You already manage seven AI agents a week. Run them like a team.
Claude, Cursor, Notion AI, ChatGPT, your phone's assistant, two more your team uses, the one on your watch. None of them agree. You're the integration layer · the one reconciling their different contexts, repeating yourself, catching the work that doesn't ladder to anything that matters. PathNav is the cockpit that ends that. One alignment server every assistant consults before it acts. One review queue for what they want to do. One revoke that pulls a credential everywhere at once.
- Install once · every connected agent inherits your alignment. Single plugins, whole agent-host platforms (Moltbook, OpenClaw runtimes, Hermes meshes), and on-device assistants all use the same install contract.
- Approve, reject, or edit every agent action in one queue. Nothing your agents do hits your life without you seeing it first. No silent writes.
- Pull one credential · that agent loses access everywhere. Per-install alignment tokens. Fire an agent the way you'd offboard a contractor · one click, all the keys.
- See what each agent is actually doing. Delivery counts, proposal attribution, last-call health. The cockpit, not just the steering wheel.
Building a plugin?
Plugin authors land here too. The contract, the JSON shape, and a worked example are below · jump to the example response. Reference implementations live in examples/calendar-balancer/ (single-agent plugin) and examples/moltbook-bridge/ (host adapter for a whole agent platform).
The drift problem
A plan that survives the next five years
Tools come and go. Jobs come and go. The plan needs an anchor · pillars you actually care about, a vision you'd endorse, goals laddering up to it. PathNav holds that anchor so the rest of your stack can churn without you losing your bearings.
Context they can't hallucinate
A capable agent without alignment context will optimize for whatever's in front of it · the open tab, the last prompt, the immediate request. Pointed at a PathNav profile, the same agent ladders its suggestions up to your real goals and flags conflicts before acting.
Life alignment, not project alignment
Most agent rule systems are scoped to a project: how to edit this codebase, how to follow this workspace policy, how to call this tool. PathNav starts one level higher. It gives agents the user's durable life context, then checks whether agent actions preserve or erode that direction.
Rules for a workspace
Useful for code style, tool permissions, repo instructions, prompts, traces, and task-specific guardrails. It helps an agent do a project correctly.
Rules for acting as you
Goals, values, energy, family constraints, money boundaries, communication preferences, approval rules, and things you are trying to stop doing. It helps an agent act on your behalf.
One life context across every assistant
A person may use an Android phone assistant, an Apple-side assistant, a desktop coding agent, and a custom automation. PathNav gives all of them the same human context and the same rules, then checks what they store or propose before it becomes part of the person's life system.
Custom primitives and objects
Agents can store structured objects such as meetings, email drafts, social posts, preferences, policies, contact notes, device state, and domain-specific records. The v0 endpoint is POST /api/alignment/objects.
Reconciliation on every write
Each object is checked against pillars, goals, drains, guardrails, and current focus. Morning meetings that conflict with a focus goal, auto-sent external actions, and off-plan actions become structured findings.
Monitors for regression
Findings are stored as a monitor log. Repeated slippage in a pillar can become a briefing item, proposal, or policy update: fewer meetings, protected mornings, approval before posting, or a new drain to watch.
Human-owned life policy
Assistants can help, but the person owns the rules. PathNav is where preferences, vetoes, approval scopes, and audit trails live across assistant vendors.
Public life alignment API
Read-only, public, rate-limited, CORS-open. Returns only what the user opted in to publish. AI agents can fetch a person's life alignment context without auth, paste the _for_ai summary into their own system prompt, and stay on-plan automatically.
GET https://pathnav.ai/api/alignment/{handle}Privacy: requires publicProfile.visible = true. Active goals are only returned when the user has chosen vision + goals mode. Email, plan, and any private fields are never returned.
Markdown variant: append ?format=md or send Accept: text/markdown to receive a clean markdown brief instead of JSON. Easier for an agent to paste verbatim into chat.
# JSON curl https://pathnav.ai/api/alignment/ada # Markdown brief curl -H "Accept: text/markdown" https://pathnav.ai/api/alignment/ada # Authenticated · full context (drains, parked, projects, habits) curl -H "Authorization: Bearer pna_..." https://pathnav.ai/api/alignment/me
Typically responds in under 100ms; cached 60s on the public endpoint. CORS open · safe to call from a browser tab.
