Give your coding agents a memory that never forgets.

A single map of what Memtrace does: indexing, code intelligence, temporal memory, Cortex decision memory, Fleet coordination, worktree overlays, code review, API topology, watching, CLI, skills, and configuration.

One binary, three moving parts: the MemDB storage sidecar, the workspace runtime on :3030, and the Cortex decision-memory sidecars — plus how a second MCP client attaches instead of duplicating the stack.

Hybrid BM25 + semantic search over your indexed graph, plus token-lean source windows and a repo style fingerprint.

The supported Memtrace command surface for installing, running, configuring, and troubleshooting the local workspace runtime.

memtrace mcp exposes the code-intelligence graph to AI coding agents over the Model Context Protocol — 78 tools, stdio or HTTP, adapting its response shape to whichever client connects.

The validated reference for every environment variable Memtrace reads — runtime and ports, MemDB, embeddings, MCP, Cortex, git hooks, install, telemetry, and licensing — grouped with defaults.

What Memtrace ships home, what it never touches, and how to turn any of it off — four content-free, opt-out streams and a hard list of things that never leave your machine.

Community, Pro, Pro+, and Teams: what the graph-query quota actually meters, how the meter is enforced, and why multi-device use is never a problem.

Symptom-first fixes for the failures people actually hit: ONNX load errors, a "stuck" first run, port conflicts, pre-AVX2 CPUs, a tripped embed circuit breaker, deferred installs, and degraded auth.