ais MCP server
2026년 11월 12일 커밋사용자가 지정한 일반 텍스트 키를 사용하여 AI agent가 정보를 저장하고 정확하게 불러올 수 있도록 지원합니다.
다른 이름 Anode1/ais
- 스타
- 7
- Tools
- —
- 다운로드, 30일
- —
- 최신 버전
- 0.3.47
- 마지막 커밋
- 2026년 11월 12일
- 라이선스
- GPL-2.0
ais MCP란?
사용자가 지정한 일반 텍스트 키를 사용하여 AI agent가 정보를 저장하고 정확하게 불러올 수 있도록 지원합니다.
프로젝트 README에서 생성된 요약
ais MCP server 정보
ais는 AI agent와 사용자가 커스텀 일반 텍스트 키를 사용하여 정보를 저장하고 검색할 수 있는 방법을 제공합니다. 의미를 추측하는 확률적 검색이나 벡터 임베딩에 의존하는 대신, 이 시스템은 정확한 키 연관 방식을 사용하여 파일 경로, 링크, 메모와 같은 특정 참조를 불러옵니다. 데이터를 복제하는 대신 기존 데이터의 위치를 가리키는 경량 인덱스 역할을 수행하므로 원본 파일은 그대로 유지됩니다.
개발자는 단일 명령줄 명령으로 서버를 추가하여 AI 클라이언트에 이를 통합할 수 있습니다. 서버는 데이터베이스나 무거운 런타임 요구 사항 없이 C 기반 엔진을 사용하여 로컬에서 작동합니다. agent에게 recall, find, tags, timeline, due와 같은 도구를 제공합니다. 핵심 엔진은 CLI이지만, 사용자는 웹 GUI, Windows 애플리케이션, 또는 Android 및 iPhone용 모바일 앱을 통해 인덱스와 상호작용할 수 있습니다. 이러한 설정을 통해 단일 일반 텍스트 인덱스 파일을 공유함으로써 서로 다른 AI 모델과 세션 간에 메모리를 공유할 수 있습니다.
활용 사례
- 1정확한 정보 검색AI agent가 대용량 파일을 검색하는 대신 정확한 키를 사용하여 특정 데이터 포인트를 불러올 수 있습니다.
- 2효율적인 컨텍스트 관리필요한 참조 정보만 검색하여 LLM에 전송되는 토큰 수를 줄입니다.
- 3안전한 비밀 정보 저장수동으로 복호화하기 전까지는 AI agent가 내용을 알 수 없도록 암호화된 비밀번호를 저장합니다.
- 4교차 플랫폼 메모리 동기화모바일 기기, 데스크톱 컴퓨터, 터미널 환경에서 동일한 일반 텍스트 인덱스에 액세스합니다.
프로젝트의 README를 바탕으로 작성되었습니다. 모든 활용 사례는 해당 내용의 인용문과 대조하여 확인합니다.
자동 검사
2026년 11월 13일에 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 가능anode1/ais is public and reachablegithub.com/anode1/ais ↗통과
- 패키지가 이 저장소를 소스로 명시검사되지 않음
- 빌드 출처(Sigstore 증명)검사되지 않음
- 오픈 소스 라이선스 (OSI)GPL-2.0spdx.org/licenses/GPL-2.0.html ↗통과
- 최근 1년 내 커밋 또는 릴리스Last commit or release 2026-11-12github.com/anode1/ais ↗통과
- OpenSSF Scorecard검사되지 않음
- 패키지 이름이 인기 패키지와 유사하지 않음검사되지 않음
- 패키지 및 해당 종속성에 중요한 보안 권고 없음검사되지 않음
- 모델에 대한 숨겨진 지침 없음0 tool descriptions and the README read; no override phrases, credential paths or hidden characters통과
- 파괴적인 도구에 라벨 표시됨검사되지 않음
- 원격 엔드포인트가 MCP 핸드셰이크에 응답검사되지 않음
README
GitHub에서 보기ais
Save anything under your own keys, recall it by those keys.