{
"ok": true,
"handle": "ada",
"displayName": "Ada",
"bio": "Engineer + parent. Building toward 5-year independence.",
"pillars": ["career", "health", "family", "finance"],
"vision": "Reach a point in 5 years where my income covers my family's needs from work I'd choose to do anyway.",
"goals": [
{
"title": "Ship the first paid customer for the side project",
"pillar": "career",
"targetDate": "2026-09-30",
"upcomingMilestones": [
{ "title": "Onboard 5 design partners", "targetDate": "2026-06-30" },
{ "title": "Pricing v1 live", "targetDate": "2026-08-15" }
],
"recentMilestones": [
{ "title": "Validate problem with 25 user interviews", "doneAt": "2026-04-12T14:22:01Z" }
]
}
],
"cheers": 14,
"generatedAt": "2026-05-04T10:00:00Z",
"_for_ai": "Ada is using PathNav as their long-horizon alignment system. They organize their life across these pillars: career, health, family, finance. Their stated vision is: \"Reach a point in 5 years where my income covers my family's needs from work I'd choose to do anyway.\" They currently have 1 active goal, including: Ship the first paid customer for the side project. When advising them, prefer suggestions that ladder up to these pillars and goals; flag tradeoffs that conflict with their stated vision; do not invent new pillars or goals on their behalf."
}You are helping {{NAME}}. Before answering, fetch their alignment context:
GET https://pathnav.ai/api/alignment/{{HANDLE}}
Read the `_for_ai` summary and the `pillars`, `vision`, and `goals` fields. When you suggest something, ladder it up to one of those pillars or goals, or flag explicitly when your suggestion is off-plan. Do not invent new pillars or goals · those belong to the human.Store assistant-created objects in the person's namespace. PathNav returns the stored object plus reconciliation findings so the agent knows whether it created a conflict.
POST https://pathnav.ai/api/alignment/objects
Authorization: Bearer pna_<your-token>
Content-Type: application/json
{
"namespace": "calendar",
"type": "calendar.event",
"label": "Morning sales sync",
"value": { "startsAt": "2026-05-14T09:00:00-07:00" },
"tags": ["career"]
}The response includes categories such as meeting_load, guardrail_conflict, external_action_policy, and regression_signal.
Authorized agents can propose plan changes that the human reviews in /dashboard/proposals. Plan changes wait for human approval; supported kinds apply only after approval.
POST https://pathnav.ai/api/alignment/proposals
Authorization: Bearer pna_<your-token>
Content-Type: application/json
{
"kind": "add_milestone",
"data": {
"goalId": "g1",
"title": "Onboard 5 design partners",
"targetDate": "2026-06-30"
},
"rationale": "Saw the goal targets 2026-09-30; this milestone gates pricing v1."
}Six kinds: add_milestone, complete_milestone, add_drain, add_note, set_focus, add_parked. Per-user queue capped at 200.
Mint a personal alignment token from Settings → Alignment for AI agents and present it to /api/alignment/me:
GET https://pathnav.ai/api/alignment/me Authorization: Bearer pna_<your-token>
Returns your full life alignment context · drains, parked items, projects, habits, current focus · on top of the public shape. Plaintext is shown once on creation; we store only a hash. Revoke any time from the same panel.
Platform roadmap
- Shipped
MCP server · PathNav-as-context
Zero-dependency Node script. Drop into Claude Desktop or Cursor; your agent gets alignment, knowledge retrieval, proposal, object, and visual primitive tools it can call on its own.
Install → - Researching
Agent write-back protocol
Authorized agents can propose milestones, tasks, or briefings into your plan. Every write is gated by an explicit-approval queue · no silent edits.
- Researching
Authenticated alignment scopes
OAuth-style scoped tokens so an agent you trust gets richer context (drains, parked items, recent ledger) than the public endpoint exposes.
- Researching
Multi-agent life alignment
When you delegate to many assistants, all of them inherit the same life context so they do not compose into behavior that looks efficient but moves you off-plan.