v1.4.0

This release turns mcp-brain from a local MCP memory layer into a benchmarked, measurable awareness system for Claude Code and MCP-compatible coding agents.

Highlights

• SWE-bench Full benchmark: evaluated on 2,294 real GitHub bug-fix tasks.
• 63.4% Hit@10 file localization with BM25 + code graph + optional semantic reranking.
• Zero LLM cost for retrieval and file prediction.
• Sub-100ms prediction pipeline in the default local-first flow.
• Token-efficient context loading: compressed project awareness in ~100 tokens instead of repeated repo exploration.
• Lifecycle-aware memory: active, suspect, stale, and superseded decisions.
• Team-aware coordination: soft claims, conflict detection, and ownership tracking.
• Improved documentation with architecture, memory hierarchy, prediction pipeline, benchmark results, and token-efficiency diagrams.

Why this matters

Claude Code does not need more raw context. It needs structured awareness of the repo, the team, and past decisions.

mcp-brain v1.4.0 provides that awareness locally through SQLite, BM25, code graph expansion, optional semantic reranking, and MCP tools that Claude can call when starting a session or working on a ticket.

Benchmark summary

Metric	Top-1	Top-3	Top-5	Top-10
Hit	24.5%	43.4%	53.7%	63.4%
Recall	20.1%	36.6%	46.1%	55.8%
MAP	24.5%	28.4%	30.4%	31.8%

Evaluated on SWE-bench Full with 2,294 instances, test files excluded by default.

Recommended install

pip install -e ".[all]"

v1.3.0

Complete persistent memory and team coordination for Claude Code.

Highlights

• Persistent SQLite memory with lifecycle (active, suspect, stale, superseded)
• Git-aware staleness detection
• Raw capture + promotion rules (signal over noise)
• Semantic superseding via Jaccard similarity
• GitHub ticket workflow with conflict detection
• AST-based file indexing with explainable predictions
• Soft-claims system shared via git
• Storage split (.brain/shared / .brain/local)
• 13 MCP tools + one-command project setup