The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
Python agentic-memoryagentic-memory-systemagentsaiai-agentschatgptgenaillmlong-term-memorymemorymemory-managementpythonragstate-management
docs(cookbooks): Company Brain with Mem0 Platform + Supabase (#7309)
Himanshua39a802bbc93
diff --git a/docs/cookbooks/integrations/supabase.mdx b/docs/cookbooks/integrations/supabase.mdxnew file mode 100644index 000000000..cf9b8c038--- /dev/null+++ b/docs/cookbooks/integrations/supabase.mdx@@ -0,0 +1,388 @@+---+title: Build a Company Brain with Mem0 Platform and Supabase+description: "A step-by-step guide to a shared organizational memory: Mem0 Platform is the managed brain, Supabase is your system of record, and every agent taps it through the Mem0 MCP server."+---++<Info icon="server">+**Uses:** Mem0 **Platform** (`MemoryClient`) · **System of record:** Supabase (Postgres + Auth) · **Access layer:** the hosted Mem0 MCP server. **You'll build:** a company brain your whole org (and every agent) writes to and queries, ending with a new-hire onboarding demo.+</Info>++Companies lose knowledge constantly: why you picked Postgres over Mongo, who owns billing, the deploy rule only one engineer remembers. A **company brain** captures this and answers questions about it, for every employee and every agent, and keeps it after people leave.++We'll build one on **Mem0 Platform** (the managed memory layer, so there's no vector DB to run) with **Supabase as the system of record** (where your employees, teams, and source documents actually live) and the **Mem0 MCP server** as the wire that lets Claude Code, Cursor, or a Slack bot all reach the same brain.++<Note>+**How Platform and Supabase divide the work.** Mem0 Platform manages storage and extraction server-side, you do **not** point it at your own database. Supabase is your app's source of truth and identity provider; we *ingest* knowledge from Supabase into the brain and use Supabase Auth to decide who's asking. (If you want to self-host the vector store instead, that's the OSS path, see the [Supabase vector store reference](/components/vectordbs/dbs/supabase).)+</Note>++## Architecture++```mermaid+flowchart LR+ subgraph SB["Supabase: system of record"]+ K[(knowledge / employees / teams)]+ AU[Auth · who is asking]+ end+ subgraph M0["Mem0 Platform: the brain"]+ B[(managed memory)]+ end+ K -->|ingest| B+ AU -->|maps to scope| B+ CC[Claude Code] --> MCP[Mem0 MCP server]+ CU[Cursor] --> MCP+ SL[Slack bot] --> MCP+ MCP --> B+```++Memory splits by entity. An individual is a **`user_id`** (their Supabase Auth id). Shared knowledge lives on an **`agent_id`**: the company-wide brain is `org:acme`, and each team is its own agent, e.g. `team:payments`. A person's own facts route to their `user_id`; company and team facts route to the agent. This split is what lets one search return "my" context alongside the shared org knowledge.++## Prerequisites++- **Python 3.9+**+- A **Mem0 Platform API key**, [app.mem0.ai/dashboard/api-keys](https://app.mem0.ai/dashboard/api-keys?utm_source=oss&utm_medium=cookbook-company-brain). (Platform runs extraction and embeddings for you, so there's no OpenAI key to manage.)+- A **Supabase** project, [supabase.com](https://supabase.com)++About 20 minutes.++---++## Step 1: Get your Mem0 Platform API key++Sign in at [app.mem0.ai](https://app.mem0.ai) and copy a key from **Dashboard → API Keys**. The key is scoped to your org and project; Mem0 resolves both server-side, so you never pass IDs by hand.++## Step 2: Create the Supabase system of record++In the Supabase **SQL editor**, create the tables your company already thinks in: people, teams, and a `knowledge` table the brain will ingest from. Identity reuses Supabase Auth's built-in `auth.users`.