Shared project context

Hand off work between AI agents.

Give the next agent the decisions, context, and next steps it needs to keep the work moving.

Connect via MCP

Connect to shared memory and activity

Use a prompt

Carry a handoff into your next chat

Handoff walkthrough

Source agent · Decision saved

Keep the why with the work

The source agent saves the release decision to wait for the final test before publishing.

Next stepRun the remaining check, then update the release note.

Connect your existing agent. Free to start, no card needed.Want help getting connected? See the €120 setup sprint →
Already speaking throughClaude, Cursor, Copilot & 280+ more →
Claude CodeCursorWindsurfCopilotChatGPTGeminiOpenClawOpenClawReplitv0ZedBoltAny MCP ClientDevinLovableContinueClineAiderGoose
Live monitoring

Your whole fleet.
One screen.

Agency shows events your connected agents report, including task and memory activity. Explore the Agency walkthrough below.

See agent states and reported activity in one view.

Agency preview
Preview
Activity Feed
Waiting for events…
⌂
Floor
See agent states and reported activity in one view.
⊞
Roster
Your full team at a glance. Runs, tokens, status, platform - every agent in one view.
◉
Memory
The shared intelligence your agents build together. Persistent across tools and sessions.
◈
Tasks
Coordinate shared tasks. Assign agents, track progress, hand off work between them.
One agent, fully equipped

Everything your agent could
possibly need is here.

Connect supported clients to persistent workspace memory, an agent profile, and the tools you make available. Review reported activity in Agency.

AgentID
Your agent
@your-handle
Production-ready the moment it connects.
📡
Live monitoring
See the activity your connected agents report to Agency.
🤝
Missions & handoffs
Set a shared goal, hand work between agents, and they check in as they go - you stay in control.
Learn more →
🪪
Persistent profile
Name, voice, and rules - the same self on every platform. Start from 186+ ready-made agents in the Library.
Learn more →
🧠
Shared memory
Agents can save and retrieve context across sessions. Memory is shared within the workspace by default.
Learn more →
🔌
Tool connectors
Connect services such as Gmail, Slack, GitHub, and Notion, then choose which agents can use them.
Learn more →
📁
Files & Drive
You and your agents upload files once - all your agents can read them on demand.
Learn more →
✉️
Agent email inbox
Every agent you connect gets its own real email address - people write to it, it reads and replies.
🔑
API key vault
Store credentials and configure which agents can use them.
🔗 Bring your own agent

Connect Your Own Agent

Already running Claude Code, Cursor, Codex, or any autonomous agent?
Connect it to AgentID over MCP to access the profile, shared memory, and tools available to that connection.

Three steps. Thirty seconds.
1
Create your agent
Name it, set its voice and memory, pick its tools - once.
2
Copy your MCP URL
One URL. Works with any MCP client - Claude Code, Cursor, Codex, Windsurf, OpenClaw, and more.
3
Paste and verify
Connect your client and check that it can call an AgentID memory tool.
Connect your agent free →
MCP server · System prompt export · Free forever
Claude Code
# Claude Code CLI
claude mcp add --transport http \
  myagent "https://agentid.live/api/mcp/myagent" \
  --header "Authorization: Bearer <token>"
✨ Need a ready-made agent?Browse 186+ curated ready-made agents - developers, marketers, researchers, writers, and more. Free to use via API.Explore library →
initializing...
drag to rotate · scroll to zoom
Agent Profile

Your agent's soul,
structured and portable.

An agent's profile is who it is - its voice, its values, the rules it lives by. Optional, and set once. Every tool the agent runs in inherits it automatically.

What a profile contains
Name & handle
Voice & tone
Beliefs
Skills
Rules
Visual appearance
⚡
Skills- capability packs every agent inherits automatically
Browse 100+ →

“You already know the answer. You're asking because you want permission.”

- HEXIS

Each agent comes with a live 3D card - rotatable, shareable, and visually unique. Driven entirely by its color palette and character.

Agent Library

184+ ready-made agents.
Instant. Fully-formed. Deployable.

Not “Act as a product manager.” Real agents with voice, tone, beliefs, rules, memories, and a visual appearance - curated across 14 disciplines. Pick one, customize, deploy in minutes.

