Tempreon
About
Person-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.
Details
- Author
- Tempreon
- Downloads
- 986
- Transport
- SSE
- Categories
- AI, Knowledge Base, Productivity
Jump to
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
TempreonCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
{
"mcpServers": {
"tempreon": {
"type": "http",
"url": "https://api.tempreon.com/functions/v1/tempreon-mcp/mcp"
}
}
}
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"tempreon": {
"tempreon": {
"type": "http",
"url": "https://api.tempreon.com/functions/v1/tempreon-mcp/mcp"
}
}
}
}McpServers
{
"tempreon": {
"type": "http",
"url": "https://api.tempreon.com/functions/v1/tempreon-mcp/mcp"
}
}The MCP layer between you and every AI tool. Your voice, your decisions, your judgment. Across Claude, ChatGPT, Cursor, and any MCP-capable client.
tempreon.com·Documentation·Pricing·Use cases·About
Tempreon is a portable knowledge layer about you, connected to AI tools through the Model Context Protocol (MCP). Where a company knowledge base brings a company's knowledge to AI, Tempreon bringsyouto AI — your voice, your decisions, your accumulated knowledge, your judgment — across every LLM you use.
Where most memory systems store and recall, Tempreon learns and grows. The model changes. The layer travels. The work compounds.
- Persistent identity layer.Your Core Imprint, Knowledge Vault, Instincts, and captured patterns travel with you across every AI tool you connect.
- Cross-LLM continuity.Knowledge captured in Claude is available in ChatGPT, Cursor, Codex, and any MCP-capable client. No re-explaining.
- Learning, not just memory.Tempreon doesn't only store what you said — it learns from how you actually work, what you decide, and refines those patterns over time.
- Person-centered, not company-centered.Built around the individual operator, consultant, founder, or knowledge worker — not the team or department.
Seetempreon.com/use-casesfor how operators, consultants, founders, sales professionals, knowledge workers, and others put Tempreon to work.
- Create your Tempreon accountattempreon.com. Complete the 13-dimension onboarding to seed your Core Imprint (~15 minutes).
- Connect a Bridge.Generate a Bridge URL from your dashboard, paste it into your MCP client (Claude Desktop, ChatGPT, Cursor, etc.), and authorize via OAuth in your browser.
- Use any AI tool.Your Tempreon layer is available across every connected client. As you work, Tempreon captures knowledge and refines instincts in the background.
For terminology specific to Tempreon (Core Imprint, Knowledge Vault, Forge Journey, Bridges, Instincts, and more), see theglossary.
- Transport.Streamable HTTP (not stdio). No local config file or local process to manage — Tempreon is a hosted MCP server. Connect with a single URL.
- Endpoint.https://api.tempreon.com/functions/v1/tempreon-mcp/mcp
- Registry.Listed on the officialMCP Registryascom.tempreon/tempreon.
- Authentication.OAuth 2.1 with PKCE. Dynamic client registration perRFC 7591— no pre-registration required.
- Per-user isolation.Each account is isolated at the database level via row-level security. Your data is never shared with other users or used to train AI models — see ourAI Use Policyfor the full statement.
Seedocs/install.mdfor a quick install snippet, or theuniversal install guidefor the canonical walkthrough.
Free and paid plans— paid from$19/month(Founders Circle pricing, effective rate when billed annually). Seetempreon.com/pricingfor current plans and details.
Tempreon is built byBriggs Ventures, LLC(d/b/a Tempreon). For the founder story and product origin, seetempreon.com/about. Five patent applications are pending on the underlying architecture, including knowledge classification, learning pipeline mechanics, decision rules, MCP-integrated identity, and cross-LLM portability.
Proprietary. All rights reserved. Patent pending. SeeLICENSEfor repository-specific terms. The Tempreon product and service are governed by theTerms of Service. This repository contains public documentation and integration assets only — Tempreon's product source code is not open source.
- General:team@tempreon.com
- Support requests:tempreon.com/support/contact
- Security disclosures:SECURITY.md
- Documentation:tempreon.com/support/docs
Local Work Model for AI agents that learns from real outcomes.
Auditable, self-improving knowledge & memory for AI agents over MCP — citation-enforced answers and a replayable why-trace, self-hosted on Postgres.
Self-hosted MCP server giving AI agents persistent memory — Markdown source of truth, hybrid BM25+embedding search, typed graph relations.
MCP (Model Context Protocol) server that exposes 70 tools spanning cognitive memory, working memory, sessions, agents, the L0–L3 knowledge hierarchy, orchestration tasks, and training pipelines. The server speaks stdio and is consumed by Claude Desktop, Claude Code, OpenCodex, and any MCP-aware client.
Set up a private AI memory vault in about a minute. No migration, no setup call, no card required.
mem0-mcp-server — exposes Mem0 persistent semantic memory as an MCP HTTP server; supports add/search/read/update/delete operations and semantic search for agent memory.
Personal memory layer for AI assistants. Store, search and recall preferences, decisions and facts — available from any MCP-compatible client.
A living memory that decays, learns, and evolves with your AI.
Hosted MCP memory across Claude Code, Cursor, ChatGPT and any MCP client. Community-hosted instance of the MIT-licensed MemPalace engine. EU-hosted, GDPR-compliant. Free tier with 200 memories.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
