CommitLore MCP server
2026년 11월 1일 커밋제약 사항과 거절된 대안을 저장소에 직접 저장하여 코딩 에이전트에게 Git 기반의 의사결정 메모리를 제공합니다.
다른 이름 MongLong0214/commitlore
- 스타
- 19
- Tools
- —
- 다운로드, 30일
- —
- 최신 버전
- 1.2.0
- 마지막 커밋
- 2026년 11월 1일
- 라이선스
- MIT
CommitLore MCP란?
CommitLore은(는) MCP server입니다. 제약 사항과 거절된 대안을 저장소에 직접 저장하여 코딩 에이전트에게 Git 기반의 의사결정 메모리를 제공합니다.
프로젝트 README에서 생성된 요약
CommitLore MCP server 정보
CommitLore는 코딩 에이전트가 Git 저장소 내에서 의사결정 메모리에 직접 접근할 수 있는 방법을 제공합니다. 외부 호스팅 데이터베이스에 의존하는 대신, Git trailers와 notes를 사용하여 제약 사항, 경고 및 거절된 대안을 저장합니다. 이를 통해 코드 변경의 근거가 소스 코드와 함께 브랜치 생성, 병합 및 클로닝 과정에서도 유지되도록 보장합니다.
개발자는 쉘 스크립트를 통해 도구를 설치하고 commitlore init 명령어를 사용하여 저장소를 초기화할 수 있습니다. MCP 또는 Claude Code 및 Codex용 특정 플러그인을 통해 다양한 AI 클라이언트와 통합됩니다. 이 시스템은 활성(active), 대체(superseded), 만료(expired)된 의사결정을 구분하여, 에이전트가 현재 편집 중인 파일 경로와 관련된 컨텍스트만 수신하도록 합니다. 이를 통해 에이전트가 팀에서 이미 거절한 아이디어를 반복해서 제안하는 것을 방지합니다.
활용 사례
- 1반복적인 거절 제안 방지AI 에이전트가 저장소를 확인하여 특정 코딩 방식이 이전에 팀에 의해 거절되었는지 여부를 파악할 수 있습니다.
- 2파일 편집을 위한 컨텍스트 제공에이전트가 파일을 수정하기 전에 해당 경로와 관련된 활성 제약 사항 및 제한 사항을 전달받을 수 있습니다.
- 3병합 중 의사결정 이력 보존GitHub Action을 사용하여 squash merge를 수행할 때 의사결정 기록이 유실되지 않도록 할 수 있습니다.
- 4의사결정 캡처 자동화팀은 매 커밋마다 수동으로 프롬프트를 입력할 필요 없이 의사결정 기록을 자동으로 스테이징하도록 저장소를 구성할 수 있습니다.
프로젝트의 README를 바탕으로 작성되었습니다. 모든 활용 사례는 해당 내용의 인용문과 대조하여 확인합니다.
자동 검사
2026년 11월 14일에 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 가능monglong0214/commitlore is public and reachablegithub.com/monglong0214/commitlore ↗통과
- 패키지가 이 저장소를 소스로 명시검사되지 않음
- 빌드 출처(Sigstore 증명)검사되지 않음
- 오픈 소스 라이선스 (OSI)MITspdx.org/licenses/MIT.html ↗통과
- 최근 1년 내 커밋 또는 릴리스Last commit or release 2026-11-01github.com/monglong0214/commitlore ↗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 보기curl -fsSL https://raw.githubusercontent.com/MongLong0214/commitlore/v1.7.5/install.sh | sh -s v1.7.5
curl -fsSLO https://raw.githubusercontent.com/MongLong0214/commitlore/v1.7.5/install.sh
sh install.sh v1.7.5
# Or skip the script: the checkout it makes is one you can make yourself.
git clone --depth 1 --branch v1.7.5 https://github.com/MongLong0214/commitlore
node commitlore/dist/commitlore.mjs --version
It installs a pinned source checkout and a wrapper that runs
node <checkout>/dist/commitlore.mjs — no compiled download, no build step.
The code survives. The judgment doesn't.
An agent proposes an approach. Your team rejects it because of a non-obvious constraint. The final code preserves the outcome, but usually not why the alternative was rejected. A later agent sees only the code and proposes the same idea again.
CommitLore keeps that judgment beside the code.
