Memory + reasoning substrate for AI agents.
Drop persistent memory into Claude Code, Cursor, LangChain, or any MCP-aware agent in one line. Typed agentic events, federated agent_remember/recall/context, customizable context blocks. 5 KG engines, Pearl do-operator, 13 cognitive primitives no frontier LLM matches (counterfactual rollouts, theory-of-mind, EFE planning, few-shot rule induction). Sub-100ms recall, deterministic replay.
All 13 cognitive primitives free to try — 30/day, no credit card.
Claude Code agent that remembers
Drop neruva-record into your Claude Code hook. Every session, every decision, every mistake — recallable across projects.
Typed agentic events
decisions, mistakes, tool_calls, llm_turns — auto-embedded at D=1024 with one federated agent_remember call. Smart routing across records + KG.
Cross-project semantic recall
Sub-100ms search over months of agent transcripts. Customizable context blocks: entity-grounded, deterministic, $0/call (vs Zep per-call).
Knowledge graph that scales
Five engines including a 3-shard quorum mode that surfaces adversarial shard tampering. N-hop derive in a single matrix-power op.
Causal reasoning, not RAG
Pearl do-operator over your memory. "What if X had happened" returns a different answer than "X happened" — arithmetically distinct, not a paraphrase.
Theory of Mind, nested belief
Alice believes Bob believes Carol believes X. Position-tagged binding keeps depths separable so each layer of "believes that" is independently queryable.
Counterfactual rollouts + EFE planning
What if at step k the agent had taken action a' instead? Replayable, deterministic. KL-optimal plan selection on caller-owned dynamics.
Few-shot rule induction + continual K-gram
Learn a named transformation rule from a few demos. Sharded K-gram next-token predictor with integer-add accumulation — no catastrophic forgetting.
Deterministic replay from seed
Bit-identical reruns. Auditable, exportable, regulator-friendly. The compliance story nobody else ships.
Secrets redaction client-side
14-pattern leak guard before bytes leave your machine. Recalled context wrapped in injection-guard tags. Built-in.
Your data stays yours.
.neruva file. Yours forever.Get a free API key
Sign in at neruva.io/dashboard. Free tier: 10k records, 1k recalls/mo, no card required.
Install the MCP server
One line in your Claude Code / Cursor config. Or pip install neruva-mcpfor Python, @neruva/mcp on npm.
Your agent remembers
52 tools across records, 5 KG engines, causal, analogy, CBR. Recall is sub-100ms. Build whatever agent on top.
What other memory vendors can't do.
Zep wins on temporal KGs. Pinecone Nexus is a context compiler. Anthropic Memory is key-value persistence. Neruva is the only substrate that stacks KG + causal + analogy + episodic in one API, sub-100ms, deterministic from a seed.
They store temporal facts. Neruva adds Pearl do-operator (causal), HD analogy parallelogram, and CBR episodes — reasoning, not just recall. Export as one portable .neruva file. No lock-in.
They're a layer. Neruva is a substrate — records + KG + causal + analogy + episodic, one API key, one billing ledger. Hybrid entity-grounded + cosine retrieval beats cosine alone on multi-hop questions.
That's key-value persistence inside one vendor's SDK. Neruva is vendor-neutral memory infrastructure — works with Claude, OpenAI, open-weights, your own. Bring your LLM, we handle the brain.
~3,000× cheaper per recall vs cramming the conversation back into the prompt. Sub-100ms p95 (mostly network). Server-side compute is microseconds — every op is integer multiply / sign / cosine.
Stop bolting on a vector DB.
Drop in the substrate.
Free tier: 10k records, 1k recalls/mo, no card. Indie $20/mo unlocks 1M records + all KG engines. See pricing →