iai-personal-memory-engine MCP sunucusu
Commit 13 Kas 2026Konuşmaları kelimesi kelimesine kaydederek ve yerel bir hiperboyutlu depolama motoru aracılığıyla ilgili bağlamı sunarak yapay zeka ajanlarına uzun süreli bellek sağlar.
Ayrıca bilinen adı CodeAbra/iai-personal-memory-engine
- Yıldızlar
- 921
- Araçlar
- —
- İndirmeler, 30 gün
- —
- En son sürüm
- —
- Son commit
- 13 Kas 2026
- Lisans
- MIT
iai-personal-memory-engine MCP nedir?
Konuşmaları kelimesi kelimesine kaydederek ve yerel bir hiperboyutlu depolama motoru aracılığıyla ilgili bağlamı sunarak yapay zeka ajanlarına uzun süreli bellek sağlar.
Özet, projenin README dosyasından oluşturuldu
iai-personal-memory-engine MCP sunucusu hakkında
iai-personal-memory-engine, MCP uyumlu istemciler kullanan geliştiriciler için konuşmaları kelimesi kelimesine kaydederek yapay zeka ajanlarına uzun süreli bellek kazandırır. Her oturum adımını kullanıcı kimliği ve bağlamına dair kişisel bir haritaya dönüştüren yerel bir sunucu olarak çalışır. Yerel bir hiperboyutlu depolama motoru kullanarak, belirli detayları hatırlamak için manuel talimatlara gerek kalmadan yeni konuşmaların başında ilgili bellek kesitlerini sunar.
Kullanıcılar sistemle yerel bir daemon ve komut satırı arayüzü (CLI) aracılığıyla etkileşime girer. Kurulum, Python 3.11 veya 3.12 kullanarak tamamen kendi makinenizde çalışır; macOS, Linux ve Windows beta desteği mevcuttur. Motor, depolama ve embeddings yerel olarak çalıştığı için bir API anahtarı veya özel bir hesap gerektirmez. Sistem, AES-256-GCM güvenliği ile şifrelenmiş kayıtları yönetmek için yerel bir Rust motoru ve bir Hippo deposu kullanır.
Entegrasyon, ana bilgisayara göre değişiklik gösterir; Claude Code için oturum başlangıcında ortam tabanlı hatırlatma ve her adımda güncelleme sunarken, Cursor veya Gemini CLI gibi diğer istemciler talep üzerine mevcut on beş MCP aracına erişebilir. Motor üç bellek katmanını yönetir: epizodik parçalar, semantik özetler ve prosedürel davranışsal parametreler.
Neler yapabilirsiniz
- 1Uzun süreli bağlam enjeksiyonunu otomatize edinBir yapay zeka ajanı, yeni bir oturumun başında geçmişteki ilgili konuşma detaylarını otomatik olarak geri çağırabilir.
- 2Çelişen bilgileri çözünBir geliştirici, bellekte saklanan güncelliğini yitirmiş veya çelişkili bilgileri tespit etmek ve düzeltmek için motoru kullanabilir.
- 3Harici bilgi tabanlarını dahil edinAjanın bilgisini genişletmek için bellek motoruna tüm dizinleri veya belirli belge türlerini sağlayabilirsiniz.
- 4Bellek önemini yönetinKullanıcılar, hangi anıların belirgin kalacağını veya zamanla hangi anıların aşamalı olarak kaldırılacağını manuel olarak kontrol edebilir.
Projenin README dosyasından alınmıştır. Her kullanım durumu, oradaki bir alıntı ile kontrol edilir.
Otomatik kontroller
Çalıştırıldı 12 Kas 2026Tam rapor →Henüz doğrulanmadı. Bir sunucunun 80 puana, ciddi bir bulgu olmamasına ve kontrol edebilmemiz için yeterli veriye ihtiyacı vardır. Kontroller nasıl çalışır · Daha fazla puan için nelerin düzeltileceği
- Kaynak deposu bağlantılı ve erişilebilirGeçti
- Açık kaynak lisansı (OSI)Geçti
- Son bir yıl içinde commit veya sürüm mevcutGeçti
- Paket adı popüler bir pakete yakın değilKontrol edilmedi
- Uzak uç nokta HTTPS kullanıyorKontrol edilmedi
- Yıkıcı araçlar etiketlenmişKontrol edilmedi
- Modele yönelik gizli talimat yokGeçti
- Pakette veya bağımlılıklarında kritik uyarı yokKontrol edilmedi
English | 中文
What it is
A local server that speaks the MCP protocol and gives Claude, and any other MCP-compatible agent, a long-term memory. It captures every turn of every session verbatim, organizes those captures over time into a personal map of who you are, and serves a small slice of relevant memory back at the start of each new conversation and turn. You never have to say "remember this" or "what did we say last time?".
I built this for myself. It worked. The benchmarks were mostly for my own curiosity.
