AI does the work
Your team stays in control

Claude Code, Codex, or any agent — give it an inbox, tools, memory, and a budget.It does real business work, and every sensitive action waits for your team's approval.

Works with

Claude Code

Codex

OpenClaw

Hermes

Any service through unified credits

Hunter.io

Affinity CRM

Salesforce

HubSpot

Pipedrive

Gmail

Outlook

Slack

Notion

Crunchbase

Apollo

Clearbit

Specter

Google Analytics

Stripe

GitHub

Google Calendar

Hunter.io

Affinity CRM

Salesforce

HubSpot

Pipedrive

Gmail

Outlook

Slack

Notion

Crunchbase

Apollo

Clearbit

Specter

Google Analytics

Stripe

GitHub

Google Calendar

Twitter/X

Medium

WordPress

Zapier

Webhooks

HTTP/REST

Google Sheets

Airtable

Microsoft Teams

Google Trends

Web Scraper

Puppeteer

Claude AI

GPT

Gemini

Mistral

DeepSeek

Composio

Twitter/X

Medium

WordPress

Zapier

Webhooks

HTTP/REST

Google Sheets

Airtable

Microsoft Teams

Google Trends

Web Scraper

Puppeteer

Claude AI

GPT

Gemini

Mistral

DeepSeek

Composio

From goal to result

Your agent turns goals into results you can review

agentled.app / Lead Generation

Lead Generation

Active

Owner: Lead Research Agent
Updated: Just now

Open

Goal

Build a reviewable list of 5 AI operations companies in Spain.

Next action

Review 3 qualified leads before preparing outreach.

Find
Complete
Qualify
Current
Prepare
Upcoming
Operate
Upcoming

Leads

Company	Status	Next action
Northstar Ops	Replied	Review reply
Juniper Labs	Contacted	Await reply
Orbit Systems	New	Qualify
Relay Works	Qualified	Review outreach draft
Cedar AI	New	Qualify

Northstar Ops

Review reply

Replied

Provider
CRM

Juniper Labs

Await reply

Contacted

Provider
CRM

Orbit Systems

Qualify

New

Provider
CRM

Relay Works

Review outreach draft

Qualified

Provider
CRM

Cedar AI

Qualify

New

Provider
CRM

Side by side

Your agent alone vs.
your agent + AgentLed.

Your AI agent can reason, code, and plan. AgentLed gives it the working layer: managed agents, email and team channels, any service it needs, durable memory, supervised workflows, approvals, monitoring, and ROI.

Capability	Agent alone	Agent + AgentLed
Tools, channels, and credits	Your agent can suggest the workflow, but you still assemble API keys, auth, rate limits, subscriptions, and vendor bills.	Any service your agent needs through one credit pool, one workspace, and one bill.
Managed agents and workflows	The agent writes scripts or drafts. Agent identity, inboxes, schedules, retries, state, and handoff remain your problem.	The agent deploys managed agents and supervised workflows with cache, retries, approvals, and managed heartbeats.
Business memory	Context windows reset. The agent loses ICP rules, scoring rubrics, prior approvals, and outcomes.	Knowledge Graph stores entities, scores, approvals, decisions, and outcomes across every run.
Channels	Drafts, Slack alerts, WhatsApp follow-up, and customer threads stay scattered across tools.	Agent inbox, agent email, Slack/WhatsApp notifications, and customer-facing handoff live in the workspace.
Approvals	Approvals happen in chat. No durable record of who approved what or why.	Approval queues pause sensitive actions before sends, CRM updates, publishing, or customer-facing work.
Monitoring	Terminal logs. You become the audit trail and reconstruct failures manually.	Run history, step inputs/outputs, exceptions, credit use, and owner actions are traceable.
ROI portal	ROI is a spreadsheet you update later, detached from the workflow runs.	Portal shows credits, tokens, hours saved, cost avoided, pipeline influenced, and review outcomes.

