neruva-mcp 0.19.0

MCP server for Neruva agent memory + reasoning substrate. Records, 5-engine KG (OPB / quorum / multishard / feature-bundle / Hadamard), federated agent_remember/recall/context, Pearl do-operator, HD analogy, CBR, concept blend. Cognitive primitives: depth-unlimited theory of mind, counterfactual rollouts, schema lifting, EFE planning, continual learning, hierarchical chunking, rule induction. Snapshot/restore replay. .neruva container. Drop into Claude Code / Cursor / Codex / Gemini CLI. Sub-100ms p95.

neruva-mcp

MCP server for Neruva — memory + reasoning substrate for AI agents. Knowledge graph (5 engines), Pearl do-operator, HD analogy, episodic CBR, deterministic replay. Drop into Claude Code / Cursor / Codex / Gemini CLI in one line.

For Claude Code users: see neruva.io/claude-code for the 30-second install + first-queries to try.

What's new in 0.19.0 — pattern C postmortem + routing nudges

• agent_postmortem_prompt tool (Pattern C mistake learning). Returns the canonical system prompt for failure-classification: your LLM runs it on a tool-failure context, emits a structured JSON shape (failure_class, root_cause, corrective_plan, is_agent_mistake), and you push the result to records_ingest(kind="mistake", ...). The substrate stays $0/call + LLM-free — your existing LLM does the work. Replaces the killed Magistral-backed /v1/agent/postmortem.
• Tool-description routing nudges. All 17 high-leverage tools (records_*, agent_recall/context/remember, hd_kg_query, hd_analogy, hd_causal_query, agent_counterfactual_rollout, agent_model_belief(_add), agent_postmortem_prompt, agent_register_action, agent_plan_efe, agent_induce_rule, agent_extract_schema, agent_hierarchical_decode) now lead with "Call this when..." so LLMs route into the right substrate primitive without explicit prompting.
• extract="managed" on agent_remember removed. Pairs with the substrate's "no server-side LLM calls" architecture decision: use extract="byo" with caller-side triple extraction via hd_kg_extraction_prompt.

What's new in 0.18.3 — depth-unlimited theory of mind + 125× faster cleanup

• Theory of mind is now depth-unlimited (v0.5.4 substrate fix). Position-tagged at every chain index via non-commutative permutation binding. Inner-position swaps correctly reject; recursive self- reference (same agent at multiple chain positions) works natively.
• Cleanup acceleration via FAISS-binary popcount. OPB query stage 2 uses SIMD popcount over sign-quantized atoms with deterministic float32 cosine rerank. Substantially faster on warm queries; replay bit-identical.
• 551× compression on stored OPB pages (rank-12 SVD). Persistence blobs that were >100 MB now fit in under 1 MB at perfect recall on round-trip.

The 9-level cognitive ladder — no LLM vendor ships rows 3-9

The substrate now exposes the full 9-level cognitive ladder. Every primitive runs sub-100ms, deterministic from seed, behind one MCP install.

#	Capability	MCP tool(s)	Frontier LLM equivalent
1	Vector retrieval (OPB pages + spectral routing)	records_query(engine="opb")	Pinecone/Zep (Level 1 only)
2	KG + Pearl do-operator + HD analogy + CBR	hd_kg_* · agent_causal_query · hd_analogy · hd_cbr_*	nobody
3	Theory of Mind (nested belief)	agent_model_belief_add · agent_model_belief	hallucinates at depth
4	Counterfactual rollouts ("what if k → a'?")	agent_counterfactual_rollout	confabulates
5	Schema lifting (analogical pattern matching)	agent_extract_schema	needs fine-tuning
6	Active Inference planning (Friston EFE)	agent_register_action · agent_plan_efe	not a primitive
7	Few-shot rule induction	agent_induce_rule	fine-tune (many examples)
8	Persistent rule storage	agent_persist_rule · agent_recall_rule	re-feed demos every recall
9	Continual learning, zero forgetting	agent_continual_train · agent_continual_predict	catastrophic forgetting
+	Hierarchical chunking (recursive L^K decode)	agent_hierarchical_add · agent_hierarchical_decode	not a primitive

~90 tools across Records, KG, Causal, Analogy, CBR, Blend, Vector memory, federated agent_*, the 9 cognitive primitives above, self-introspection.

