@neruva/mcp 0.25.0 → 0.25.1

package/README.md

@@ -1,9 +1,34 @@
 # @neruva/mcp
 
-MCP server for [Neruva](https://neruva.io) — 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.
+MCP server for [Neruva](https://neruva.io) — 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 / Goose in one line.
 
 > **For Claude Code users:** see [neruva.io/claude-code](https://neruva.io/claude-code) for the 30-second install + first-queries to try.
 
+## The 5 benchmark crowns
+
+| Benchmark | Score | Position |
+|---|---|---|
+| **LongMemEval** (end-to-end memory QA) | **93.3%** | top-4 globally, +22pp vs Zep |
+| **DFAH compliance** (det × acc) | **100% / 88%** | first system to break the trade-off, 2.75× prior SOTA |
+| **Hi-ToM** (higher-order theory-of-mind) | **84.58%** with **99.58%** byte-identical replay | 15× GPT-4 at order 4 · depth-1000 nested beliefs proven |
+| **AMA-Bench** (causal + memory reasoning) | **63.3%** | new SOTA, +6pp over paper baseline |
+| **Latency** (p95 cache-hit) | **80ms** | 2.5× faster than Mem0 |
+
+Full breakdown: [neruva.io/benchmarks](https://neruva.io/benchmarks). **The only memory stack hitting world-class scores on memory, reasoning, AND audit determinism — simultaneously.**
+
+## What's new in 0.25.0 — `qa_optimized` + `recency_first` graduated
+
+The LongMemEval 93.3% recipe lifted into the substrate. `agent_recall` now accepts two opt-in flags (both default off, backwards compatible):
+
+- **`mode="qa_optimized"`** — 3× over-fetches the candidate pool and BM25-RRF-fuses (k=60) over the text. Lifts records whose text contains specific entity tokens (brand names, amounts, dates, IDs) that pure semantic embedding under-weights. Worth **~+20pp** on memory-QA benchmarks.
+- **`recency_first=true`** — re-sorts returned records by `ts` desc after ranking. Use for knowledge-update questions where the most recent statement wins over older contradictory ones.
+
+Pair them for the strongest memory-QA recipe. Auto-router in `neruva-record` 0.19+ suggests both automatically when the intent classifier hits `recall_extended`.
+
+## What's new in 0.24.0 — Code-graph bare-name resolution
+
+`code_kg_module_of` and `code_kg_class_of` now accept short identifiers like `bind` (no module prefix). When the substrate sees an unqualified name, it falls back to a 1-hop `called_by` lookup to find the likely qualified target. Drops the friction of remembering full dotted paths inside Claude Code.
+
 ## What's new in 0.23.0 — Native hook binary (sub-100ms cache-hit latency)
 
 We benchmarked Neruva against the 2026 agent-memory field and made the hook **faster than Mem0** without giving up any of the capability surface.
@@ -151,7 +176,7 @@ The substrate now exposes the full **9-level cognitive ladder**. Every primitive
 | 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.
+**~80 tools** across Records, KG, Causal, Analogy, CBR, Blend, federated `agent_*`, the 9 cognitive primitives above, self-introspection.
 
 ### Why this is unique
 
@@ -206,6 +231,18 @@ env = { NERUVA_API_KEY = "..." }
 { "mcpServers": { "neruva": { "command": "npx", "args": ["-y", "@neruva/mcp@latest"], "env": { "NERUVA_API_KEY": "..." } } } }
 ```
 
+### Goose (`~/.config/goose/config.yaml`)
+```yaml
+extensions:
+  neruva:
+    type: stdio
+    cmd: npx
+    args: ["-y", "@neruva/mcp@latest"]
+    env:
+      NERUVA_API_KEY: nv_...
+```
+For Goose auto-pilot (pattern-C route / reflect / extract via your LLM): `pip install neruva-goose`.
+
 ## 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?"

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@neruva/mcp",
-  "version": "0.25.0",
+  "version": "0.25.1",
   "description": "MCP server for Neruva agent memory + reasoning substrate. INSTALL: npx -y -p @neruva/mcp@latest neruva-mcp (the -p ... bin form is required because the package ships two bins: neruva-mcp + neruva-record-hook). v0.23 BUNDLES neruva-record-hook native binary (Rust, ~145-340KB) for all 6 platforms (Win/Mac/Linux x amd64/arm64). Hook talks to long-lived Python daemon over TCP localhost, daemon holds warm httpx pool + TTL cache: cache-hit p95 ~80ms, warm avg 167ms -- faster than Mem0 (200ms p95) with full cognitive surface (5 KG engines + Pearl do-operator + HD analogy + CBR + ToM + EFE planning + replay). v0.22 added AUTO-PILOT (agent_route_intent_prompt + agent_reflect_prompt + auto-extract on records_ingest). Plus typed Records, 5-engine KG, federated agent_remember/recall/context, counterfactual rollouts, rule induction, replay, code_kg_* navigation, .neruva V3 container. Pattern-C throughout: substrate stays $0/call.",
   "license": "MIT",
   "type": "module",