The memory layer
your agents are missing.
ContextQ gives AI coding agents persistent, searchable memory that compounds across conversations, projects, and tools. Built on Postgres + pgvector + Elasticsearch with PKM-grade memory evolution.
31
MCP tools
6
Agent clients
RRF
Hybrid search
# Save a decision once, available everywhere
$ /ctq save "Auth flow uses Zitadel JWT, RS256 only"
saved · ctx_4f2 · type=reference
# Hybrid retrieval the next session, the next project
$ /ctq search "how do we sign tokens"
full-text + vector + RRF fusion
3 results · 92ms · rank=ctx_4f2
# Synthesize across stored knowledge
$ /ctq dream
clustering 47 entries...
synth 3 MOCs · 12 supersedes · 4 archived
Works with the agents you already use
Features
Memory that thinks, not just stores.
Vector DBs give you embeddings. ContextQ gives you a second brain that clusters, links, and prunes itself.
Dream synthesis
LLM-assisted passes cluster related entries, write durable summaries, and archive the originals — keeping your memory atomic and discoverable. Think weekly retrospective for your second brain.
Hybrid search
Full-text (Postgres tsvector + Elasticsearch BM25) fused with pgvector cosine via Reciprocal Rank Fusion. Find context fast, even with vague queries.
Typed links
Wikilinks resolve to typed edges (supersedes, contradicts, derived_from). Memory evolution auto-archives outdated entries.
31 MCP tools, one endpoint
Drop the HTTP MCP URL + your API key into Claude Code, Cursor, Codex, Gemini, Windsurf, Cline. Every agent gets the same memory.
Tamper-evident audit chain
Every write is hash-chained. Verify integrity on demand, export CSV, set per-tenant retention. Tenant-isolated row-level security + AES at rest.
How we compare
Not just a vector DB. Not just a memory API.
ContextQ is the only stack that combines hybrid retrieval, PKM-grade evolution, and developer-tool ergonomics.
| Capability |
ContextQ
| Mem0 | Zep | Pinecone |
|---|---|---|---|---|
| Hybrid full-text + vector + RRF | partial | partial | — | |
| Dream / synthesis (LLM-assisted) | — | — | — | |
| Typed links + MOC clustering | — | — | — | |
| Memory evolution (auto-archive) | partial | — | — | |
| MCP native (31 tools) | — | — | — | |
| Tamper-evident audit chain | — | — | — | |
| Bi-temporal lifecycle | — | — | — | |
| Entry-level price | Free / $19 | $19+ | $99+ | $70+ |
Comparison reflects publicly available pricing and feature pages as of May 2026. Independent assessment, not affiliated.
Get started
Three steps. Five minutes.
Two install paths — universal MCP, or the /ctq skill for Claude Code power users.
Create an API key
Sign up free, no credit card. Create a tenant, generate a scoped API key from the dashboard.
Connect your agent
Paste the MCP endpoint into Claude Code, Cursor, Codex, Gemini CLI, Windsurf, or Cline. Tools auto-discover.
Save and search
Your agents now share memory across sessions, projects, and editors. Decisions compound instead of evaporating.
Drop-in config
.mcp.json{
"mcpServers": {
"contextq": {
"type": "http",
"url": "https://api.contextq.dev/mcp",
"headers": {
"Authorization": "Bearer ctq_••••••••"
}
}
}
} Works the same in Cursor, Codex, Gemini, Windsurf, Cline.
Tool surface
31 tools. Seven groups. One memory layer.
Full CRUD, PKM operations, ingest, events, admin — every capability the agent needs.
Pricing
Start free. Scale when ready.
All plans include hybrid search, MCP integration, audit chain, and tenant isolation. Cancel anytime.
Pro
For solo builders shipping fast
$19 /mo
- 5,000 contexts
- 1 user
- Unlimited workspaces
- CSV export
- API keys
- Webhooks
Team
For teams scaling memory together
$79 /mo
- 25,000 contexts
- 5 users
- Unlimited workspaces
- CSV export
- API keys
- Webhooks
- Team mode
- Priority support
Enterprise
For organizations with custom needs
Custom
- Unlimited contexts
- Unlimited users
- Unlimited workspaces
- Team mode
- Priority support
- SSO / SAML
- Audit log export
All plans include tenant isolation, AES-256 encryption at rest, and the tamper-evident audit chain.
Stop teaching your agents
the same thing twice.
Free for your first 100 contexts. No credit card. Five minutes to set up.