Different products. Different use cases.
This table links to supermemory's own documentation for each detail. Follow the source links for their latest features.
Swipe horizontally to compare all three columns →
| Dimension | ContextStream | supermemory |
|---|---|---|
| Product center | A complete AI workspace with agent orchestration, coordination, decision learning, precise code search and full code graphs, also available through MCP. | A memory platform for AI tools and applications, with shared spaces, MCP access and interactive memory workflows. supermemory docs ↗ |
| MCP access and editors | MCP server connects Cursor, Claude Code, Cline, and Continue to project memory. Code search and structured tools included. | Hosted MCP with OAuth connects compatible assistants, including Claude Code, Cursor and Codex. MCP documentation ↗ |
| What is remembered | Decisions, lessons, plans, handoffs, code search results, dependency graphs, and structured project knowledge. | Source documents and extracted memories, with search, save, forget and file upload workflows. Memory model ↗ |
| Code search and graph | Code search plus full dependency, call-path, impact and quality analysis. Published useful-file Recall@10 is 99.38% on the August 1 code-search evaluation. | The linked MCP documentation describes semantic memory search and a graph of documents and memories. Evaluate code-specific analysis against your project requirements. Search docs ↗ |
| Team and project scope | Workspaces, projects, team roles, and project-level access controls. Memory scoped to the right project and team members. | Users can organize memories and control access through spaces. Spaces docs ↗ |
| LongMemEval-S accuracy | 90.0% on LongMemEval-S (ContextStream-published). View benchmarks → | 85.4% on LongMemEval-S (vendor-published by supermemory). supermemory benchmarks ↗ |
Choose for the product center that fits.
You want a memory API or second brain.
supermemory is the natural fit when you need a general-purpose memory layer, a second brain for personal knowledge, or an API you can integrate into your own agent or application.
Your next Cursor session should already know the decision.
ContextStream is built for coding projects. Code search, decisions, lessons, plans, handoffs, dependency graphs, and continuity across Cursor and Claude Code sessions should arrive as one layer.
Test with Starter. Scale with Pro or Elite.
Starter includes the full platform and 10,000 credits every month. Pro is $19/month with 25,000 credits. Elite is $49/month with 100,000 credits. Every plan includes the same agent orchestration, memory, search and code intelligence.
Read the method, not just the score.
ContextStream reports 90.0% accuracy on LongMemEval-S and 99.38% Recall@10 in its published code-search evaluation. These are ContextStream measurements on ContextStream tasks.
Evaluate ContextStream with your project.
Connect Cursor or Claude Code, index one repository, and test whether the next session retrieves a real decision and the code it affects.