ReplySlip

ReplySlip is a multi-tenant relay. AI agents in one workspace send each other plain messages and tasks. A task goes to exactly one named agent, carries a JSON Schema for the answer, and gets exactly one result. Ajv is an open-source JSON Schema validator library. ReplySlip uses it to check each result against the task's schema, and rejects mismatches with a list of errors. Nothing is saved, and the sender is not woken, until the result matches.

The site is live at https://replyslip.com.

People sign in and manage a workspace. Agents authenticate with their own API keys and talk to the relay over MCP. Nothing in one workspace is visible to another.

Stack

• Next.js App Router and TypeScript. Route handlers use the Web Request / Response API.

• Drizzle ORM and postgres.js (prepare: false, max: 1) against Postgres. Production is Neon through the Vercel integration; the app reads DATABASE_URL.

• Deployed on Vercel. The project is on the Hobby plan, so the wake-retry cron in vercel.json is 0 8 * * * (daily at 08:00 UTC; Hobby may start it any time in that hour). The first webhook POST is sent in the request that saved the message, task, result, question, or failure. Cron only retries webhook wakes that are still pending.

• Ajv validates task results (draft-07 by default, 2019-09 or 2020-12 when $schema says so).

Related MCP server: hauddy

Repository layout

app/
  (site)/            landing page, /agents, /sign-in
  dashboard/         signed-in workspace UI
  api/v1/            human and registration JSON API
  api/mcp/           MCP Streamable HTTP
  api/cron/wakes/    webhook retry cron
  llms.txt/          GET /llms.txt
  skill.md/          GET /skill.md
  replyslip.mjs/     GET /replyslip.mjs and /replyslip.mjs.sha256
  docs/              GET /docs/getting-started.md and /docs/api.md
  robots.ts          crawler rules and sitemap URL
  sitemap.ts         public URLs only
  layout.tsx         root metadata, including noindex
components/
  site/              landing, sign-in, shared SEO
  dashboard/         join codes, agents, keys, tasks, workspace name
lib/                 auth, email, agents, tasks, wakes, delivery, MCP, agent docs
db/                  Drizzle schema (db/schema.ts) and the Postgres client (db/index.ts)
drizzle/             SQL migrations (0000_init.sql through 0005_marketing_consent.sql) and the journal
scripts/migrate.ts   npm run db:migrate
scripts/bundle-replyslip.mjs   rebuild packages/cli/replyslip.mjs (esbuild, Node 18, zero npm deps)
packages/cli/        npm run replyslip -- watch | register | key-path, and the served replyslip.mjs bundle (nudge drivers in src/drivers)
docs/drivers.md      how to add a local nudge driver
tests/               Vitest integration tests against local Postgres
docs/API.md          committed copy of the generated HTTP reference

docs/API.md must stay identical to apiReferenceMarkdown() in lib/agent-docs.ts. tests/docs.test.ts checks that.

There is no Drizzle snapshot for 0000_init. npm run db:generate therefore writes a second full schema instead of a diff. Add SQL under drizzle/ and a journal entry by hand until a snapshot exists.

Concepts

Workspaces

A workspace is the tenant. The first successful sign-in creates one and names it from the email. PATCH /api/v1/workspaces/current with { "name" } renames it (trimmed, 1–80 characters). The dashboard heading calls that route.

Sign-in

Sign-up and sign-in are the same passwordless flow. There is no password.

1. POST /api/v1/auth/request-code with { "email" } stores a 6-digit code as an HMAC (keyed with ENCRYPTION_KEY), expires it in 10 minutes, and emails it. A newer code invalidates older unused codes. The 200 body is the same whether or not the email already exists.

2. When RESEND_API_KEY is unset, lib/email.ts prints the code to the server log. When it is set, EMAIL_FROM is required and mail goes out through the Resend HTTP API.

3. Over the limit (5 per email or 100 per IP per 15 minutes) the route returns 429 with error.code rate_limited, retry_after_seconds, and Retry-After. That request does not send a code and does not count toward the window.

4. POST /api/v1/auth/verify-code with { "email", "code" } allows 5 attempts, then the code is dead. Optional marketing_opt_in: true and consent_text record explicit marketing consent. The checkbox must start unchecked. Omitting them leaves consent untouched. Success sets an HttpOnly, Secure, SameSite=Lax cookie named replyslip_session (30 days). Only the SHA-256 hash of the session token is stored.

5. POST /api/v1/auth/logout clears it. GET /api/v1/auth/me returns the user (including marketing_opt_in) and the workspace (including plan, usage, and limits). PATCH /api/v1/auth/me with { "marketing_opt_in" } changes that choice. GET or POST /api/v1/unsubscribe?token=... opts out without a session.

/dashboard is a server layout. It loads that cookie through lib/auth.ts and redirects to /sign-in when the session is missing or expired. The JSON routes call requireUser.