An index in plain text on your own disk, with apps for the phone, the browser and the terminal over it. You save anything (a link, a file, a note, a password) under one or more keys, and recall it by those keys: ais venice italy gives back what you saved under both, the way your mind does, by association. It stores only a reference, so your documents stay where you keep them; the index is a view, and your data is never touched. Not a search engine over everyone's web, and not a tagger that guesses: an index of your own things under your own words. Why that matters is below.
One engine, thin front-ends. The CLI is the contract; the web GUI (ais --serve), the Flutter mobile app and a native Win32 wrapper sit over it, and the engine depends on none of them. C, no database, no runtime to install.
A coding agent can call ais the way it calls grep, except that it recalls what you filed instead of searching for it again: one line of config, 2,900 tokens a question against 24,500, and 40 of 40 answers exact. The measurement, and how to reproduce it.
Because it is plain text, it outlives its own tools: your index still opens in fifty years and exports into anything. Keeping data readable that long is computing's unsolved digital dark age, where file formats and the apps that open them die faster than the data. Plain text, readable since the 1960s on any machine with no special program, is the oldest answer.
Why
Your memory, yours to keep.
A search engine and an automatic tagger both answer with the mean: what these words mean to most people, what the model saw most often. That is the right answer when you are looking for something everyone knows, and the wrong one when you are looking for something only you saved.
Your keys are the deviation from that mean. "venice" is a week in 2023 for one person, a glass factory for another, a chapter of a thesis for a third. Nothing but you records which one it is, and no amount of training data recovers it, because averaging is precisely what removes it.
So ais does not guess and does not tag for you. It saves what you give it under the words you chose, and hands it back when you say them again. That is the whole trade: you do the small work of naming a thing once, and in exchange the index is yours rather than an average of everyone's.
See about.txt for the pitch and the memex origin, and foundation.md for the prior/compression argument behind it.
Questions
Why not SQLite, or a database?
SQLite is a binary file one program understands; ais is line-oriented plain text you can read, grep, diff, and recover by hand. You trade query power you do not need for the durability and transparency of plain text (see about.txt).
Why not an embedded engine (BerkeleyDB, LMDB, gdbm)? Because a bundled engine is a dependency you do not control. An early ais version ran on BerkeleyDB (both the Java and the C editions) right as it was acquired and relicensed; this plain-text design is that lesson. A format only one library version can open is a bet that the library, its license, and its on-disk layout outlive your data; they rarely do. ais has no engine to depend on: any future ais, any unix tool, or any format you migrate to can read the store.
Is keys-only search not limiting?
On purpose. The keys you assign are your prior, your ordering of the world. (ais --find still searches values and paths.) To search a document's contents, keep it as a file and index its path.
Is the built-in web server not a toy?
ais --serve is one thin wrapper over the CLI, a single-user loop that binds 127.0.0.1 only. The full front-end map is in dev/DISTRIBUTION.md.
Is this not just a bookmark manager / recoll / org-mode? Not a bookmark manager: it saves anything under any keys, not URLs in a browser. Not full-text (recoll): it indexes the keys you choose, not document bodies. Not org-mode: no single tree, no app lock-in, no markup to learn, keys with set algebra (AND / OR) over plain files.
Why not embeddings or a vector database? An embedding places your note near the average meaning of its words, which is the averaging this index exists to avoid. Recall here is exact: the keys you chose, intersected. A wrong key returns nothing instead of the three nearest neighbours, so an agent gets an answer it can trust or no answer at all, with no index to rebuild, no model to pin, and no similarity threshold to tune. Embedding search is the better tool when you do not know what you filed; keys are the better tool when you do.
Does it replace my photo library or files? No, it points into them: a photo stays in Immich, a file on disk, a page at its URL, and the index holds the reference under your own keys. (Secrets are the one exception: those it stores inline, encrypted, see below.)
Can it hold passwords? Is it a password manager?