++```sql+-- Employees extend Supabase Auth's users; identity is auth.users.id (uuid)+create table public.employees (+ id uuid primary key references auth.users (id) on delete cascade,+ name text not null,+ team text not null+);++-- The company knowledge the brain ingests. `scope` decides who can recall it.+create table public.knowledge (+ id bigint generated always as identity primary key,+ scope text not null, -- the shared agent this belongs to: 'org:acme' | 'team:payments'+ content text not null,+ author uuid references auth.users (id), -- who recorded it (their user_id); null for org seed data+ created_at timestamptz default now(),+ mem0_synced_at timestamptz -- null until ingested into the brain+);+create index on public.knowledge (mem0_synced_at, created_at);++-- Seed a little company knowledge to ingest.+insert into public.knowledge (scope, content) values+ ('org:acme', 'We chose Postgres over MongoDB for the core product for strong transactional guarantees and relational joins.'),+ ('org:acme', 'All production deploys go out Tuesday and Thursday; never on Fridays.'),+ ('org:acme', 'Customer data must stay in the EU region for GDPR compliance.'),+ ('org:acme', 'Billing is owned by the Payments team, and Alice is the Payments tech lead.'),+ ('team:payments', 'Stripe is our processor; webhooks are verified with PAYMENTS_WEBHOOK_SECRET.');+```++Grab your project URL and **service-role** key from **Settings → API** (the ingestion job runs server-side and needs to read every scope).++## Step 3: Project setup++```bash+mkdir company-brain && cd company-brain+pip install "mem0ai>=2.0.17" supabase requests # 2.0.17+ for agent_custom_instructions+```++```bash+export MEM0_API_KEY="m0-..."+export SUPABASE_URL="https://<project-ref>.supabase.co"+export SUPABASE_SERVICE_KEY="<service-role-key>"+```++## Step 4: Configure the brain++Create **`brain.py`**. This constructs the Platform client and teaches it what to remember. The key is the **two** instruction sets: `custom_instructions` governs a person's own (`user_id`) memories, and `agent_custom_instructions` governs shared (`agent_id`) memories, phrased in the third person so company facts read "The company…", not "The user's organization…". `custom_categories` files each memory under a useful label.++```python+# brain.py+import os+from mem0 import MemoryClient++client = MemoryClient(api_key=os.environ["MEM0_API_KEY"])++# Steer extraction (project-wide). Runs server-side; no LLM key needed here.+client.project.update(+ # Governs a person's OWN memories (user_id).+ custom_instructions=(+ "Extract the individual's own durable preferences, context, and how they work. "+ "Ignore greetings and one-off chatter."+ ),+ # Governs SHARED memories (agent_id); write them in the third person.+ agent_custom_instructions=(+ "Extract durable company/team knowledge in the third person "+ "(\"The company...\", \"The team...\"): decisions and their rationale, ownership "+ "(who owns what), processes, policies, tooling choices, and gotchas. "+ "Ignore greetings, scheduling, and one-off chatter."+ ),+ custom_categories=[+ {"decision": "Architectural or product decisions and why they were made"},+ {"ownership": "Who owns a system, service, or process"},+ {"policy": "Compliance, security, and process rules"},+ {"tooling": "Tools, services, and how they're configured"},+ ],+)++# Scopes. A person is a user_id; shared brains are agent_ids.+COMPANY = "org:acme" # agent_id: company-wide shared brain+def team(name): return f"team:{name}" # agent_id: a team's shared brain+def person(uid): return uid # user_id: an individual (Supabase auth id)+```++Run it once to apply the project settings:++```bash+python -c "import brain; print('brain configured')"+```+++## Step 5: Ingest company knowledge from Supabase++This is where Supabase and the brain connect. Create **`ingest.py`**: read un-synced rows from `knowledge`, add each to the Platform brain under its scope, then mark it synced. Platform `add()` is **asynchronous**, it returns an `event_id` you can poll, so we include a small `wait_for` helper.