What CommitLore does
| Behavior | Product path | |
|---|---|---|
| Captures | Preserves constraints, rejected alternatives, and warnings that a diff cannot show. Candidates are checked against the session transcript and the staged diff. | commitlore capture |
| Preserves | Stores accepted records in Git trailers or notes instead of a hosted memory database. | commit hooks · refs/notes/commitlore |
| Tracks lifecycle | Keeps active, superseded, and expired decisions distinct. | commitlore stale |
| Scopes | Selects decisions for the path an agent is about to edit. | commitlore context |
| Grades trust | Delivers records as directives, claims, or withheld content. | default / signed mode |
| Delivers | Gives supported agents current context before an edit. | plugin hook · MCP |
Most commits should carry no record. CommitLore is for judgment the code cannot preserve, not for narrating every change.
60 seconds to decision-aware agents
1. Install the CLI
macOS and Linux:
curl -fsSL https://raw.githubusercontent.com/MongLong0214/commitlore/v1.7.5/install.sh | sh -s v1.7.5
Windows:
& ([scriptblock]::Create((irm https://raw.githubusercontent.com/MongLong0214/commitlore/v1.7.5/install.ps1))) v1.7.5
Requires Node.js 22.23.2+ and Git. The script checks both before it writes anything.
2. Connect your agent
Claude Code:
/plugin marketplace add MongLong0214/commitlore
/plugin install commitlore@commitlore
Codex:
commitlore plugin install-codex
The plugin puts no commitlore on PATH, so the commands below need the CLI
install as well. The installers also detect and wire supported MCP hosts where
they can do so safely; the exact matrix is below.
3. Initialize a repository
cd your-repository
commitlore init
commitlore context .
Start a new agent session after installing or updating a plugin: a running session keeps the runtime it loaded.
Then work and commit normally. On supported skill integrations, CommitLore is considered during ordinary commit requests and stays silent when there is nothing worth preserving. You do not need to name CommitLore on every commit.
Want accepted records to stage without a per-record prompt? The repository can
opt in once with commitlore auto on. That policy is repository-owned and
applies to the team, so it is not silently enabled by this page.
What the agent receives
Before editing src/pricing.ts:
commitlore: active records for src/pricing.ts
Limit
[claim] r-price01 a1b2c3d4 calculatePrice owns final checkout pricing only
Ruled-out
[claim] r-price01 a1b2c3d4 Reuse it for admin quotes | eligibility and rounding semantics differ
[claim] means "weigh this as information." A repository can opt into the
stronger signed-authority mode. Delivery gives the agent context; it does not
block the edit.
Why Git?
The repository should own the judgment behind its code.
CommitLore stores records in ordinary Git trailers and notes, so they branch, merge, clone, review, and survive provider changes with the code they explain.
SQLite is only a rebuildable index. Delete it and Git still holds the record.
Finding an old decision is not enough
A general memory or retrieval system asks:
Which old text looks related?
CommitLore asks:
Which recorded decisions still apply to this path now?
A superseded decision can be highly relevant and still be wrong as current guidance. Relevance and authority are different questions.
How it works
- Capture — an agent drafts only decision context the diff cannot show.
- Verify — CommitLore checks the draft against the session and staged diff.
- Preserve — the accepted record lives in Git with identity and lifecycle.
- Deliver — before a later edit, only active records for that path are returned.
Most commits carry no record. The commit hook validates a record when one is present; it does not invent one.
An existing hook is not overwritten. commitlore init honours core.hooksPath,
moves any hook already installed to <hook>.commitlore-chained, and calls it
first; commitlore hooks uninstall puts it back.
What happens automatically
| Host | Pre-edit delivery | Verified capture workflow | Deterministic every-commit capture |
|---|---|---|---|
| Claude Code | Automatic through the plugin | Available through the plugin skill | Not certified |
| Codex | Automatic through the plugin | Available through the plugin skill | Not certified |
| Hermes | Available after commitlore hermes install |
Available after host install | Not certified |
| Gemini CLI, Cursor, Windsurf, opencode | MCP delivery where the host uses the registration | Procedure exposed over MCP | No |
AGENTS.md hosts |
Procedure only | Procedure only | No |
"Available" means the prepare → verify → stage workflow exists. It does not mean every eligible commit is assessed automatically.
Users on supported skill hosts do not need to say "record this in CommitLore" on every commit. The remaining limitation is host initiation, not a required per-record user command.