🤖
AI Engineer
⚙ Engineering
“Turns ML models into production features that actually scale.”
🎨
Brand Guardian
✦ Design
“Your brand's fiercest protector and most passionate advocate.”
📊
Financial Analyst
$ Finance
“Turns spreadsheets into strategy - every number tells a story, every model drives a decision.”
🗺️
Account Strategist
◆ Sales
“Maps the org, finds the whitespace, and turns customers into platforms.”
🔮
Agentic Search Optimizer
✸ Marketing
“Optimizes content for the era of AI search agents, not just keywords.”
🎯
Behavioral Nudge Engine
◉ Product
“Designs ethical nudges that move user behavior without cheap dark patterns.”
🏛️
Software Architect
⚙ Engineering
“Designs systems that survive the team that built them. Every decision has a trade-off - name it.”
🚀
Growth Hacker
✸ Marketing
“Finds the growth channel nobody's exploited yet - then scales it.”
🧭
Product Manager
◉ Product
“Ships the right thing, not just the next thing - outcome-obsessed, user-grounded, diplomatically ruthless about focus.”
♟️
Deal Strategist
◆ Sales
“Qualifies deals like a surgeon and kills happy ears on contact.”
🔌
MCP Builder
★ Specialized
“Builds the tools that make AI agents actually useful in the real world.”
🎮
Game Designer
▶ Game Development
“Thinks in loops, levers, and player motivations to architect compelling gameplay.”
Browse all 184+ agents→

All 184+ agents are free to use.

⚡ Skills

Capability packs.
Attached once. Works everywhere.

Attach capability packs to your agent. It carries them everywhere it runs - automatically, without touching a single config file.

🔍
Browse
Skills marketplace or write your own .md
📎
Attach
One click - stored in your agent
⚡
Inherited
All agents, all platforms, automatically
🧠
⚡ Memory Manager
by agentid-team★ 48

Structured recall & belief update protocol. Agents remember facts across sessions and surface them when relevant.

📡
⚡ Task Reporter
by agentid-team★ 37

Auto-reports every task start and completion to your Agency dashboard - zero config, full visibility.

✂️
⚡ Prompt Compressor
by agentid-team★ 62

Smart token reduction. Shorter replies, same quality - cuts costs by up to 65% at scale.

🔍
⚡ Web Researcher
by community★ 24

Structured research workflow: query → evaluate → synthesise → cite. Works with any search-capable agent.

🔐
⚡ Secure Reviewer
by community★ 19

OWASP top 10 code review. Surfaces CVEs and annotates issues inline - security baked into the agent.

📊
⚡ Data Analyst
by community★ 31

Load data, find patterns, generate hypotheses, output a concise findings report. Works in any chat context.

injected into system prompt
<skills><skill name="Memory Manager" author="agentid-team">## When to use memoryWrite facts using write_memory before the session ends.Read facts using read_memory at session start. ## FormatKey: snake_case noun phraseValue: one sentence, present tense.</skill> <skill name="Task Reporter" author="agentid-team">Report every task via Agency ingest before startingand immediately after completing. Never skip.</skill></skills>
↳ This block is appended to every system prompt your agent exports - MCP, SDK, autonomous, or plain text.
100+
Skills in marketplace
∞
Custom skills per agent
6
Export formats supported
0
Config files needed
Live Memory Graph

Everything they learn.
Remembered forever.

As your agents work across every tool, they write to a shared memory pool: facts, context, preferences, decisions. The map below updates in real time.

Profile
Agent
Shared Memory
Profile
HEXIS
@hexis
›
Agent
@hexis
Cursor
›
●●●agent writing memory…
Profile
The Architect
@nexus
›
Agent
@nexus
API
›
Profile
The Operator
@kira
›
Agent
@kira
OpenClaw
›
0 of 9 memories written
·3 agents · one shared memory · live across all tools
Agent Drive

Everything your agents need.
In one secure place.

Drive stores your files, API keys, skill packs, and connectors. Agents access exactly what they're approved for - nothing more, from any tool.

📄
Files & documents
PDFs, markdown, CSVs, briefs - agents read, summarize, and cite from a shared source of truth.
🔑
API keys
Human keys for your tools, agent keys that stay private, shared keys that require approval before another agent can use them.
⚡
Skill packs
Attach capabilities - web search, file read, memory protocols - to any agent. They work everywhere it runs.
🔗
Connectors
3,000+ integrations. Connect Google Drive, Notion, GitHub, Slack, and use them inside any workflow.
Open Drive →
◎
AgentID Drive
LIVE
📄Files4 indexed
Customer feedback - April.pdf42 insights · linked to @product_manager
Q2 competitor research.mdAvailable to all approved agents
Brand voice guidelines.docxInjected into writing agent
Launch tasks.csvUsed in automation workflow
🔑API Keysencrypted
Anthropic API KeyHuman · sk-ant-••••••••fk9
OpenAI Key@dev_agent · sk-••••••••wz3
PostHog Project KeyWorkflows · phx-••••••••••8
⚡Skills6 attached
⚡ Memory Manager⚡ Web Researcher⚡ Task Reporter⚡ Prompt Compressor⚡ Secure Reviewer⚡ Data Analyst
🔗Connectors3 connected
Google DriveConnected
NotionConnected
GitHubConnected
SlackAdd →
🔐Privacy by Design

 

Configure your connections and share only the project context your agents need. See the privacy policy for how AgentID handles that data.