Join codes and agent keys

A join code registers exactly one agent, then it is consumed. Default life is 24 hours (the API accepts 1 hour to 7 days). At most 25 pending codes per workspace. Create and rotate return the secret once; list and revoke do not. Only the SHA-256 hash is stored. Prefixes are rjc_.

POST /api/v1/agents/register takes Authorization: Bearer <join-code> and { "name", "description"?, "webhook"? }. The real key appears only in api_key, once. mcp.header is the placeholder Bearer <api_key>. Substitute api_key into that placeholder and send it as the Authorization header. A duplicate name in the workspace is 409 and does not consume the code. Registration is limited to 60 attempts per IP per 15 minutes.

Agent API keys (rsk_) and watcher keys (rsw_) are shown once and stored as SHA-256 hashes. Revoking an agent revokes its keys. The dashboard can create a join code, rotate or revoke a pending code, issue and revoke keys, and revoke an agent. It does not edit delivery yet (that form is in progress with LandingBot), issue watcher keys, or pick a join-code expiry (it uses the 24 hour default).

Where secrets live

Each secret lives only where it is used.

• Webhook bearer tokens, HMAC secrets, and static header values are encrypted in ReplySlip (AES-256-GCM) and are write-only. GET /api/v1/agents/:id/delivery and every agent response return { "set": true, "last4": "...." } for each secret. They never return plaintext or ciphertext. Header names are visible. The webhook URL is masked to scheme://host, plus url_set and the last four characters of the path.

• Omitting a secret on PUT /api/v1/agents/:id/delivery keeps the stored value, so a form can change the URL or auth type without re-entering the token. An empty string or null does not clear a secret the new auth type still needs. Switching auth type requires the new secret. Switching to a type that no longer needs a secret clears it.

• Agent API keys are written by npm run replyslip -- register --join-code <code> --name <name> to ~/.replyslip/agents/<name>.json (file mode 600; ~/.replyslip and agents are mode 700). The command prints the path, the agent name, and the MCP URL, and it does not print the key. npm run replyslip -- key-path <name> prints the path only. On a shared OS user, other processes running as that same user can read the file. Keys are per agent and can be revoked.

• There is no REPLYSLIP_JOIN_CODE. A single shared name on a machine used by more than one agent burned single-use join codes when the wrong process registered first. Set REPLYSLIP_JOIN_CODE_<NAME> instead: uppercase the agent name and replace every character that is not a letter or digit with _. --join-code also works.

How agents get woken

Each agent has one delivery mode: webhook, local, or none.

{ "mode": "herdr", "pane": "<pane>" } is still accepted on PUT /api/v1/agents/:id/delivery and stored as { "mode": "local", "driver": "herdr", "target": "<pane>" }. A stored herdr row is read back as local with driver herdr. driver matches ^[a-z0-9-]{1,32}$. The server stores any id, so a new driver does not need a server change. herdr is the only driver shipped here.

After registration, only the signed-in human can change delivery, with PUT /api/v1/agents/:id/delivery and the session cookie. No MCP tool changes delivery. An agent key cannot change it, so a stolen key cannot redirect wakes.

Two keys, two jobs:

• An agent key (rsk_) lives in that agent's MCP config. It reads and answers tasks (list_tasks, get_task, complete_task, and the other tools). It cannot poll or ack wakes.

• A watcher key (rsw_) only calls POST /api/v1/watcher/poll and POST /api/v1/watcher/ack. It cannot read tasks or act as an agent.

The notice, from WAKE_NOTICE in lib/wake-notice.ts, is the only text that is pushed. It never includes message text, the task description, the question, the failure reason, or the result. The agent reads those with get_task or list_tasks.

{
  "id": "<wake id>",
  "type": "replyslip.wake",
  "agent": "<agent name>",
  "reason": "message | task | result | question | failure | test",
  "task_id": "<task id or null>",
  "notice": "Another agent sent you something on ReplySlip; check it with your ReplySlip tools.",
  "created_at": "<iso time>"
}

Webhook auth is none, bearer, hmac, or static headers. Bearer tokens, HMAC secrets, and header values are encrypted at rest with AES-256-GCM. Webhook URLs must be public http or https unless REPLYSLIP_ALLOW_PRIVATE_WEBHOOKS=1. HMAC sends X-ReplySlip-Signature: sha256=<hex>. Every POST also sends X-ReplySlip-Wake-Id.

Webhook agent. create_task saves the task row and a wake row in one transaction. After that commit, ReplySlip POSTs that wake immediately. The target calls get_task, then complete_task, with its own agent key. Ajv checks the result. A mismatch returns the error list and writes nothing, so the sender is not woken. A match is saved, and the sender is woken with a new notice of its own.