Read the CLI docs

How It Works

Connect your agent.
Give it a real job.

Connect

Install AgentLed in Claude Code, Codex, or any MCP agent.

Set the goal

Describe the outcome. AgentLed builds and runs the workflow.

Approve & improve

Review sensitive actions. Feedback becomes memory.

Agent channels

Your agent gets an inbox, an email address, and a seat in your channels.

Give agents managed channels for replies, alerts, and handoffs. Every email, Slack alert, and WhatsApp escalation stays attached to the workflow run that created it.

agentled.app / agent inbox

Growth Agent

growth@company.agentled.ai

agent@company.agentled.ai

3 replies need review

Slack

#sales-ops

Daily run summary posted

Agency owner alerts

Qualified reply escalated

Unified agent inbox

Live

Founder reply

Asked for revised pricing after SEO preview

Owner review

Slack alert

Outbound workflow found 5 high-intent accounts

Auto-posted

WhatsApp note

Client approved full GBP report

Create task

agentled.app / approvals and ROI

Approval queue

Send 12 personalized founder follow-ups

Email · waits for owner

Approve

Update CRM stage for 5 qualified accounts

HubSpot · waits for owner

Review

Low-confidence investor fit score

Deal flow · waits for owner

Escalate

Deployment ROI

Hours saved

Cost avoided

$12.4K

Pipeline influenced

$38K

Approval rate

91%

Approvals, monitoring, ROI

Let agents act, but keep the business in control.

Sensitive actions pause before they hit customers or systems of record. Owners approve, exceptions are tracked, and ROI stays visible from the same portal.

What Teams Build

Teams are building managed agents with AgentLed.

Examples of managed agent workflows being built and deployed with AgentLed. The agent gets the goal; AgentLed supplies managed agents, workflow runtime, tools, memory, approvals, monitoring, and the ROI portal.

Inovexus — VC Managed Agents

inovexus.com

Client goal

“Help our investment team source, score, and match companies with the right investors or mentors while the system remembers every decision.”

Workflow deployed

Inovexus is deploying managed AI agents with AgentLed to support startup sourcing and investor matching. Agents monitor deal channels, score companies against the investment thesis, recommend relevant investors or mentors, and generate approval-ready reports so the team keeps control while every decision is remembered.

Outcome

Pilot deployment in progress across startup sourcing, thesis-based scoring, investor recommendations, and approval-ready reports.

Managed agents being deployedInvestor recommendations with memoryApproval-ready reports

Connected tools

affinitylinkedinspectermistralknowledge-graphemailweb-search

Agwanet — Agency SEO Workflow

agwanet.com

Client goal

“Turn our local SEO consulting offer into a repeatable Google Business Profile lead-gen workflow.”

Workflow deployed

Agwanet used the AgentLed CLI to build and run a Google Business Profile lead-gen workflow for local-business SEO leads. The agent generates a preview report, queues teaser outreach, gates the full report after payment, and creates an upsell path into the agency's SEO services. Agwanet is now connecting AgentLed into Hermes so its own agent can deploy new AI integrations, trigger SEO workflows, and monitor results.

Outcome

First workflow running in one day, with payment-gated reports and an upsell path into agency services.

First workflow live in one dayGoogle Business Profile lead-gen workflowHermes integration started

Connected tools

hermesgoogle-business-profileemailwhatsappknowledge-graphwhite-label

These are two examples. More clients are building custom AgentLed deployments with connected tools, private data, approval gates, and integrations across their existing stack.

CLI + credits

One CLI install. One credit budget.

Install AgentLed once and your agent can spend credits on research, models, extraction, public forms, reports, and Knowledge Graph memory. Start with 300 free credits; Pro and higher add durable workspace memory and monthly credit tiers.