Under the hood it's not a wrapper around someone else's vector store and graph library — the parts that matter are my own code: the storage engine, the community-detection algorithm, the hyperdimensional memory substrate, and a native engine that makes it fast.
And unlike cloud memory services, there's no API key, no account, and no
telemetry: the engine, the store, and the embeddings all run locally. The only
things that leave your machine are the normal model calls your CLI already makes,
a nightly consolidation step that asks your model for a single insight through
the same subscription your CLI already uses (on by default;
IAI_MCP_REM_DISABLED=1 turns it off), a daily version check, and the one-time
download of the embedding model.
Quick start
Claude Code
python3.12 -m pip install -U iai-pme
Then run inside Claude Code:
/plugin marketplace add CodeAbra/iai-personal-memory-engine
/plugin install iai-memory@iai-pme
Restart the session, then verify:
iai --version
iai-mcp daemon status
iai-mcp doctor
Python 3.11 is also supported.
macOS or Linux: all-in-one source install
curl -fsSL https://raw.githubusercontent.com/CodeAbra/iai-personal-memory-engine/main/scripts/bootstrap.sh | bash
This builds the Rust engine and TypeScript wrapper, installs the background service and hooks, registers Claude Code, and runs the health check. It requires Git, Python 3.11/3.12, Node.js 18+, and Rust. To inspect the steps without changing anything:
curl -fsSL https://raw.githubusercontent.com/CodeAbra/iai-personal-memory-engine/main/scripts/bootstrap.sh | bash -s -- --dry-run
Other hosts
python3.12 -m pip install -U iai-pme
iai-mcp crypto init
iai-mcp daemon install
iai-mcp capture-hooks install --target codex
Replace codex with cursor, antigravity, hermes, openclaw, or all.
MCP tools work with any MCP-over-stdio client; automatic capture and context
injection depend on the hooks exposed by the host. See the
technical reference.
New stores use the native engine format by default; an existing store keeps its
current format on upgrade. To move an existing legacy SQLite store onto the
native engine, run iai-mcp migrate-to-lilli — iai-mcp doctor prints the exact
command, and the technical reference documents the full flow.
What happens after installation
| Event | Action |
|---|---|
| Prompt | New turns are appended to a session buffer as file IO; no embedding or engine RPC is needed on the capture path |
| Session end | Remaining transcript content is rolled over for ingestion; hook failures do not block the host |
| Session start | A bounded memory prefix is exposed as host context; an empty store or unavailable engine yields empty output |
| Later turns | Supported hosts receive a small foresight or delta pack with age and revision markers |
| Idle time | Captures are embedded, deduplicated, encrypted, inserted, clustered, consolidated, reinforced, and decayed |
The background process is called the daemon in the CLI. The MCP wrapper and
iai can still read the local store directly when it is asleep or temporarily
unavailable.
How it works
Memory model
| Tier | Contains |
|---|---|
| Episodic | Timestamped, write-once fragments of what was said |
| Semantic | Summaries induced from related episodes during idle consolidation |
| Procedural | Ten bounded behavioural parameters learned over time |
Distinct hyperdimensional representations keep literal detail, semantic structure, and behavioural tendencies from collapsing into one vector surface.
The local, LLM-free recall path combines semantic similarity, graph evidence,
recency, temporal validity, and lexical evidence. memory_recall returns both
hits and anti_hits; memory_contradict closes the old record's validity
interval, creates a new record, and links the two.
While idle, the engine groups related episodes, induces semantic memory,
reinforces useful paths, and decays weak unreviewed edges. One REM step, on by
default, may invoke claude -p through the user's existing Claude subscription,
capped at no more than 1% of the daily quota; IAI_MCP_REM_DISABLED=1 turns it
off. No Anthropic API key is required.
First-party components
| Component | Role |
|---|---|
| Hippo | Encrypted records, vector index, and graph in one local store |
| MOSAIC | Leiden-family community detection with stable community identity |
| Lilli HD | Hyperdimensional substrate and structural recall |
| Native engine | Rust embedder and graph kernels |
Dashboard and CLI
iai brain
The local dashboard searches the store, exposes graph neighbourhoods and contradictions, pins or fades memories, ingests files, controls the background engine, and reports token-use estimates from your own store.
iai recall · temporal-recall · search · ask · capture · teach · upload
iai watch · brain · status · last
iai upload accepts documents, Office files, e-books, source code,
configuration files, and directories. Full formats and administrative commands
are listed in docs/REFERENCE.md.
Benchmarks
Every harness ships in bench/; methodology and reproduce commands are in
BENCHMARKS.md.
| Benchmark | Result |
|---|---|
| Rescue@10 after contradiction | 1.000 |
| Historical-verbatim hit@10 | 1.000 |
| LongMemEval-S R@5, product embedder | 0.962 |
| LongMemEval-S R@10, product embedder | 0.978 |
Historical-verbatim retrieval uses a flat-cosine baseline of about 0.71. With
the matched all-MiniLM-L6-v2 embedder, iai-memory and mempalace v3.3.6 both
score R@5 0.966 and R@10 0.978; no win is claimed.