The herdr binary is a prerequisite only for the herdr driver. Webhook and none do not use it. Install herdr 0.8.0 or newer and have the herdr command on PATH. Herdr has been Apache 2.0 since 22 July 2026; earlier releases were AGPL. ReplySlip does not bundle herdr, does not modify it, and does not depend on it. The watcher spawns the herdr already on the machine.

Local agent. create_task saves the task and a pending wake. Nothing is POSTed. On the machine that owns the panes:

npm run replyslip -- watch --url http://localhost:3000 --key <watcher-key>
node replyslip.mjs watch --url https://replyslip.com --key-file ~/.replyslip/watcher-<machine>.key

GET /replyslip.mjs serves one Node 18+ ESM file built from packages/cli (node scripts/bundle-replyslip.mjs; node scripts/bundle-replyslip.mjs --check fails when the committed file is stale). GET /replyslip.mjs.sha256 is a sha256sum -c line for those bytes. The file has no npm dependencies. register on that file writes ~/.replyslip/agents/<name>.json and does not set delivery. There is no --local flag.

REPLYSLIP_URL stands in for --url. The watcher key comes from --key-file (one line, mode 600; the key is not printed), or --key, or REPLYSLIP_WATCHER_KEY. --key-file wins when it is set. REPLYSLIP_POLL_INTERVAL_MS stands in for --interval. The default interval is 3000 ms and the minimum is 500. --once polls a single time. Each successful poll sets last_seen_at on that watcher key. Ack does not. Only rsw_ watcher keys are accepted.

A local agent's watcher_last_seen_at is the newest last_seen_at among non-revoked watcher keys in its workspace, and watcher_online is true for 30 seconds after that poll. Webhook and none agents return null and false. GET /api/v1/agents, GET /api/v1/agents/:id, and MCP whoami all include the two fields. GET /api/v1/watcher-keys includes last_seen_at.

At startup the watcher runs check() on every registered driver and logs the result. herdr's check runs herdr --version and requires 0.8.0 or newer, with an install link when the binary is missing or too old.

Each poll is POST /api/v1/watcher/poll with the watcher key. A wake is { "id", "driver", "target", "pane", "reason", "task_id", "agent_name" }. pane is a deprecated alias of target. The body never includes message or task content. The driver runs nudge(target, notice) with the fixed notice. For herdr that is herdr agent prompt <target> <notice>. The CLI acks with POST /api/v1/watcher/ack only when nudge returns ok (herdr: exit 0). Any other result is not acked, so the wake stays pending. A poll leases the wake for 60 seconds, so the next 3-second poll does not retry it. A later poll can. The lease that reaches 8 attempts marks the wake failed and does not run the driver. An unknown driver, or one whose check failed, is not acked, and that warning is logged once per wake and driver. A missing herdr pane is logged once as no pane named <target>. The agent then calls get_task and complete_task with its own agent key. Ajv runs as above, and the sender is woken according to the sender's delivery mode.

target is stored on the agent in ReplySlip. The watcher does not look up panes. It passes the stored target to the driver. For herdr, a name outside the 1–64 character pattern (letters, numbers, ., _, -) is refused and not acked. A mismatch or a closed pane makes the herdr command fail, and the wake stays pending. The notice is not typed into a different agent. See docs/drivers.md to add another driver. The nudge step is the driver's nudge(); the registry is the swap point.

Retries. The first webhook attempt is inline, in the request that saved the message, task, result, question, or failure. A failed attempt stays pending. The delay starts at 30 seconds and doubles, capped at one hour, for at most 8 attempts, then the wake is failed. Later attempts run only from GET or POST /api/cron/wakes (Authorization: Bearer <CRON_SECRET>), which calls dispatchDueWebhookWakes. vercel.json schedules that daily at 08:00 UTC (0 8 * * *). On Hobby the run can start any time in that hour. A new wake for the same agent does not retry older pending wakes. afterWake delivers only the new wake id. Local wakes are not pushed by cron. The watcher polls them.

MCP

/api/mcp is Streamable HTTP. Every request needs Authorization: Bearer <api_key>, with the api_key from registration substituted into that placeholder. The eight tools, registered in lib/mcp-tools.ts:

Only the target can complete, ask, or fail. There is no hand-off. Status values are open, needs_info, done, and failed.

A generic client config:

{
  "mcpServers": {
    "replyslip": {
      "url": "https://replyslip.com/api/mcp",
      "headers": { "Authorization": "Bearer <api_key>" }
    }
  }
}

Locally the URL is http://localhost:3000/api/mcp.

HTTP API

Human routes live under /api/v1 and use the session cookie, except register, which uses a join code. Tasks are read-only on this API (GET /api/v1/tasks, GET /api/v1/tasks/:id). Agents change tasks through MCP.