Capability	Credits	What you'd need otherwise
Connect Claude Code, Codex, or MCP agent	0	Manual MCP config and auth
Research an account or lead list	3–10	LinkedIn, data APIs, spreadsheets
Draft approval-ready emails or replies	10–30	OpenAI / Claude API billing
Inspect or extract from a website	3–10	Apify / Firecrawl setup
Public form intake for new jobs	Included	Typeform plus webhook glue
Generate a client-facing report	10–40	Docs, dashboard, and reporting stack
Knowledge Graph memory read/write (Pro+)	1–2	Custom database and retrieval logic

Usage transparency

Prioritize tokens for high-ROI work.

Every run is attributed by model, app, workflow step, and agent so teams can allocate monthly-plan credits against hours saved, operating cost avoided, or revenue unlocked.

Plan credits allocated

8,420

Runs

126

agentled.app / usage attribution

Token drivers · Current refresh cycle · Jun 1-Jul 1, 2026

ROI view: 84 hours saved · $12.4K cost avoided · $38K pipeline influenced

Models

GPT-5.5

openai

2,380 cr · 74 runs

Claude Opus

anthropic

1,840 cr · 31 runs

Gemini 3 Pro

google

940 cr · 52 runs

Mistral Small 4

mistral

280 cr · 9 runs

Apps with attribution

Profile enrichment

1,260 cr · 42 runs

Firecrawl

Web extraction

890 cr · 36 runs

Personal follow-up

520 cr · 28 runs

KG Memory

Read and update

410 cr · 96 runs

Steps

Match ICP

Account fit

1,680 cr · 18 runs

Read Signals

Recent context

1,320 cr · 42 runs

Write Touch

Personalized

980 cr · 34 runs

Save Memory

Next action

620 cr · 32 runs

Agents

Warm ICP SEO

Finds best-fit leads

1,480 cr · 16 runs

Signal Scout

Reads buying triggers

1,120 cr · 24 runs

Content Manager

Writes 1:1 assets

760 cr · 18 runs

Reengagement Lead

Remembers next step

520 cr · 37 runs

Free credits are for first supervised runs. Pro includes Knowledge Graph memory; plan limits come from credit volume, workspaces, members, snapshots, and support level.

Knowledge Graph

Agents that remember,
learn, and improve.

Your agent uses workflows behind the scenes — and persistent memory to get smarter over time. Two layers:

◆

Business-level memory— company context, ICP definitions, scoring models, workflow outcomes. Shared across all workflows and users. One workflow learns it, every workflow benefits.

◆

User-level context— individual preferences, conversation history, personal patterns. Your agent remembers how you work, not just what the company knows.

Not just automation — a system that gets smarter with every run.

Learn more about Knowledge Graph

Knowledge Graph

847 entities · 2,340 relationships

Live

Recent Activity

Scored 43 investors — DMF avg 7.22m ago

IC outcome: prediction matched 89%1h ago

12 new leads enriched + stored3h ago

Sector feedback updated (fintech)6h ago

Compound Learning

Run 1

62%

Run 5

78%

Run 12

89%

Investor scoring accuracy improving with each execution

	n8n / Zapier	AgentLed
Remembers last run	✗	✓
Cross-workflow memory	✗	✓
Compound scoring	✗	✓
Prediction vs outcome	✗	✓
Learns from results	✗	✓
One API key for any service	✗	✓

Every other tool starts from zero.

n8n runs the same workflow with no memory of previous results. Custom scripts need you to build and maintain your own database.

AgentLed's Knowledge Graph stores every insight, score, and outcome automatically. Each run compounds on the last. After 12 runs, our investor scoring went from 62% to 89% accuracy — with zero manual tuning.

See how it works

Managed agents that keep working.

NEW — Agent orchestration

Define the agent, give it email and team channels, connect tools, and set the approval rules. It can run on demand or on a heartbeat, then bring customer-facing actions back to your team before anything sensitive ships.