Yes. A secret is stored encrypted inline (-e), so a login lives right next to the context it belongs to, and two things set it apart from a built-in manager. It is cross-platform: Apple Keychain and Google Password Manager are locked to one ecosystem, while ais is the same plain-text index on Windows, macOS, Linux, Android, iPhone and the CLI, so your secrets travel with you. And it is agent-safe: decryption is interactive (a passphrase you supply at a terminal or in the app), so an agent reading your index sees an opaque aisc: marker, not the secret, with no master key or unlocked vault to drain. For hundreds of site logins a dedicated manager is still more convenient: there is no autofill, no generation, no shared vault here (about.txt).
Give an agent your index
For an agent the index works like a cache of earlier extraction: a thing is found once and filed, and a later recall costs one line, where grep repeats the whole search on every question.
One line wires it into a client:
claude mcp add ais -- ais --mcp # or: {"mcpServers":{"ais":{"command":"ais","args":["--mcp"]}}}
That serves recall, find, tags, timeline and due over stdin/stdout. It is read-only, ais --mcp rw adds saving, and there is no delete or edit at any setting. Encrypted values stay opaque. It refuses a .ais/ it merely found by walking up, because a clone can ship one; a project index is served by naming it with -f. Which index it opens, what it refuses and what a model never sees: doc/MCP.md.
The same index is memory shared between sessions, between you and an agent, and between agents of different models. On your home index the agent asks you for keys. On a project's or a group's index, named with -f, it chooses them from the keys already in use, so the next session, or another model, recalls what was saved by the group's words. An agent saves when asked; left alone it rarely does (measured). Details, and what the plain-text file does not show: locking, crash-safe rewrites, recall in milliseconds at a million records, and a merge that survives edits and deletes on devices that were apart.
A skill is the other door, for an agent that already has a shell: .claude/skills/ais/SKILL.md, copied into your own project's .claude/skills/. It drives the CLI, so it can edit and delete records, which the server cannot at any setting.
The measurement: eight questions, five repeats each, claude-sonnet-4-6 run both ways over the same corpus, the recall arm answering from the recalled row alone. The questions were written by the person who filed the records, so every question matched a key: the table is the cost of a hit, and a miss costs the usual search. The index reached the agent as CLI tools, which is the same lookup ais --mcp serves over a pipe.
| file search (grep + read) | recall by key | |
|---|---|---|
| answered correctly | 31 of 40 | 40 of 40 |
| tokens per question, mean | 24,500 | 2,900 |
| of that, the retrieval payload | 4,744 | 68 |
Four times fewer tokens at the median and nine at the mean, and 69x less content dragged into the context window. Run ais yourself at the terminal and the cost is zero, because no model is involved.
The measurement is the paper Key Lookup versus File Search for a Coding Agent, doi.org/10.5281/zenodo.20764255. Its harness, the deposited run and a public photo-library stand-in are beside the paper, in ais/experiment/ of the articles repository; the deposited run reproduces there with no API key. The headline numbers come from the same method over a private 100k-line code project.
Download
Android: the app is on Google Play:
https://play.google.com/store/apps/details?id=com.aisindex.ais
iPhone: the same app, built for iOS and in TestFlight; the App Store link lands here once the listing is approved.
macOS and Linux: one line installs or updates:
curl -fsSL https://raw.githubusercontent.com/Anode1/ais/main/scripts/install.sh | sh
It downloads the build for your OS and CPU, checks it against the published .sha256, and installs into ~/.local (PREFIX=/usr/local to put it elsewhere). It compiles nothing and needs no root. If ~/.local/bin is not on your PATH, it prints the line to add. Read scripts/install.sh first if you would rather not pipe a script to a shell. ais --serve opens the GUI in your browser.
Or take the files by hand. The link below always points at the current release:
- Android without Play: the
.apkon the release page, or addhttps://github.com/Anode1/aisin Obtainium, which installs each release as it appears; when it asks which APK, the…-arm64-v8a.apkfits a modern phone. - macOS / Linux without the script: unzip the
…-<os>-<arch>.zipand run theaisinside it from there, or copy it onto your PATH. - Windows: run the
…-windows-x86_64-setup.exe. It installs for your user only (no admin prompt), puts AIS in the Start menu and on the Desktop, and theaiscommand on your PATH. AIS opens in your browser (if nothing opens, go tohttp://127.0.0.1:8765) and sits in the notification area by the clock: right-click it to quit. Syncing a phone by QR code works as on Linux. Without installing: unzip the…-windows-x86_64.zipand double-clickais-gui.exe; theais.exebeside it is the CLI. No runtime either way.
