Piia Engram

data-ai MCP Server

Local-first AI memory you can see, edit, and override — portable across Claude Code, Codex, Cursor, Windsurf, and other MCP coding tools.

Verified
data-aidata-ai
4 views161 stars14 forksAGPL-3.0

Why This Matters

Discovered via github-topic:model-context-protocol and last synced 2w ago.

Verified
Source
github-topic:model-context-protocol
Stars
161
Last synced
2w ago
Install
Check source

Install

Install instructions not detected yet

Check the source repository for the latest setup steps.

View source instructions
102
Tools
0
Resources
0
Prompts
Standard I/O
Transport

Available Tools (102)

get_preferences

Read communication and workflow preferences

bulk_add_knowledge

Add multiple lessons or decisions in one call

get_related_knowledge

Follow links between knowledge items

Codex

Implementation, testing, documentation assistance

update_identity

Update profile, preferences, or quality standards

get_lessons

List reusable lessons learned

archive_knowledge

Archive a lesson or decision by ID

export_knowledge_report

Active lessons/decisions grouped by domain/month (Markdown).

start_project

Start a project with inherited knowledge

Price

Free, AGPL-3.0

get_project_context

Read a saved project snapshot

get_decisions

List key decisions; `thread_seed_id` / `history_question` reconstruct decision threads and revision history

review_knowledge

Mark a knowledge item as reviewed

request_outline_review

Owner-gated export: generate an interactive local HTML review page

Free

Free / Cloud tiers

get_user_context

**Startup** — Load identity + knowledge at session start (supports `token_budget` for context size control)

get_domains

Read domain experience stats

merge_knowledge

Merge a duplicate into the primary item

apply_review

Process review results (promote/archive staging items)

OpenClaw

SOUL.md / MEMORY.md / USER.md import and export

Encryption

Optional field-level AES-256-GCM for supported profile fields; local files are plaintext JSON/Markdown by default

wrap_up_session

**Session end** — Save insights + sync at session end

get_knowledge_inheritance

Build cross-project knowledge starter pack

link_knowledge

Create a bidirectional link between items

export_engram

Owner-gated export: write a full backup (`format="openclaw"` for OpenClaw-compatible files)

Usable

## Comparison

Contributor

Role

add_lesson

Store a reusable lesson learned

get_profile

Read user profile (safe=true by default)

list_projects

List saved project snapshots

unlink_knowledge

Remove a bidirectional knowledge link

import_engram

Owner/admin import: use `dry_run=True` first for a metadata-only merge/conflict preview (`format="openclaw"` supported)

Engram

Claude Memory

add_decision

Record a key decision with reasoning

get_work_style

Read work style preferences

extract_session_insights

Extract lessons and decisions from session text

get_knowledge_overview

Knowledge digest, health report, stale checks

export_engram_to_openclaw

Export OpenClaw-compatible files

Mem0

Letta (MemGPT)

Area

Current State

get_relevant_knowledge

Find knowledge relevant to current project

get_trust_boundaries

Read data access boundaries

ingest_notes

Parse free-form notes into structured knowledge

find_similar_knowledge

Find similar items by content

Local

Vector DB + Mem0 Cloud

get_identity_card

Curated Markdown: who you are, how you work, recent verified lessons/decisions. Excludes raw config-file knowledge and caps recent items.

get_quality_standards

Read quality expectations

update_knowledge

Update a lesson or decision by ID

get_stale_knowledge

List items that need review

get_audit_log

Get recent audit log entries

MCP-native

✅

import_engram_from_openclaw

Import OpenClaw-compatible files

Storage

Local JSON in `~/.engram/`

Cursor

MCP over stdio

Hermes

MCP over stdio

Cline

MCP over stdio

Augment

MCP over stdio

Zed

MCP over stdio

Trae

MCP over stdio

Claim

Public evidence

memory_store

**Writeback** — Unified write endpoint: routes to add_lesson / add_decision / add_playbook by `kind`

add_playbook

Record an operational playbook (multi-step procedure with trigger keywords)

get_recall

Return one structured identity + recent activity + relevant knowledge recall payload

save_project_snapshot

Persist project state for future sessions

get_recent_context

Recover lost session context after restart

get_daily_log

Read a human-friendly project timeline for a day

get_resume_brief

Build a cross-session/cross-tool resume brief

doctor

Run memory system self-diagnosis

Tool

Purpose

user_portrait

`action`: get / save / compare the AI-maintained user portrait

manage_relation

`action`: link / unlink — manage typed relations between knowledge items (decision threads)

read_web_content

Fetch a user-provided URL: prefers a local sidecar if running, otherwise uses the self-contained built-in reader (`pip install "piia-engram[reader]"`)

register_tool

Optional local integration governed write: register a local tool, runtime, or CLI to the environment map

preview_context_governance

Advanced owner-gated preview: build safe-context, freshness/conflict, replay, or evidence proposals without applying changes

explore_knowledge

Knowledge graph exploration via `mode`: related, similar, merge_candidates

find_tool

Optional local integration: look up a registered local tool by name

get_playbooks

Playbook reads via `mode`: list, get (full content), recent, management (incl. archived/deleted metadata)

Feature

piia-engram

Tier

Tools

list_tools

Optional local integration: list registered local tools (optionally filter by category)

manage_playbook

Playbook lifecycle via `action`: update, archive, delete, restore (mutations stay confirm-gated)

get_permission_profile

View all callers' trust levels and access boundaries

17

Identity, knowledge read/write, project context, session recovery, diagnostics

save_agent_context

Save AI session checkpoint (also runs automatically)

playbook_execution

Guided execution via `action`: prepare a step plan, update_step, status rollup (passive reference; no auto-execution)

confirm_knowledge

Owner-only confirmation stamp via human, test, or anchor provenance

review_staging

Staging review hub via `action`: list pending, batch decisions, review_item, apply_text review results

manage_caller_trust

Owner/admin `action`: grant / revoke a caller's trust level

40

Knowledge review, merge, decision threads, permission management, tools registry, import/export, audit

list_agent_sessions

Browse saved session records across tools

onboard_repo

Owner-only repo scan: create staging repo-fact candidates from anchors

export_feedback_report

Maintainer feedback: generate an anonymous aggregate feedback report

refresh_quick_context

Refresh local `quick_context.md` snapshot for offline/cross-tool use

onboard_accept

Owner-only accept: validate a candidate anchor and promote it to verified

apply

rollback

check_anchors

Owner-only revalidation for existing anchor-backed facts

Level

Signal

Want

Tool

search_knowledge

**Retrieval** — Search lessons, decisions, and playbooks (supports `filters_json` for domain/tier/date filtering)

get_identity_facets

Read identity facets via `facet`: profile, preferences, trust_boundaries, work_style, quality_standards, domains, or all

18

Identity, knowledge read/write, project context, session recovery, diagnostics

get_knowledge_history

Read one item's revision history (superseded snapshots; exact by-version lookup)