iai-personal-memory-engine MCP server
2026년 11월 13일 커밋대화를 있는 그대로 캡처하고 로컬 초차원 저장 엔진을 통해 관련 컨텍스트를 제공하여 AI agent에게 장기 기억을 부여합니다.
다른 이름 CodeAbra/iai-personal-memory-engine
- 스타
- 921
- Tools
- —
- 다운로드, 30일
- —
- 최신 버전
- —
- 마지막 커밋
- 2026년 11월 13일
- 라이선스
- MIT
iai-personal-memory-engine MCP란?
대화를 있는 그대로 캡처하고 로컬 초차원 저장 엔진을 통해 관련 컨텍스트를 제공하여 AI agent에게 장기 기억을 부여합니다.
프로젝트 README에서 생성된 요약
iai-personal-memory-engine MCP server 정보
iai-personal-memory-engine은 MCP 호환 클라이언트를 사용하는 개발자가 대화를 있는 그대로 캡처하여 AI agent에게 장기 기억을 제공할 수 있도록 합니다. 이 시스템은 모든 세션 턴을 사용자 정체성과 컨텍스트의 개인용 맵으로 구성하는 로컬 server로 작동합니다. 로컬 초차원 저장 엔진을 활용하여, 특정 세부 사항을 기억하도록 수동으로 지시할 필요 없이 새로운 대화 시작 시 관련 메모리 조각을 제공합니다.
사용자는 로컬 데몬과 CLI를 통해 시스템과 상호작용합니다. 설정은 Python 3.11 또는 3.12를 사용하여 사용자의 로컬 환경에서 완전히 실행되며, macOS, Linux 및 Windows beta를 지원합니다. 엔진, 저장소, 임베딩이 로컬에서 실행되므로 API key나 별도의 계정이 필요하지 않습니다. 시스템은 네이티브 Rust 엔진과 Hippo store를 사용하여 AES-256-GCM 보안으로 암호화된 기록을 관리합니다.
통합 방식은 호스트에 따라 다르며, Claude Code의 경우 세션 시작 시의 주변 회상 및 턴별 업데이트를 제공합니다. Cursor 또는 Gemini CLI와 같은 other 클라이언트는 요청 시 사용 가능한 15개의 MCP 도구에 액세스할 수 있습니다. 엔진은 에피소드 파편, 의미적 요약, 절차적 행동 파라미터의 세 가지 메모리 계층을 관리합니다.
활용 사례
- 1장기 컨텍스트 주입 자동화AI agent가 새로운 세션 시작 시 관련 과거 대화 세부 사항을 자동으로 검색할 수 있습니다.
- 2상충하는 정보 해결개발자는 엔진을 사용하여 메모리에 저장된 오래되었거나 모순된 정보를 식별하고 수정할 수 있습니다.
- 3외부 지식 베이스 수집메모리 엔진에 전체 디렉토리나 특정 문서 유형을 제공하여 agent의 지식을 확장할 수 있습니다.
- 4메모리 중요도 관리사용자는 어떤 메모리를 계속 유지하거나 시간이 지남에 따라 단계적으로 제거할지 수동으로 제어할 수 있습니다.
프로젝트의 README를 바탕으로 작성되었습니다. 모든 활용 사례는 해당 내용의 인용문과 대조하여 확인합니다.
자동 검사
2026년 11월 12일에 실행됨전체 보고서 →아직 인증되지 않았습니다. 서버는 80점 이상의 점수, 심각한 결함 없음, 그리고 검사에 충분한 데이터를 갖추어야 합니다. 검사 방식 · 점수를 높이기 위해 수정할 항목
- 소스 저장소 연결 및 접근 가능통과
- 오픈 소스 라이선스 (OSI)통과
- 최근 1년 내 커밋 또는 릴리스통과
- 패키지 이름이 인기 패키지와 유사하지 않음검사되지 않음
- 원격 엔드포인트가 HTTPS 사용검사되지 않음
- 파괴적인 도구에 라벨 표시됨검사되지 않음
- 모델에 대한 숨겨진 지침 없음통과
- 패키지 및 해당 종속성에 중요한 보안 권고 없음검사되지 않음
README
GitHub에서 보기English | 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 질문
API key나 계정이 필요한가요?
아니요, 계정이나 API key가 필요하지 않습니다. 엔진, 저장소, 임베딩 모두 사용자의 로컬 환경에서 실행됩니다.
데이터는 안전한가요?
네, 기록은 AES-256-GCM을 사용하여 암호화되어 저장되며 저장소는 사용자의 로컬 환경에 유지됩니다.