The desktop binaries are not code-signed, so the first run is flagged as an unrecognized download (macOS Gatekeeper "could not verify", Windows SmartScreen "Windows protected your PC"). That is a new-and-unsigned notice, not a malware finding: on Windows click More info, then Run anyway, once for the setup exe (what it installs is not flagged again); on macOS run xattr -dr com.apple.quarantine . in the unzipped folder. A copy you build yourself is never flagged. The Android package is signed, with the project's own upload key.
Verify a download
Each release file ships beside a matching …zip.sha256. Download both, then check the hash (prints OK on a match):
shasum -a 256 -c ais-*-*.zip.sha256 # macOS / Linux
Releases are built by GitHub Actions (.github/workflows/release.yml).
Quick start (from source)
make # build ./ais
./ais --init # create an index here (a .ais/ directory, git-style)
./ais --serve # open the web GUI in your browser
ais --help lists every command; doc/USING.txt has the everyday CLI cheat-sheet (recall, add, edit) and where your data lives.
Tip: alias is='ais' gives you two-character recall: is venice italy reads like the question it answers.
Learn more
| Read | For |
|---|---|
doc/USING.txt |
How to use it, GUI on every OS (plain steps, no jargon). |
doc/about.txt |
What ais is, and what it is not. |
doc/command_line.txt |
Every command and option, the full ais --help. |
doc/MCP.md |
The ais --mcp agent tool: wiring it into a client, which index it opens, what it refuses. |
doc/dev/HTTP_API.md |
The /api/... routes ais --serve answers, for curl or any program: the other agent door. |
doc/NOTES.md |
The shape of a note an agent writes: plain-text bullets filed with ais --doc, one fact in one place. |
doc/SYNC.md |
Sync your index between devices: encrypted LAN sync (--sync), or through a shared folder a tool like Syncthing keeps in sync (--sync-folder). |
doc/OVERVIEW.md |
Why it is built this way, and where it came from. |
doc/ROADMAP.md |
What's planned, what is knowingly unfixed, and where to help. |
doc/dev/LAYOUT.md |
On-disk format and module map. |
AGENTS.md |
How to develop it: the contract, the build, the test loop. |
doc/dev/README.md |
Every other developer note, indexed: sync, front ends, packaging, releases. |
man ais |
Full command reference. |
See also
agent-recipes: short prompts for working with coding agents; ais is one of them (store and recall procedures instead of re-deriving them).
License
New code: dual licensed, your choice of GNU GPL v2 or later (COPYING) or MIT (LICENSE-MIT). Legacy material (legacy/) under its original Apache License 2.0. Author: Vasili Gavrilov (GitHub Anode1).
ais MCP 질문
ais는 벡터 데이터베이스와 어떻게 다른가요?
평균적인 의미를 사용하는 임베딩과 달리, ais는 정확한 키 기반의 호출 방식을 사용합니다. 이를 통해 agent가 유사도 기반의 추측을 하는 대신, 신뢰할 수 있는 답변을 받거나 혹은 아무것도 받지 않도록 보장합니다.
ais에 비밀번호를 저장할 수 있나요?
네, 비밀 정보는 인라인으로 암호화하여 저장할 수 있습니다. 복호화는 암호를 통한 대화형 방식으로 이루어지므로, agent는 불투명한 마커만 보게 되어 agent 사용 환경에서도 안전합니다.
데이터가 독자적인 형식으로 저장되나요?
아니요, 인덱스는 라인 기반의 일반 텍스트 파일로 저장되므로 표준 도구를 사용하여 읽기, grep, diff 작업이 가능합니다.
Claude에 ais를 어떻게 추가하나요?
claude mcp add ais -- ais --mcp 명령어를 사용하여 추가할 수 있습니다.