, edit, govern, and inspect.
Reviewable
Every plan and workflow is visible before it runs. Plan mode proposes; nothing executes until you approve it.
Editable
The graph the agent builds is the same graph you can edit. Inspect a node, swap a module, or rewind a step.
Governed
Work runs in your own vault. Per-vault memory and access stay scoped to that workspace.
Inspectable
Every step logs its inputs, outputs, and duration. Runs are versioned, so you act on what changed.
Give the agent your team's expertise
Skills are playbooks the agent works from. It ships with offensive security methods and learns how your team operates.
API Testing
v1.0.0Test and validate APIs using Hurl (declarative HTTP tests), Newman (Postman collections), and grpcurl (gRPC testing).
App Builder
v4.1.0Build production-grade Next.js apps in the sandbox over live workflow data.
Audio Processing
v1.0.0Process audio files — convert formats, normalize loudness, trim, merge, apply effects, and encode using SoX, LAME, FLAC, Opus, and FFmpeg.
Cloud Enumeration
v1.0.0Enumerate and audit cloud infrastructure assets across AWS, GCP, and Azure.
Cluster: Bridges Reports
v1.0.0Cross-solution data bridges, reporting, and utility tools in Trickest workflows.
Cluster: Content Discovery
v1.0.0URL/path discovery and JavaScript analysis modules in Trickest workflows.
Cluster: Hostname Enumeration
v1.0.0Build the hostname/subdomain discovery side of a Trickest workflow.
Cluster: Network Scanning
v1.0.0Network-side vulnerability scanners in Trickest workflows.
Cluster: Port Services
v1.0.0Port discovery and network service fingerprinting in Trickest workflows.
Explore the platform
Adjacent surfaces on the same engine. Pick the next cut of the stack.
Get a personalized demo
See Trickest in Action
A 30-minute walkthrough. We map the platform to your stack and answer pricing and deployment questions for your environment.