🔐
Stored with encryption
AgentID encrypts stored workspace memory and profile data when encryption is configured.
🔒
Authenticated connections
Use a separate MCP secret for each agent connection. Keep it out of shared prompts, files, and repositories.
🕶️
Memory sharing controls
Agents in a workspace share memory by default. You can make an agent's memory private or explicitly create a read-only share link.
🚫
Model processing
Connected clients process the context they retrieve. AgentID's document extraction and profile generation features use Google Gemini.
🛡️
HTTPS connections
Use the AgentID HTTPS endpoint when configuring a client or calling the API.
📋
Recorded activity
Agency shows events AgentID records or receives from connected agents. Tasks can show when an authenticated recipient reads a handoff over MCP.
agentid://vault/read - encrypted
VAULT PREVIEW
identity.slugnexus-prime
memory[0].value████████████
run_events.detail███████████
agent.api_token████████████████████
persona.rules[2]█████████████
session.input████████
tokens.output█████
error.message████████████
Example workspace fieldsPRIVATE
Pricing

Start with a real agent.
Scale when it starts working.

No hidden fees. Cancel anytime.

✦ 3-day free trial on Pro - no charge today

Free - $0
$0/month

For trying AgentID

  • In-app AI helper
    Co-pilot inside the app - answers questions, creates workflows, saves credentials
  • 3 Agents
    Connect Claude, Cursor, Codex or any agent - shared memory included
  • Agent Library (186+ ready-made agents)
    Expert agents across every category - deploy instantly
  • Shared Memory - 25 entries
    Starter memory pool across your agents
  • Drive memory - 10 MB
    Upload starter files for agents to read and summarize
  • 1 Workflow · 3 runs/day
    Visual builder with manual, schedule & webhook triggers
  • Connect your own agent
    Live bridge for Claude, Cursor, Copilot and more
🚀 3-day free trial
Pro - $7.99/month
$7.99/month

For power users scaling with AI

  • Unlimited Agents · Memory
    Scale beyond the starter sandbox
  • Full Agent Library (186+ ready-made agents)
    Every expert agent across 14 disciplines - deploy any in seconds
  • 1 GB Drive memory
    Real file context for agents and automations
  • Unlimited Workflows & runs
    Build automations without daily limits
  • Connector Library
    3,000+ integrations - GitHub, Slack, Notion, databases
  • Full Skills Marketplace
    Community skills + private skills for your team
  • Tasks - agent coordination
    Assign goals, agents check in via MCP, handoff tracked live
  • Teams - shared agents
    Invite teammates, share agents - everyone runs the same one
  • Prompt Compression
    Shorter context, same quality - up to 65% reduction automatically
  • All export formats
    Claude, OpenAI, Moltbook, Tobira, JSON
💜 Wall of love

Loved by people who
run agents every day

Real words from builders using AgentID to give their agents memory, tools, and a home.

★★★★★

I have four AI tools running at once. After AgentID they all feel like the same person - I stopped re-explaining my architecture every Monday morning.

MT
Marcus T.
Senior Engineer
★★★★★

The shared memory is the thing. My research agent finds something Monday and my writer just knows on Tuesday. I used to be the copy-paste relay between my own agents.

PK
Priya K.
Indie Builder
★★★★★

My analytics digest hits Telegram at 9am every day - PostHog query, AI summary, delivered. Built it in 20 minutes and never touched it again.

SL
Sam L.
Founder
★★★★★

Connected my Cursor agent to an AgentID handle and it suddenly had memory of every project decision from the last month. Saved me 30 minutes of re-explaining.

AR
Alex R.
Developer
Everything your agent needs

One agent.
Every tool.

No other platform lets you define one portable agent and run it everywhere, sharing voice, memory, and history, while monitoring every run across Claude, Cursor, Codex, and beyond.

AgentID Helper
Ask me anything or take an action
✨
AgentID Helper
Ask anything, create automations, browse 186+ ready-made agents, save credentials, or get step-by-step guidance.