Kanister Request Access
FOR BUSINESS

Drop it in.
We'll remember.

Your org's memory. The machines handle it. You oversee.

Every deal detail across every channel. Every client requirement from every conversation. Every pricing change, every supplier commitment, every decision your team has ever made. Kanister captures it all, connects the dots, and makes it instantly findable — for your people and your AI agents.

Request Access See what you get
Kanister business dashboard Kanister mobile
WHAT YOUR TEAM GETS

Institutional memory that never walks out the door.

🎯

Find anything in half a second

"What did Kevin say about FE pricing in March?" — instant answer with source, date, and confidence score. Across Telegram, email, Slack, WhatsApp — every channel your team uses, searched at once. Under 500ms.

💰

Never lose deal context again

Your VP of Sales leaves? Their three years of client relationships, pricing negotiations, and supplier preferences stay behind — captured, connected, and searchable. New hires get productive on day one, not month six.

🧠

AI that connects the dots

Kanister auto-extracts people, companies, deals, amounts, and dates from every conversation. It builds a knowledge graph linking every interaction across every source. And it flags contradictions — like when a supplier quotes two different prices in the same week.

🤖

Your AI agents share one brain

Run five Claude terminals, a Cursor instance, and custom bots on the same projects? Through Agent Telepathy, they coordinate themselves — shared context, live broadcasts, intent signals. Zero conflicts, zero human coordination needed.

🔗

Plugs into your existing stack

Telegram, Slack, WhatsApp, Teams, Gmail — connect once, messages flow in forever. Webhooks for n8n, Zapier, custom scripts. PM sync for Linear and GitHub Issues. If your tools send data, Kanister consumes it.

🔒

Self-hosted. Your data never leaves.

Runs on your infrastructure. No cloud dependencies for core features. Every conversation, every deal detail, every decision stays on your hardware. Full audit trail, API key auth, no third-party data sharing.

🔥 NOW — AGENT TELEPATHY

Your AI agents just got a shared brain.

Your team runs Claude terminals, Cursor, custom bots — all on the same projects. Now they coordinate through Kanister. Presence, broadcasts, shared context, coordinated work. Your agents operate as a team. You oversee.

See it in action
🟢 Agent A registers: "Working on the pricing API refactor"
🟢 Agent B sees A's focus — grabs the dashboard tasks
🟢 Agent A broadcasts: "Pricing endpoint schema changed"
🟢 Agent C reads A's decisions log — builds tests for the new schema
Three agents. One brain. Zero conflicts. You just watch.
terminal — mb status 
$ mb status
  ● claude-api        active    Pricing API refactor
  ● claude-dashboard  active    Dashboard components
  ● cursor-tests      active    Test suite expansion
  ⟩ 3 agents, 0 conflicts, 12 tasks done today

  Recent broadcasts:
  → /api/pricing: schema updated (v2)
  → Decisions: "Using integer cents for amounts"
  → context handed off: claude-api → cursor-tests

  Signals: none active
  Status: ALL CLEAR
📡

Session Presence

Every agent registers a heartbeat. Who's alive, what they're focused on, when they last checked in. A standup that happens automatically.

🔊

Live Broadcasts

Agent reshapes the project? Broadcasts it instantly. Everyone's in the loop on the next turn. Pub/sub for your AI workforce.

🧠

Shared Working Memory

Each agent writes what it's doing, what it decided, and what's pending. The next session picks up exactly where the last one left off.

🔒

Intent Signals

Before touching critical files, agents signal what they're about to change. Others work around it. Crashes auto-expire. No deadlocks.

🖥️

Agent CLI

mb who — who's working. mb claim task-42 — lock it. mb status — the full picture. You oversee. The machines work.

🔌

The Platform

12 MCP tools. Decisions API with semantic search. PM sync for Linear + GitHub. Context assembly from Postgres + knowledge graph. Not a feature — the platform your agents run on.

Your agents are ready to work as a team. Give them the brain.

Request Business Access
FOR YOUR DEV TEAM

Here's what's under the hood.

API-first, self-hosted, standards-based. No vendor lock-in.

API Surface

55+ REST Endpoints

Full CRUD for memories, entities, sources, and ingestion. Hybrid search (vector + BM25 + graph). Timeline, analytics, and health monitoring. Agent coordination via /api/coordination/*. JSON responses, consistent error format, API key auth.

GET  /api/search?q="Kevin FE pricing March"
POST /api/capture  { content, source, metadata }
GET  /api/stats
GET  /api/ingestion/status
POST /api/coordination/sessions
POST /api/admin/sources/{source}/sync
Agent Protocol

12 MCP Tools

Structured tools for search, capture, entity management, coordination, and context delivery. Any MCP-speaking agent gets full memory access — Claude Code, Cursor, custom bots, n8n workflows.

mcp://kanister_search
mcp://kanister_capture
mcp://kanister_entity_lookup
mcp://telepathy_register
mcp://telepathy_broadcast
mcp://telepathy_check
Agent OS

Task Management + Decisions

Task API with claim/release and distributed locks. Decisions API — log every architectural choice with semantic search. PM sync adapters for Linear and GitHub Issues. Context assembly from Postgres + knowledge graph in a single query.

POST /api/tasks          { title, priority }
POST /api/tasks/claim    { task_id, agent_id }
POST /api/decisions      { topic, decision, rationale }
GET  /api/decisions/search?q="database choice"
Stack

Open Architecture

FastAPI backend. PostgreSQL 16 + pgvector for hybrid search. Redis 7 event bus. Memgraph knowledge graph. Qdrant vector store. Docker Compose — 10 containers, ~14.5 GB RAM. Runs on a Mac Mini or rack server.

FastAPI PostgreSQL 16 pgvector Redis 7 Memgraph Qdrant Docker
55+
API endpoints
12
MCP agent tools
6
Ingestion sources
99.9%
Uptime SLA