AlphaNimble Technologies LLP
mem-brain docs

Memory infrastructure
for AI agents

Store facts, decisions, and context as memories. Retrieve them later — semantically, across graph edges, not just by keyword. Works with any LLM stack.

API version
v1
Base URL
Railway
Auth
X-API-Key
For builders

Agentic API guide

One Markdown file: HTTP auth, async jobs, search modes, regex tag scoping, tool wrappers, and copy-ready prompts for LangChain, Vercel AI SDK, AutoGen, or your own stack.

Quick start
Up and running in under two minutes
2 min setup
Windows & PowerShellQuick-start curl blocks use bash style (line breaks with \). The HTTP API is the same on every OS — only the shell differs. PowerShell: $env:MEMBRAIN_API_KEY="mb_live_..." · CMD: set MEMBRAIN_API_KEY=mb_live_... · Or use Git Bash / WSL for copy-paste identical to macOS/Linux, or run curl as a single line (no \).
1
Get an API key

Sign in to the Mem-Brain access portal and create a key. Keys start with mb_live_.

2
Store a memory
curl -X POST https://mem-brain-api-cutover-v4-production.up.railway.app/api/v1/memories \
  -H "X-API-Key: mb_live_xxx" \
  -H "Content-Type: application/json" \
  -d '{"content": "User prefers dark mode", "tags": ["type.preference", "domain.ui"]}'
Returns 202 Accepted with a job_id. The playground below polls it automatically.
3
Search your memories
curl -X POST https://mem-brain-api-cutover-v4-production.up.railway.app/api/v1/memories/search \
  -H "X-API-Key: mb_live_xxx" \
  -H "Content-Type: application/json" \
  -d '{"query": "What UI preferences does this user have?", "k": 5, "response_format": "interpreted"}'
Use response_format: "interpreted" to get a plain-language LLM summary — inject directly into a system prompt.
Live playground — use your own API key
Interactive Playground

CRUD, search, polling, and graph exploration in one place

Paste your API key once, then create memories, poll ingest jobs, run graph operations, and inspect your own graph live.

Base URL: https://mem-brain-api-cutover-v4-production.up.railway.app
The playground sends browser requests directly to the hosted API using your X-API-Key.
cURL
curl -X POST https://mem-brain-api-cutover-v4-production.up.railway.app/api/v1/memories \
  -H "X-API-Key: mb_live_xxx" \
  -H "Content-Type: application/json" \
  -d '{
  "content": "User prefers dark mode and keeps notes in Obsidian",
  "tags": [
    "type.preference",
    "domain.workflow"
  ],
  "category": "user-prefs"
}'
Ready
Run an operation to see the live response here.
Your Graph
Force-directed graph explorer for your own memories. Drag nodes, zoom, and click into details.
No graph loaded yet.
Load your graph from the Graph tab to start exploring your own memory network.
Selected

Click a node or edge to inspect it. The latest created memory is highlighted in green when present.

How memory works

The key concepts behind storage and retrieval

Semantic storage

Every memory is embedded and stored as a node in a knowledge graph. Related memories are linked automatically at write time.

Graph retrieval

Search combines vector similarity with graph traversal — so related memories surface even when the wording doesn't match.

Structured tags

Tag memories with dot-separated keys like type.preference or domain.ui to filter results and scope searches precisely.

Async ingest

POST /memories returns 202 with a job_id. Poll the job until completed — or let the MCP client handle polling for you.

Example memory object
{
  "content": "Project uses Turborepo + pnpm workspaces",
  "tags": ["type.project-config", "tech.turborepo"],
  "category": "project"
}