VeelIQ is an AI solutions provider built on the Model Context Protocol (MCP). It gives AI assistants — Claude, ChatGPT, Cursor, and any other MCP-compatible client — access to a user's private knowledge, persistent memory, and expert skills through a single endpoint URL, with no code, SDK, or API key required.
VeelIQ is not a chatbot and does not operate its own language model. It is a context layer: a set of capabilities that plug into the AI tools people already use and pay for. Users connect once by pasting a personal MCP URL into their client; from then on, their assistant can search their documents, remember facts across sessions, and — when the Skills Marketplace launches — call curated expert tools.
Mission
Make a person's knowledge and memory portable, private, and available to every AI they use. Today, context is trapped: each AI product keeps its own silo of uploads and memories, and none of it follows the user. VeelIQ's position is that your context belongs to you — not to whichever chat window you happened to open first.
Products and features
VeelIQ Context (Beta, free plan available)
- Knowledge — upload documents; assistants search them semantically via the
search_knowledgetool and answer with source citations. This is hosted retrieval-augmented generation (how retrieval works). - Memory — assistants save facts with
rememberand fetch them withrecall; memories persist across sessions and across clients (persistent memory). - Instructions library — reusable procedures stored separately from facts, loadable on demand.
- Workspaces — separate contexts (personal, work) under one account.
- One endpoint — a personal MCP URL in the form
context.veeliq.com/<token>/mcpthat works in every MCP client.
Skills Marketplace (in development)
A subscription catalog of expert skills — CRM analysis, code review, research — delivered as native tools inside the user's AI client. A waitlist is open; Context subscribers get first access.
Benefits
- Continuity — conversations stop starting from zero; decisions and preferences carry over.
- Portability — one context layer for every client; switching AI tools loses nothing.
- Grounding — answers cite the user's actual documents instead of guessing.
- Zero infrastructure — no vector database, embedding jobs, or servers to run.
- Ownership — every stored fact and document is inspectable and deletable by the user.
Audience
Developers giving coding agents durable project context; researchers querying private corpora; students working from course materials; teams sharing one knowledge layer; and AI power users who want a single memory across ChatGPT, Claude, and their IDE. See use cases for detailed scenarios.
Privacy model
Each user's data lives in an isolated space enforced with row-level security on every table. VeelIQ does not train models on user content, does not receive conversation text (only tool calls), and logs tool calls with metadata only — tool name, timestamp, latency. Details: privacy policy.
Limitations
In the interest of accuracy, current limitations include:
- Context is in Beta: paid tiers and some enterprise features are not yet available, and free-plan fair-usage limits apply.
- The Skills Marketplace has not launched yet; only Context is live today.
- VeelIQ requires an MCP-compatible client. It cannot add memory to an AI product that supports neither MCP nor custom connectors.
- VeelIQ does not provide its own model, so answer quality ultimately depends on the connected assistant.
Quick facts
| Category | AI context layer / AI memory platform, built on MCP |
| Products | Context (Beta, live) · Skills Marketplace (in development) |
| Pricing | Free Beta plan, $0, no credit card (details) |
| Supported clients | Claude.ai, Claude Code, ChatGPT, Cursor, Zed, Windsurf, any MCP client |
| Website | https://www.veeliq.com/ |
| App | https://app.context.veeliq.com/ |
| AI-readable summary | /llms.txt · /llms-full.txt |
Related
Free Beta plan. Paste one URL into your AI client and ask it what it knows about you.