Why this is unique

Every primitive in rows 3-9 is a graduated, production-shipped engine. No published memory vendor offers more than rows 1-2. Substrate-augmented small LLMs can match frontier-class agentic capabilities at a fraction of the cost per recall.

Install

# In Claude Code (any directory, user scope):
claude mcp add-json neruva '{"command":"npx","args":["-y","@neruva/mcp@latest"],"env":{"NERUVA_API_KEY":"nv_..."}}'

Or one-line install via npx for any MCP host:

npx -y @neruva/mcp@latest    # one-off
npm i -g @neruva/mcp         # then `neruva-mcp`

Get an API key at https://app.neruva.io (free tier, no credit card).

Wire into a host

Claude Code

claude mcp add-json neruva '{"command":"npx","args":["-y","@neruva/mcp@latest"],"env":{"NERUVA_API_KEY":"..."}}'

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "neruva": {
      "command": "npx",
      "args": ["-y", "@neruva/mcp@latest"],
      "env": { "NERUVA_API_KEY": "..." }
    }
  }
}

Codex (~/.codex/config.toml)

[mcp_servers.neruva]
command = "npx"
args = ["-y", "@neruva/mcp@latest"]
env = { NERUVA_API_KEY = "..." }

Gemini CLI (~/.gemini/settings.json)

{ "mcpServers": { "neruva": { "command": "npx", "args": ["-y", "@neruva/mcp@latest"], "env": { "NERUVA_API_KEY": "..." } } } }

The substrate, in one paragraph

Five layers, one API. Records = typed agentic events (decisions, mistakes, tool_calls, llm_turns; auto-embedded at D=1024). Knowledge Graph = mutable structured state across 5 engines, sub-ms cosine retrieval, matrix-power N-hop derive. Causal = Pearl's do-operator (observation vs intervention arithmetically distinct). Analogy = a:b::c:? in HD feature space. Concept Blending = provenance-preserving merge of multiple memories. CBR = factored episode store. The new federated agent_* layer (agent_remember / agent_recall / agent_context) routes across all substrates so a single call handles "where does X store, and how do I get it back?"

Deterministic from a seed. Replayable bit-exactly. Portable as .neruva containers — your data is yours.

Three-line LangChain integration

# pip install neruva-langchain
from neruva_langchain import NeruvaChatMessageHistory
history = NeruvaChatMessageHistory(namespace="user_alice")
# wire into any chain that takes BaseChatMessageHistory

Same pattern: neruva-langgraph (BaseCheckpointSaver + BaseStore), neruva-crewai (Storage interface + 3 memory flavors).

Auto-record for Claude Code

pip install neruva-record && neruva-record-install

Every Claude Code session lands in your Neruva account: tool calls, chat turns, secrets-redacted client-side, queryable across sessions.

Why use this over a vector DB or Zep

	Vector DB	Zep	Neruva
KG engines	0	1	5
Causal queries (Pearl do-operator)	❌	❌	✅
Provable replay (deterministic snapshot/restore)	❌	❌	✅
Anomaly detection (quorum disagreement)	❌	❌	✅
Federated context (records+KG one call)	❌	partial	✅
Portable container	❌	❌	✅ .neruva
p95 latency	varies	varies	<100ms
Cost per recall vs context-stuffing	varies	varies	dramatically lower

Auth

Set NERUVA_API_KEY in env. NERUVA_URL defaults to https://api.neruva.io.

Optional: NERUVA_AUTO_RECORD=namespace[:ttl_days] — every tool call this agent makes auto-records into the named records namespace. Fire-and-forget, never blocks or breaks the call.

Update flow

The startup banner prints when a newer version is available:

[neruva-mcp] update available: you have 0.16.0, latest is 0.16.1.

If registered with @neruva/mcp@latest, a Claude Code restart auto-updates.

License

MIT