++```python+# ingest.py+import os, time, requests+from supabase import create_client+from brain import client, person++sb = create_client(os.environ["SUPABASE_URL"], os.environ["SUPABASE_SERVICE_KEY"])+MEM0_HEADERS = {"Authorization": f"Token {os.environ['MEM0_API_KEY']}"}++def wait_for(event_id, timeout=30):+ """Platform extraction is async; poll the event until it settles."""+ for _ in range(timeout):+ r = requests.get(f"https://api.mem0.ai/v1/event/{event_id}/", headers=MEM0_HEADERS).json()+ if r.get("status") in ("SUCCEEDED", "FAILED"):+ return r["status"]+ time.sleep(1)+ return "TIMEOUT"++# 1. Read knowledge that hasn't been ingested yet+rows = sb.table("knowledge").select("*").is_("mem0_synced_at", "null").execute().data++for row in rows:+ # 2. Add it. agent_id = the shared scope (org/team); user_id = who recorded it.+ # Mem0 routes shared facts to the agent and personal facts to the individual,+ # so pass both when there's an author.+ add_kwargs = {+ "agent_id": row["scope"],+ "metadata": {"source": "supabase", "knowledge_id": row["id"]},+ }+ if row["author"]:+ add_kwargs["user_id"] = person(row["author"])+ res = client.add([{"role": "user", "content": row["content"]}], **add_kwargs)+ # 3. Platform returns an event_id; wait for extraction to finish+ event_id = res.get("event_id") if isinstance(res, dict) else None+ if event_id:+ wait_for(event_id)+ # 4. Mark the row synced so we never double-ingest+ sb.table("knowledge").update({"mem0_synced_at": "now()"}).eq("id", row["id"]).execute()++print(f"Ingested {len(rows)} knowledge items into the company brain.")+```++```bash+python ingest.py+```++```text+Ingested 5 knowledge items into the company brain.+```++Re-running is safe, `mem0_synced_at` gates it, so a nightly cron can keep the brain in step with Supabase.++## Step 6: Ask the brain++Create **`ask.py`**. It searches everything relevant to the asker: their own (`user_id`) memories **plus** the shared company and team (`agent_id`) memories. This has to be an **`OR`**, each memory row belongs to exactly one entity, so a flat filter or an `AND` of a `user_id` and an `agent_id` matches nothing.++```python+# ask.py+import sys+from brain import client, COMPANY, team, person++def ask(question: str, uid: str | None = None, user_team: str | None = None) -> str:+ scopes = [{"agent_id": COMPANY}] # company-wide brain+ if user_team:+ scopes.append({"agent_id": team(user_team)}) # the asker's team+ if uid:+ scopes.append({"user_id": person(uid)}) # the asker's own memories+ hits = client.search(+ query=question,+ filters={"OR": scopes}, # OR, never AND (one FK per memory row)+ top_k=5,+ rerank=True,+ )+ return "\n".join(f"- {h['memory']}" for h in hits.get("results", hits))++if __name__ == "__main__":+ print(ask(" ".join(sys.argv[1:]) or "When can we deploy?"))+```++```bash+python ask.py "Why did we pick Postgres, and can I deploy on Friday?"+```++```text+- The company chose Postgres over MongoDB for strong transactional guarantees and relational joins+- The company's production deploys go out Tuesday and Thursday, never on Fridays+```++Search returns every relevant memory, so a question resolves across separate facts, here it pulls both the owning team and the person:++```bash+python ask.py "Who should I talk to about billing?"