senseplane-ai/senseplane

Eyes and ears for AI agents

TypeScript

2

43 commits

updated Oct 19, 2026

See the code

See what people are saying

README

Senseplane

Eyes and ears for your agent.

Website · Docs · Run it on a VM · Connect an agent · API

Connect the cameras, microphones and sensors you already have, and any agent (Claude, ChatGPT, Cursor or your own code) can see, hear and remember what happens.

  • Look: a snapshot of what's there now, and questions about it.
  • Watch: "tell me when a package is left at the door", with events by signed webhook, MCP or Telegram.
  • Ask: "when did the courier come?", answered with the event, a snapshot and a clip.
  • Measure: "how many meals today?", "how long did she sleep?", "is it quieter than usual?", answered exactly from activities, with a daily summary if you want one.
  • Replay: any range within your retention period (7 days by default).
Asking about the yard camera: a suggested watch for when the truck leaves, and how long it has been parked

Live view of three cameras: front door, yard and living room Events: a parcel watch fired and was checked by the AI, with its snapshot

Demo footage: vpdonline, Museum of Municipal Engineering (Kraków) and Diego Torres Silvestre, via Wikimedia Commons (CC BY); see fixtures.

Senseplane does perception, not decisions: it reports what it saw, how sure it is and the evidence, and your agent decides what to do. Agents connect through an MCP server, a REST API, webhooks and a TypeScript SDK.

Status: early (v0.2). Expect rough edges, and please report what breaks.

Quick start

On a server or your own computer with Docker:

mkdir senseplane && cd senseplane
curl -fsSLO https://raw.githubusercontent.com/senseplane-ai/senseplane/main/docker-compose.yml
# edit the settings block at the top: your domain, email, passwords and (optionally) a model key
chmod 600 docker-compose.yml
docker compose up -d

Open https://<your domain> and create your account (the first one owns the workspace). Add a phone or laptop camera from the console, then connect your agent to https://<your domain>/mcp. The full guide, with DNS, firewall, backups and upgrades: Run Senseplane on a VM.

How it fits together

PartFolderLanguageRole
Media planemedia/TypeScript (mediasoup)Ingest, continuous recording, playback, analysis feed
Brainbrain/PythonMotion, objects, sounds, episodes, watches, memory
APIapi/TypeScript (Fastify)Public /v1 REST API, webhooks, auth
MCP servermcp/TypeScript10 tools for agents
SDKsdk/typescript/TypeScriptnpm i senseplane
Consoleconsole/TypeScript (React)Web UI for sources, playback, watches, chat, access
Bridgebridge/GoRTSP cameras, outbound only
Home Assistantintegrations/home-assistant/PythonForwards sensors as readings
Specspec/OpenAPI + JSON SchemaSingle source of truth for API, SDK and MCP

Everything runs on one machine from one compose file, with Caddy in front for HTTPS. More: architecture, roadmap, decisions and lawful camera use.

Contributing

The development stack and a ten-minute tour of the API, webhooks and MCP are in the quick start for contributors; see also CONTRIBUTING.md. To build and test everything:

pnpm install
docker compose -f deploy/compose/docker-compose.yml up -d   # Postgres, Valkey, object storage
pnpm -r build && pnpm -r test
pnpm docs:build                                              # docs site in docs/site/

Security issues: see SECURITY.md.

License

Apache 2.0. See LICENSE and NOTICE. The Senseplane name is a trademark; forks must rename (see TRADEMARKS.md).

senseplane-ai/senseplane

Eyes and ears for AI agents

TypeScript

2

43 commits

updated Oct 19, 2026

See the code

See what people are saying

README

Senseplane

Eyes and ears for your agent.

Website · Docs · Run it on a VM · Connect an agent · API

Connect the cameras, microphones and sensors you already have, and any agent (Claude, ChatGPT, Cursor or your own code) can see, hear and remember what happens.

  • Look: a snapshot of what's there now, and questions about it.
  • Watch: "tell me when a package is left at the door", with events by signed webhook, MCP or Telegram.
  • Ask: "when did the courier come?", answered with the event, a snapshot and a clip.
  • Measure: "how many meals today?", "how long did she sleep?", "is it quieter than usual?", answered exactly from activities, with a daily summary if you want one.
  • Replay: any range within your retention period (7 days by default).
Asking about the yard camera: a suggested watch for when the truck leaves, and how long it has been parked

Live view of three cameras: front door, yard and living room Events: a parcel watch fired and was checked by the AI, with its snapshot

Demo footage: vpdonline, Museum of Municipal Engineering (Kraków) and Diego Torres Silvestre, via Wikimedia Commons (CC BY); see fixtures.

Senseplane does perception, not decisions: it reports what it saw, how sure it is and the evidence, and your agent decides what to do. Agents connect through an MCP server, a REST API, webhooks and a TypeScript SDK.

Status: early (v0.2). Expect rough edges, and please report what breaks.

Quick start

On a server or your own computer with Docker:

mkdir senseplane && cd senseplane
curl -fsSLO https://raw.githubusercontent.com/senseplane-ai/senseplane/main/docker-compose.yml
# edit the settings block at the top: your domain, email, passwords and (optionally) a model key
chmod 600 docker-compose.yml
docker compose up -d

Open https://<your domain> and create your account (the first one owns the workspace). Add a phone or laptop camera from the console, then connect your agent to https://<your domain>/mcp. The full guide, with DNS, firewall, backups and upgrades: Run Senseplane on a VM.

How it fits together

PartFolderLanguageRole
Media planemedia/TypeScript (mediasoup)Ingest, continuous recording, playback, analysis feed
Brainbrain/PythonMotion, objects, sounds, episodes, watches, memory
APIapi/TypeScript (Fastify)Public /v1 REST API, webhooks, auth
MCP servermcp/TypeScript10 tools for agents
SDKsdk/typescript/TypeScriptnpm i senseplane
Consoleconsole/TypeScript (React)Web UI for sources, playback, watches, chat, access
Bridgebridge/GoRTSP cameras, outbound only
Home Assistantintegrations/home-assistant/PythonForwards sensors as readings
Specspec/OpenAPI + JSON SchemaSingle source of truth for API, SDK and MCP

Everything runs on one machine from one compose file, with Caddy in front for HTTPS. More: architecture, roadmap, decisions and lawful camera use.

Contributing

The development stack and a ten-minute tour of the API, webhooks and MCP are in the quick start for contributors; see also CONTRIBUTING.md. To build and test everything:

pnpm install
docker compose -f deploy/compose/docker-compose.yml up -d   # Postgres, Valkey, object storage
pnpm -r build && pnpm -r test
pnpm docs:build                                              # docs site in docs/site/

Security issues: see SECURITY.md.

License

Apache 2.0. See LICENSE and NOTICE. The Senseplane name is a trademark; forks must rename (see TRADEMARKS.md).