Squash-merge repositories
A squash merge replaces a branch's commits with one new commit, and that commit does not carry the branch's trailers. If your repository merges with the squash button, a record made on a branch is dropped by the merge unless something carries it onto the commit that squashed it.
Two paths cover that, and one of them needs a one-time setup:
| How the squash happens | What carries the record | Setup |
|---|---|---|
git merge --squash locally |
The installed prepare-commit-msg hook, from SQUASH_MSG |
None — commitlore init already did it |
| GitHub's Squash and merge button | The action/preserve GitHub Action |
The workflow below |
GitHub performs that merge on its own servers, where no local git hook runs at all, so the local hook cannot see it. The Action is the only place that has what it needs at that moment: the pull request, its commits, and the commit they were squashed into.
Add .github/workflows/commitlore-preserve.yml:
name: CommitLore squash inheritance
# pull_request_target, not pull_request: a pull request from a fork gets a
# read-only token on pull_request, so the job would build the record and then
# fail to publish it.
on:
pull_request_target:
types: [closed]
permissions:
contents: write # the one push to refs/notes/commitlore
concurrency:
group: commitlore-notes
cancel-in-progress: false
jobs:
preserve:
if: github.event.pull_request.merged == true
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
with:
# the merge commit is on the base branch, and a closed pull request
# has no merge ref left to check out
ref: ${{ github.event.pull_request.base.ref }}
fetch-depth: 0
# the mirror this action writes; publishing from a checkout that never
# read it would fork the notes history
- run: git fetch --no-tags origin '+refs/notes/commitlore:refs/notes/commitlore'
# a squash merge usually deletes the branch, and then the pull request's
# own ref is the only one still reaching the commits that carry records
- run: git fetch --no-tags --force origin
'+refs/pull/${{ github.event.pull_request.number }}/head:refs/commitlore/pr-head'
# The action runs CommitLore from a checkout of this repository: the
# package is private, so there is no published npm name to fall back to.
# `dist/` is committed (ADR-0011), so nothing needs building.
- uses: actions/checkout@v4
with:
repository: MongLong0214/commitlore
ref: v1.7.5
path: .commitlore-cli
persist-credentials: false
- uses: MongLong0214/commitlore/action/preserve@v1.7.5
with:
cli-path: .commitlore-cli/dist/cli.js
Two rules for whoever edits this next, because pull_request_target runs with a
writable token: never check out the pull request's head here, and never execute
anything reachable from refs/commitlore/pr-head. The fork's commits arrive as
data to read trailers from, not as code to run.
commitlore doctor reports whether this is switched on, under
squash inheritance. It says so before a record is lost;
squash conservation is the row that reports records already gone.
If you merge with merge commits or rebase, records survive on their own and this setup is unnecessary.
A field report, not a measurement
One run, on an unrelated repository, by someone installing v1.2.1 for the first time. Nothing here was measured and none of it is in the evidence logs. It is on this page because the paragraph above asserts a loop that no table here covers.
They asked an agent to fix a rounding bug, mentioned in passing that a decimal library had already been considered and dropped, and ended with "commit it". CommitLore was never named. Part of what the commit carried:
Ruled-out: adopting a decimal library such as Decimal.js | the backend is a
number contract, so it is meaningless
Warn: do not revert the test file to console.assert: it exits 0 even on
failure, so CI passes silently
Provenance: drafted
The Warn was not dictated to the agent. It hit the trap while working and left
it for whoever came next. Provenance: drafted records that no human read the
record, which grades it claim — delivered as a report to weigh, not an order.
A later session with no shared history was asked to adopt the decimal library
after all. It did not, and named the record as its reason. It also read the
grade: a claim is not an instruction, so it checked the stated reason against
the code before agreeing with it.
Unlike memory storage
| General memory / RAG | CommitLore | |
|---|---|---|
| Primary question | What old text is related? | Which decisions still apply here now? |
| Authority | Memory store or provider | Git |
| Scope | Semantic similarity | Repository paths |
| Lifecycle | Often append-first | Active · superseded · expired |
| Trust | Retrieved text | Directive · claim · blocked |
| Capture | Transcript or note storage | Evidence-checked decision record |
| Portability | Backend-dependent | Ordinary Git |
CommitLore is intentionally narrower. It is not a general user-memory system, conversation archive, or vector database replacement.