+```++```text+- Billing is owned by the Payments team+- Alice is the Payments tech lead+```++## Step 7: Sharper retrieval++Platform search is hybrid (semantic + keyword) and filterable. Combine a keyword pass with a category filter to answer precise questions:++```python+client.search(+ query="webhook signing secret",+ filters={"agent_id": "team:payments", "categories": {"in": ["tooling"]}},+ keyword_search=True, # hybrid keyword + semantic+ rerank=True,+ threshold=0.3,+)+```++Filters use keyword operators (`in`, `gte`, `contains`, …) and AND/OR/NOT, so you can scope by date, category, or metadata, for example the company's policies added this quarter:++```python+client.search(+ query="compliance rules",+ filters={"AND": [+ {"agent_id": "org:acme"},+ {"categories": {"in": ["policy"]}},+ {"created_at": {"gte": "2026-01-01"}},+ ]},+)+```++## Step 8: Expose the brain to every agent (MCP)++A brain only your script can reach isn't a company brain. Mem0's **hosted MCP server** lets any agent (Claude Code, Cursor, a Slack bot) query and contribute to the *same* brain. The endpoint is `https://mcp.mem0.ai/mcp`, and the supported way to connect is the `mcp-add` helper, which registers the server and runs Mem0's OAuth login so no key ever lands in a config file.++<Tabs>+<Tab title="Claude Code / Cursor">+```bash+npx mcp-add --url "https://mcp.mem0.ai/mcp" --clients "claude code,cursor"+```+Complete the browser login on first connect. Now the agent has the brain's memory tools (`add_memory`, `search_memories`, and more) available in-editor.+</Tab>+<Tab title="Manual (.mcp.json)">+```json+{+ "mcpServers": {+ "mem0": { "url": "https://mcp.mem0.ai/mcp" }+ }+}+```+Auth happens via Mem0's OAuth flow on first use, don't paste a static token into the file (the hosted gateway may reject a raw `Token` header).+</Tab>+<Tab title="Slack bot">+```python+# A Slack bot is just another MCP client. Point its MCP layer at the same URL,+# authenticate via Mem0's OAuth flow, and pass the company scope on each call.+await mcp.call_tool("search_memories", {+ "query": user_message,+ "agent_id": "org:acme",+})+```+</Tab>+</Tabs>++With this, an engineer asks the brain from their editor and a teammate asks it from Slack, one shared memory behind both.++## Step 9: Onboard a new hire (the payoff)++This is what a company brain is *for*. Dana joins, and her identity comes from **Supabase Auth**, which maps straight to her Mem0 `user_id`. She asks the questions every new hire asks and gets real answers on day one, drawn from the shared company (and her team's) brain, plus anything she's told it herself.++```python+# onboarding.py+from brain import client, person+from ask import ask++# In a real app these come from sb.auth.get_user(jwt) and the employees table.+dana_uid, dana_team = "8f3c...-dana", "payments"++# Dana also tells the brain how *she* works. This is personal, so it goes to her+# user_id, not the shared agent, and stays scoped to her.+client.add(+ [{"role": "user", "content": "I prefer early returns over nested ifs, and I review PRs in the morning."}],+ user_id=person(dana_uid),+)++for q in [+ "Who owns billing and who do I talk to?", # company (agent) knowledge+ "When are deploys, and are there hard rules?",+ "How do I like to write code?", # Dana's own (user) knowledge+]:+ print(f"Q: {q}\nA: {ask(q, uid=dana_uid, user_team=dana_team)}\n")+```++```text+Q: Who owns billing and who do I talk to?+A: - Billing is owned by the Payments team; Alice is the Payments tech lead++Q: When are deploys, and are there hard rules?+A: - The company's production deploys go out Tuesday and Thursday, never on Fridays++Q: How do I like to write code?+A: - User prefers early returns over nested ifs+```++The same `ask()` blends the shared company facts with Dana's own preference, because the `OR` filter spans both her `user_id` and the org and team `agent_id`s.++Dana onboarded herself by asking, drawing on the shared brain the rest of the team had been filling.