AGENTS.md→SOUL.md→Tools→Workflows→Heartbeat

Deal Sourcing Agent

Human-supervised · heartbeat: every 48h

Running — 3 workflows

Connected workflows

✓ deal-sourcing-specter
✓ deal-sourcing-linkedin
✓ daily-deal-flow

Agent chat

Agent

Found 8 new deals this week. 2 need your review.

CLI-started jobs

Example jobs.
Start from the CLI.

Ask your agent to start from a job template, then change the steps, approvals, forms, and outputs until it fits your business.

Lead research + CRM update

Research accounts, find contacts, draft outreach, and prepare CRM updates for approval.

Try this template

Public form → agent job

Turn a submitted form into a researched brief, next steps, and an approval-ready output.

Try this template

Google Business Profile audit

Analyze a local business, generate a preview report, and queue follow-up.

Try this template

Inbox triage & reply drafts

Classify, prioritise, and draft replies for incoming emails.

Try this template

Competitor and pricing monitor

Track website changes, pricing pages, and market updates with a weekly digest.

Try this template

Client report builder

Pull research, summarize findings, and publish a white-label report for review.

Try this template

FAQ

Questions teams ask before starting

What is AgentLed?

AgentLed gives Claude Code, Codex, Hermes, OpenClaw, or any MCP agent a managed workspace: CLI setup, email and chat channels, tools, credits, approvals, memory, monitoring, and client-ready outputs.

How do I connect my agent?

Run npx @agentled/cli setup or copy the install prompt from the homepage into your agent. It connects AgentLed to Claude Code, Codex, Hermes, OpenClaw, Cursor, Windsurf, or any MCP-compatible client.

What can I run with 300 free credits?

They let you connect an agent and run first supervised jobs before adding a paid plan. Credits are the budget your agent spends on model calls, enrichment, web extraction, report generation, and memory actions.

What does AgentLed remember for my agent?

No. Knowledge Graph memory is available on Pro and higher. Pro is limited by one workspace, two members, two snapshots per workflow, and the selected monthly credit tier; Teams adds more workspaces, unlimited members, more snapshots, and priority support.

Do I have to approve every action?

No. You set the rules: routine research, drafts, enrichment, and checks can run without review; trusted repeat sends can use delegated approval; sensitive or exceptional actions pause for a human.

Can this support client-facing workflows?

Yes. AgentLed can expose public intake forms, approval-ready outputs, and white-label client reports or portals. Advanced branding, domains, SLA, and rollout support live in higher plans.

How much does AgentLed cost?

Start with 300 free credits. Pro starts at €23.90/month for 2,000 credits and includes CLI/MCP access and Knowledge Graph memory. Teams starts at €86.90/month for 7,000 credits with unlimited members. Custom adds enterprise controls and delivery support.

Put your agent to work. Your team stays in control.

Start with 300 free credits.

Get started free

AI does the workYour team stays in control

Your agent turns goals into results you can review

Leads

Northstar Ops

Juniper Labs

Orbit Systems

Relay Works

Cedar AI

Your agent alone vs.your agent + AgentLed.

Connect your agent.Give it a real job.

Connect

Set the goal

Approve & improve

Your agent gets an inbox, an email address, and a seat in your channels.

Let agents act, but keep the business in control.

Teams are building managed agents with AgentLed.

Inovexus — VC Managed Agents

Agwanet — Agency SEO Workflow

One CLI install. One credit budget.

Prioritize tokens for high-ROI work.

Models

Apps with attribution

Steps

Agents

Agents that remember,learn, and improve.

Every other tool starts from zero.

Managed agents that keep working.

Example jobs.Start from the CLI.

Lead research + CRM update

Public form → agent job

Google Business Profile audit

Inbox triage & reply drafts

Competitor and pricing monitor

Client report builder

Questions teams ask before starting

Put your agent to work. Your team stays in control.

AI does the work
Your team stays in control

Your agent alone vs.
your agent + AgentLed.

Connect your agent.
Give it a real job.

Agents that remember,
learn, and improve.

Example jobs.
Start from the CLI.