Evidence
| Question | Measured result | Boundary |
|---|---|---|
| Did claim-grade context change re-proposal in the registered study? | 2.8% (16/580) with CommitLore vs 18.8% (109/579) without | one model, one harness, constructed tasks |
| Did lifecycle filtering deliver retired records in the measured active projection? | 0 retired records | superseded records were present; expiry was not |
| Does indexed lookup scale? | 496 ms p50 at 100k commits | the no-index fallback is much slower |
Index build time follows the number of records, not the number of commits: the expensive pass runs once per record, so a long history that has recorded little builds faster than a short one dense with records.
Path scope is what keeps a large history from reaching the model. On the #167 corpus, only 2 of 10,002 records did:
| route | model-visible records | relevant records | model-visible tokens |
|---|---|---|---|
| inject everything | 10,002 | 2/2 | 1,004,554 |
| top-k lexical | 2 | 1/2 | 190 |
| CommitLore path scope | 2 | 2/2 | 335 |
That measures exposure and recall at a fixed two-record budget — not token cost, billed cost, accuracy, or agent behaviour. One corpus, one query, one pinned embedding model.
The agent study does not establish a universal model effect. Delivery is not proof that a model read or followed a record.
Methods, full tables, exclusions, and negative results →
Limits, trust and privacy
- Capture is assisted, not deterministic. Supported skills consider ordinary commit requests, but no host is certified to assess every eligible commit.
- Default directive mode is not authentication. It matches the commit
author header, and anyone who can write a commit can set that header — so a
[directive]in default mode is policy metadata, not proof of identity. Signature mode additionally requires Git's own verified status and a match in the repository-localcommitlore.trustedSignerallowlist; an absent, empty, or unreadable signer allowlist authorizes nobody, so the mode fails closed. - Guard is an experimental advisory, not a safety net: precision 44.8% (95% Wilson CI 32.7%–57.5%), recall 22.0% on the 417-decision corpus. An empty guard result is not a safety verdict.
- Delivery spends tokens on every matching tool call. The pre-edit hook
fires on
Readas well asEdit,Write,MultiEditandNotebookEdit, so it runs far more often than an editing agent commits. Each fire spends up to the payload budget — 800 tokens by default, changed with--budget. A repository with no records spends nothing, which means this is a cost that arrives with adoption rather than with installation. - An answer may be partial. Coverage is disclosed; absence from a partial
result is not proof that no record exists.
commitlore coveragereports what a scan reached. - Commit trailers travel with a clone; notes do not. Git does not fetch
refs/notes/*by default, so a record inrefs/notes/commitloreis absent from an ordinary clone untilcommitlore initconfigures that mirror. - There is no hosted backend. But once the server or hook returns context, the host handles that context under its own policy; CommitLore does not control that data flow.
Security · Compatibility · Evidence
Records are untrusted until graded. Default author matching is policy metadata, not authentication. Signed directive mode requires Git verification and a repository-local signer allowlist; an absent or unreadable allowlist authorizes nobody. Injection-shaped payload is withheld from model-readable routes.
The CLI installer cannot rewrite hooks inside repositories it does not know
about, and running host sessions retain the runtime they loaded. commitlore doctor names both states and their repair, and commitlore upgrade reports
whether a newer release exists.
Records are ordinary Git trailers or notes. Protocol 2.0 defines lifecycle, trust grades, validation, and compatibility.
Human guide → · Normative specification →
The repository publishes the methods, exclusions, unsuccessful measurements, and the cases where the original benchmark or diagnosis was wrong.
Documentation
- Install, upgrade, and uninstall
- CLI reference
- Capture workflow
- Record protocol
- Security model
- Evidence and limitations
- Production contract
Contributing
CONTRIBUTING.md covers the record protocol this repository holds itself to, the release gate, and how to reproduce the evidence.
License
MIT — see LICENSE.
CommitLore MCP 질문
의사결정 메모리는 어디에 저장되나요?
의사결정은 호스팅된 데이터베이스가 아닌, 저장소 내부의 일반 Git trailers 또는 notes에 저장됩니다.
CommitLore를 어떻게 설치하나요?
Node.js 22.23.2+ 및 Git이 설치되어 있다면, macOS/Linux용 curl 스크립트 또는 Windows용 PowerShell 명령어를 통해 설치할 수 있습니다.
CommitLore가 GitHub의 Squash and merge 버튼과 함께 작동하나요?
네, 하지만 squash 과정에서 기록이 유지되도록 특정 GitHub Action을 사용하여 한 번 설정해야 합니다.