On the author's store, an automatically injected memory pack averaged about
350 tokens versus about 2,850 tokens for the agent-search round trip it
replaced: approximately 88% cheaper on that measured workload. This does not
apply to explicit memory_recall, whose default response budget is 1,500
tokens.
MCP tools
memory_recall memory_temporal_recall
memory_recall_structural memory_search
memory_capture memory_contradict
memory_reinforce memory_consolidate
profile_get_set topology
schema_list events_query
episodes_recent curiosity_pending
claim_check
Fifteen tools cover cue, temporal, structural, and lexical recall; checking a claim against memory; capture and correction; reinforcement and consolidation; behavioural-profile control; and store introspection.
Compatibility
| Host | Ambient behaviour |
|---|---|
| Claude Code | Session-start recall, per-turn updates, turn capture, and session capture |
| Codex CLI | Full integration through Codex hooks |
| Cursor | Session-start recall and capture; no per-turn text injection |
| Antigravity | Recall per invocation and lossless transcript capture |
| Hermes 0.5.0+ | Recall before model calls and capture from its message store |
| OpenClaw | MCP tools on request; no ambient shell hooks |
| Gemini CLI and other MCP hosts | MCP tools; no bundled host-specific hooks unless listed above |
| Claude Desktop | MCP tools; plain Chat does not expose Claude Code-style ambient hooks |
Privacy and limitations
- Records are encrypted at rest with AES-256-GCM. The store and key live under
~/.iai-mcp/; back them up together. Two kinds of files there are plain text: the per-turn capture spool until the engine's next pass encrypts it, and the caches the hooks inject memory from. The plugin README lists them. - macOS and Linux use a Unix socket. Windows uses an ephemeral loopback port with a per-user token.
- There is no iai-memory account, telemetry pipeline, hosted dashboard, or cross-machine sync.
- iai-memory goes online in three places, each with an off switch: the nightly
REM
claude -pstep (on by default,IAI_MCP_REM_DISABLED=1), a daily PyPI version check (IAI_MCP_VERSION_CHECK=0), and the first-use download of the embedding model from Hugging Face (IAI_MCP_EMBED_OFFLINE=1). - The engine checks that your Claude Code login is a subscription by reading
Claude Code's login record (
~/.claude/.credentials.json, or the macOS Keychain item) when the MCP server starts and before the REM step. Nothing from the record is sent anywhere. - The MCP server starts the engine in the background, and it keeps running
after the session ends. Stop it with
iai-mcp daemon stop. - The store refuses to mix incompatible embedding generations; changing the embedder requires an explicit migration.
- Recall is usually mediocre during roughly the first ten sessions, and quality and latency depend on corpus size, language, embedder, and stored history.
- The default store is English-first. Raw non-English records require an
explicit
raw:<lang>tag and a multilingual or custom embedder. - Windows support is beta. Ambient behaviour varies with host hook support.
- The project is solo-maintained and has no enterprise SLA.
Health and updates:
iai-mcp doctor # 38 checks
iai-mcp daemon status
iai-mcp self-update
About the name
IAI — Independent Autistic Intelligence describes the memory design.
- Independent: the engine, store, embeddings, and dashboard run locally.
- Autistic: literal preservation, precise cues, sustained focus, and rare events retained as rare rather than smoothed into a typical summary. This is an operational design description, not a diagnosis or casual metaphor.
- Intelligence: used in the systems sense — a process that observes, adapts, reorganizes itself, and remains viable over time.
“Personal memory engine” describes the scope: one person's memory, on one machine, used by the assistant they already have.
Documentation
docs/REFERENCE.md— technical and operational referenceBENCHMARKS.md— methodology and reproduce commandsdocs/EMBEDDERS.md— providers, languages, and migrationsCHANGELOG.md— release historyCONTRIBUTING.md— development and test setupSECURITY.md— private vulnerability reporting
Issues and pull requests are welcome. Changes to retrieval, capture, contradiction handling, or consolidation should include relevant benchmark reruns.
Authors
By Areg Aramovich Noya and Lilli Noya, in collaboration with the team at lcgc.dev.
License
iai-personal-memory-engine MCP soruları
Bir API anahtarı veya hesap gerektiriyor mu?
Hayır, herhangi bir hesap veya API anahtarı gerekmez. Motor, depolama ve gömmeler (embeddings) tamamen yerel makinenizde çalışır.
Verilerim güvende mi?
Evet, kayıtlar AES-256-GCM kullanılarak dinlenme durumunda şifrelenir ve depolama birimi yerel makinenizde tutulur.