Skip to main content
BetaRicord is in public beta.
Works in Claude, ChatGPT, Cursor & every MCP-aware AI

Your AI keeps forgetting you.
Ricord remembers.

One install. Persistent memory across Claude, Cursor, and ChatGPT — every conversation, every tool, forever.

npx ricord@latest install
LangChainVercel AI SDKOpenAIMCPCrewAI
p95 retrieval
300ms
uptime SLA
99.9%
memories stored
50K+
integrations
12+
Capabilities

Memory that organizes itself.

Every topic in your life gets its own wiki page. Ricord rewrites them as you learn — and connects them in a graph you can actually browse.

Adaptive relevance ranking

Every piece of knowledge earns a utility score that improves with usage. Retrieval gets smarter over time — the most useful knowledge surfaces first.

Product roadmap Q2
94
API rate limits
87
Meeting notes - Jan
62
Old bookmark
23

Conflict resolution

Detects duplicates, contradictions, and updates automatically. No stale data.

conflict API limit: 1000 → 5000
resolved Updated to latest

Tiered context loading

Three-level hierarchy (L0/L1/L2) delivers 80-98% token savings.

L0Core facts~50
L1Context~500
L2Full detail~5K

Universal ingest

Save from any source — URLs, PDFs, images, audio, notes, Kindle highlights. 100+ integrations via Composio. Everything becomes searchable.

URLsPDFsImagesAudioNotesKindleSlackEmailCodeDocs

Knowledge lifecycle

Knowledge matures from draft to proven, and auto-depreciates when stale.

Draft
Active
Proven
Stale

API-first

Every feature is an API endpoint. Standard REST + MCP server, drop-in for any language, and works with LangChain, Vercel AI SDK, and CrewAI.

RESTMCPWebhooksOpenAPI
For developers

Three lines to
infinite memory

Get an API key, curl your first memory, and your agents have instant retrieval over everything you've saved. Or install the MCP server with one command for Claude Code, Cursor, Windsurf, VS Code, and more.

LangChainVercel AI SDKCrewAIOpenAI SDKMCP ServerREST API
demo.sh
1
2
3
4
5
6
7
8
9
# Two memories — the second one contradicts the first
curl -X POST https://api.ricord.ai/v1/memories \
-H "Authorization: Bearer rc_live_..." \
-d '{"content": "Q2 launch: April 15"}'
-d '{"content": "Q2 launch slipped to May 8 (legal review)"}'
# Ricord follows the graph + resolves the conflict
curl -X POST https://api.ricord.ai/v1/memories/search \
-d '{"query": "when does Q2 ship?"}'
Output
{ content: "Q2 launch slipped to May 8 (legal review)",
score: 0.94, status: "current", supersedes: "Q2 launch: April 15" }
How it works

From raw content to instant recall

Three steps. Zero configuration. Production-ready in minutes.

01

Ingest

Save URLs, paste text, upload PDFs, images, or audio. Push via API, MCP, or 100+ integrations.

02

Process

Content is embedded, conflict-checked, and scored. Knowledge gets a maturity lifecycle and adaptive utility score.

03

Retrieve

Query with natural language. Adaptive ranking surfaces your most useful knowledge first — 80-98% token savings.

Integrations

Works with everything you already use

Connect your tools and content flows. Ricord ingests from 12+ sources and exposes your knowledge via MCP, REST API, and native SDKs.

Notion
Obsidian
Chrome
X (Twitter)
Kindle
PDFs
Slack
Telegram
RSS
GitHub
API
MCP

What builders say

From solo developers to AI teams shipping production agents.

Finally, a memory layer that actually works. Our agents went from forgetting context every session to having perfect recall across thousands of conversations.

A
Alex R.
AI Engineer · Series A Startup

The auto-wiki pages are the killer feature. Every entity in our system — users, projects, decisions — gets a living Wikipedia page I can actually read. Nothing else ships this.

S
Sarah K.
ML Lead · Enterprise AI Team

Set up the MCP server in 2 minutes. Now Claude Code remembers my entire codebase context, preferences, and project decisions across sessions.

M
Marcus T.
Full-stack Developer · Indie Builder
Auto-wikis
for every entity
3 signals
meaning · graph · memory
<300ms
p95 retrieval
99.9%
uptime SLA
Pricing

Built to scale with you

Pick the plan that fits today. Upgrade anytime as you grow.

Pro

Most popular
$15/mo

Save $48.00/yr

For developers shipping agents

  • 50,000 memories
  • 50,000 searches/mo
  • Unlimited spaces
  • Conflict resolution
  • Temporal queries
  • All integrations
  • API access
  • $0.01 / 1K search overage
Get started

Plus

$39/mo

Save $120.00/yr

For power users with bigger libraries

  • 500,000 memories
  • 500,000 searches/mo
  • Unlimited spaces
  • Priority support
  • Custom embeddings
  • Advanced analytics
  • $0.005 / 1K search overage
Get started

Max

$79/mo

Save $240.00/yr

For high-volume workloads

  • 5M memories
  • 5M searches/mo
  • Everything in Plus
  • Usage-based overage
  • Dedicated support
  • 99.9% SLA
Get started

Enterprise

Custom

Unlimited memories & searches · SSO / SAML · On-prem · Audit logs · Custom SLA · Dedicated support

Contact sales

Frequently asked questions

Everything you need to know before getting started.

Most memory tools are filing cabinets — they store past messages with a search box on top. Ricord is a brain: it extracts facts, connects them into a knowledge graph, auto-writes wiki pages for every entity, and resolves contradictions when your memory changes. Knowledge graph is included on every tier; Mem0 gates it behind $249/mo. See the comparison page for the full breakdown.

Pro ($15/mo billed annually, $19/mo monthly), Plus ($39/$49), and Max ($79/$99). Pick one at signup — upgrade or downgrade anytime from your dashboard.

Under 2 minutes. Sign up, grab your API key, and curl https://api.ricord.ai/v1/memories — that's it for the REST path. For Claude Code, Cursor, Windsurf, or VS Code users, just run npx ricord@latest install and the MCP server auto-configures.

Yes. All data is encrypted at rest and in transit. We use Google Cloud Platform infrastructure with SOC 2-level controls. You can hard-delete any data at any time (GDPR compliant), and we never use your data to train models.

Absolutely. We have native integrations with LangChain, Vercel AI SDK, CrewAI, LlamaIndex, and any OpenAI-compatible setup. Our MCP server works with Claude Code, Cursor, Windsurf, and VS Code.

You'll get a friendly notification when you hit 80% of your limit. Once you reach the cap, write operations pause but you can still read and search your existing memories. Upgrade anytime — no data is lost.

Your knowledge deserves better than bookmarks

Set up in under a minute.

Connect via MCP
npx ricord@latest install

Auto-detects installed agents, opens browser login, and configures each.