++## Production notes++<Warning>+**`user_id` vs `agent_id`.** An individual is a `user_id`; shared brains (company, team) are `agent_id`s. Keeping them separate is what gives you the third-person "The company…" framing and lets a person's own context sit alongside org knowledge. Put a secret like a webhook key on a **team** agent, never the company agent, or everyone can recall it, and mirror the boundary in Supabase with a Row Level Security policy on `knowledge`.+</Warning>++<Warning>+**Search must `OR` the scopes.** A memory row belongs to exactly one entity, so `filters={"OR": [{"user_id": ...}, {"agent_id": "org:acme"}, {"agent_id": "team:..."}]}`. A flat filter, or an `AND` of a `user_id` and an `agent_id`, returns nothing.+</Warning>++<Warning>+**`add()` is asynchronous.** It returns `{event_id, status: "PENDING"}` and extraction finishes a moment later, poll `GET /v1/event/{event_id}/` (as in Step 5) when you need to know a write has landed before searching for it.+</Warning>++<Note>+**Where the entity ID goes differs by call.** `search()` and `get_all()` take the scope inside `filters={...}` (a top-level `user_id=`/`agent_id=` is rejected). `add()` and `delete_all()` are the opposite, they take it as a top-level keyword: `client.delete_all(agent_id="team:payments")`. Deletes are asynchronous too, so a `get_all` right after a `delete_all` can still show rows for a few seconds.+</Note>++## Where to take it next++- **Auto-feed the brain** from PR descriptions, RFCs, and incident write-ups so it grows without anyone thinking about it, just insert into Supabase `knowledge` and let the cron ingest.+- **Scope by real identity** end to end: verify the Supabase JWT, read `sb.auth.get_user(jwt).user.id` for the `user_id`, look up the person's team, and `OR` their `user_id` with the company and team `agent_id`s on every recall.+- **Give teams a private view** with Supabase RLS so `team:` knowledge is only readable by that team.++---++<CardGroup cols={2}>+ <Card title="Mem0 MCP Server" icon="plug" href="/platform/mem0-mcp">+ Connect any agent or editor to the brain over MCP.+ </Card>+ <Card title="Custom Categories & Instructions" icon="sliders" href="/platform/features/custom-instructions">+ Steer exactly what the brain extracts and how it's filed.+ </Card>+</CardGroup>++<Snippet file="star-on-github.mdx" />diff --git a/docs/docs.json b/docs/docs.jsonindex 4ca51fa24..7aecc007c 100644--- a/docs/docs.json+++ b/docs/docs.json@@ -444,7 +444,8 @@"cookbooks/integrations/mastra-agent","cookbooks/integrations/healthcare-google-adk","cookbooks/integrations/aws-bedrock",- "cookbooks/integrations/tavily-search"+ "cookbooks/integrations/tavily-search",+ "cookbooks/integrations/supabase"]},{diff --git a/docs/llms.txt b/docs/llms.txtindex 686835a0e..ce60e29f5 100644--- a/docs/llms.txt+++ b/docs/llms.txt@@ -326,6 +326,7 @@ If the user is on a pre-current major (Python < 2, TS < 3, or a Platform call st- [Healthcare Google ADK](https://docs.mem0.ai/cookbooks/integrations/healthcare-google-adk) [Platform]: Use when the domain is medical and the framework is Google ADK.- [AWS Bedrock](https://docs.mem0.ai/cookbooks/integrations/aws-bedrock) [OSS]: Use when deploying with AWS managed model services.- [Tavily Search](https://docs.mem0.ai/cookbooks/integrations/tavily-search) [Platform]: Use when the agent layers web search on memory.+- [Company Brain (Mem0 Platform + Supabase)](https://docs.mem0.ai/cookbooks/integrations/supabase) [Platform]: Use to build a shared org brain on Mem0 Platform with Supabase as system of record and the MCP server as the access layer (with a new-hire onboarding demo).### Framework Examples- [LlamaIndex React](https://docs.mem0.ai/cookbooks/frameworks/llamaindex-react) [Both]: Use when building a React UI with LlamaIndex and memory.