engram-ms 1.8.0

Engram — AI agent memory system with SQLite+FTS5, MCP integration, and quality gates. Canonical distribution (formerly published as 'memorytrace').

Engram

Persistent memory for AI agents, backed by SQLite + FTS5.

Measured impact: across five realistic tool-output scenarios (587 KB of raw text), Engram persists ~8% on disk and surfaces just ~0.08% per recall call — a ~1250× reduction at the recall path. Search returns in <1 ms; intake in ~2 ms. See BENCHMARK.md for the full table and python scripts/benchmark.py to reproduce.

Install

pip install engram-ms

Optional extras:

pip install "engram-ms[llm]"
pip install "engram-ms[semantic]"
pip install "engram-ms[mcp]"
pip install "engram-ms[full]"

The memorytrace distribution name is the legacy alias still on PyPI: pip install memorytrace installs the same engine.

Simple CLI

The default CLI is engram. python -m engram is equivalent.

engram init
engram save "Minseong Jeong is the CTO of Galaxy Corp"
engram find "CTO"
engram who "Minseong Jeong"
engram remember "Minseong Jeong" "Interested in AI and robotics"
engram status

Advanced CLI

Use engram-advanced when you need structured options, JSON output, or a custom DB path.

engram-advanced --db ~/.engram/memory.db search "Galaxy Corp" --max-results 5
engram-advanced --json health

Python SDK

from engram.integrations.sdk import EngramSDK

with EngramSDK() as sdk:
    sdk.start_session("assistant")
    sdk.store("Minseong Jeong is the CTO of Galaxy Corp")
    sdk.add_fact("Minseong Jeong", "Interested in AI and robotics")
    result = sdk.search("Galaxy")
    print(result.to_agent_context())

Source Checkout Compatibility

A repo-local python mem ... wrapper is kept for backward compatibility in source checkouts. It forwards to the same simple CLI as engram, but it is not installed as a packaged console script.

Related packages

The engram namespace on PyPI is reserved for small, focused tools that share this memory model. Sibling packages currently published from this workspace:

Package	Status	Purpose
engram-ms	canonical (0.0.x placeholder, full engine in 0.1.x)	The engram-named distribution — preferred install
memorytrace	legacy alias	The original distribution name; same engine

Docs

• docs/04-usage-guide/01-quickstart.md
• docs/01-project-analysis/05-cli-commands.md
• docs/01-project-analysis/09-setup-guide.md

Workspace Skill

A workspace-local skill package for generating a static project wiki tree lives at .agents/skills/engram-tree.

Generate the site with:

python tools/run_engram_tree.py
python .agents/skills/engram-tree/scripts/build_engram_tree.py --project-root . --output-dir dist/engram-tree

Install the skill for Claude Code and Codex with:

python tools/install_engram_tree_skill.py --dry-run
python tools/install_engram_tree_skill.py --create-missing

Bridge to Claude Code / Codex CLI (engram-ctx)

After pip install engram-ms, register engram-ctx as a memory bridge in your CLI of choice:

# Claude Code
engram-ctx install claude-code

# Codex CLI
engram-ctx install codex

Both installers are idempotent. They register:

• MCP server engram exposing engram_ctx_index, engram_ctx_search, engram_ctx_stats, engram_ctx_doctor, engram_ctx_purge (in addition to the existing memory_* tools).
• Lifecycle hooks SessionStart, PreToolUse, PostToolUse, UserPromptSubmit, Stop. Large tool outputs (>500 chars) are auto-indexed into tool_observations (PII-masked, head/tail truncated). Recall via engram_ctx_search.
• Skill engram-context with caveman-style output compression and routing rules.

For non-hook MCP clients (Cursor, Copilot CLI, OpenCode), use engram.integrations.mcp_middleware.EngramContextMiddleware directly.