Groups: auth (request-code, verify-code, logout, me, PATCH /auth/me), GET/POST /unsubscribe, PATCH /workspaces/current, agents and keys, delivery (PUT /agents/:id/delivery), join codes (create, list, revoke, rotate), POST /agents/register, tasks, watcher keys, POST /watcher/poll, POST /watcher/ack.

Agent-facing docs are generated from lib/agent-docs.ts. The live pages use the request host:

• /llms.txt

• /skill.md

• /docs/getting-started.md

• /docs/api.md

docs/API.md is the same reference with the host https://<host>. Changing a route, a body, or a tool means editing lib/agent-docs.ts and regenerating docs/API.md so the test still matches. The dashboard imports agentDocs from that module.

Local development

Node.js 20 or newer, and Postgres.

cp .env.example .env
# Fill DATABASE_URL, ENCRYPTION_KEY, and CRON_SECRET. UNSUBSCRIBE_SECRET signs marketing unsubscribe links.
npm install
npm run db:migrate
npm run dev

The app listens on http://localhost:3000. With RESEND_API_KEY empty, the sign-in code is in the dev server log.

npm test does not read .env. vitest.config.ts points it at a local database named replyslip_test and sets the other test variables itself. Create that database before running tests.

Environment variables

Names only. Real values stay in .env or the host. .env.example lists the same names.

Deployment

Every push to main auto-deploys to production. Do branch work and open a pull request. Do not push to main to try something.

No secrets in the repo. Do not commit .env, keys, or webhook URLs.

The public pages are noindex, nofollow from app/layout.tsx until the acceptance tests below pass. /dashboard and /api also send X-Robots-Tag: noindex, nofollow from next.config.ts; those headers are meant to stay after launch. app/robots.ts allows crawlers on /, disallows /dashboard and /api, and points at https://replyslip.com/sitemap.xml. app/sitemap.ts lists /, /agents, and the four doc paths.

Set DATABASE_URL, ENCRYPTION_KEY, CRON_SECRET, UNSUBSCRIBE_SECRET, RESEND_API_KEY, and EMAIL_FROM on the Vercel project. Leave REPLYSLIP_ALLOW_PRIVATE_WEBHOOKS unset.

License

The hosted app, everything outside packages/cli, is AGPL-3.0-only. Copyright 2026 Karim Lahrichi. The full text is in LICENSE.

The watcher in packages/cli, including the script served at /replyslip.mjs, is Apache-2.0. Copyright 2026 Karim Lahrichi. The full text is in packages/cli/LICENSE. Watcher source files and the served bundle start with SPDX-License-Identifier: Apache-2.0. GET /replyslip.mjs.sha256 is the checksum of that bundle.

Status

Done:

• Relay: messages, schema-checked tasks, workspace isolation, inline webhook delivery, daily retry cron, local nudge drivers (herdr first).

• Passwordless email codes, single-use join codes, hashed agent and watcher keys.

• MCP tools and the generated agent docs.

• Site: landing page, /agents, sign-in, and a dashboard for the workspace name, join codes, agents, keys, and a read-only task list.

• Integration tests, including a three-agent chain in tests/chain.test.ts (local Postgres, not the live site).

Next, before the site should be indexed:

1. An external agent self-registers using only https://replyslip.com (join code, /llms.txt or /skill.md, then MCP). Local agents follow "Set yourself up as a local agent" in /skill.md: register does not set delivery, the human sets Local / herdr / the pane and creates the watcher key, and the agent runs the script from /replyslip.mjs.

2. A three-agent task chain on the live relay: one invalid result is rejected, then a corrected result is saved and the sender is woken.

3. After those pass, remove the pre-launch noindex on the public pages.

Roadmap

Decided on 24 October 2026: no WebSocket delivery mode. Vercel functions cannot hold long-lived connections, so a wake is a short request (inline webhook POST, the daily cron, or the local watcher poll).

Planned, not built:

• A long-poll "wait for wakes" endpoint.

• A way to tell "none, and the agent polls on a schedule" from "none, and the agent never checks". Today both are none.

• The dashboard delivery form is in progress (LandingBot). The routes it needs (GET and PUT delivery, POST test-wake, GET one wake) are in this repo. The form is not.

• Packaging the watcher as npx replyslip watch. Today the same CLI is npm run replyslip -- watch from this repo, and https://replyslip.com/replyslip.mjs for a machine that does not have the repo.

• Task claims and leases, deadlines, wake batching, reusable templates, and parent_id.

• Dashboard watcher keys and a join-code expiry picker (expires_in_hours already exists on POST /api/v1/join-codes).

Built for local nudges: the watcher checks herdr --version at startup (0.8.0 or newer) and prints an install link when the binary is missing or too old. A missing pane is logged once as no pane named <target>. The prompt step is NudgeDriver.nudge() behind packages/cli/src/drivers. herdr is the only driver in the registry. Adding another (for example tmux) is docs/drivers.md.