Skip to main content
Glama
curl -fsSL https://raw.githubusercontent.com/MongLong0214/commitlore/v1.2.0/install.sh | sh -s v1.2.0
curl -fsSLO https://raw.githubusercontent.com/MongLong0214/commitlore/v1.2.0/install.sh
sh install.sh v1.2.0

# Or skip the script: the checkout it makes is one you can make yourself.
git clone --depth 1 --branch v1.2.0 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Keeps active, superseded, and expired decisions distinct.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.

Related MCP server: Hypermnesic

60 seconds to decision-aware agents

1. Install the CLI

macOS and Linux:

curl -fsSL https://raw.githubusercontent.com/MongLong0214/commitlore/v1.2.0/install.sh | sh -s v1.2.0

Windows:

& ([scriptblock]::Create((irm https://raw.githubusercontent.com/MongLong0214/commitlore/v1.2.0/install.ps1))) v1.2.0

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  calculatePrice owns final checkout pricing only

Ruled-out
  [claim] r-price01  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.

Security model →

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

  1. Capture — an agent drafts only decision context the diff cannot show.

  2. Verify — CommitLore checks the draft against the session and staged diff.

  3. Preserve — the accepted record lives in Git with identity and lifecycle.

  4. 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.

A field report, not a measurement

One run, on an unrelated repository, by someone installing v1.2.0 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-local commitlore.trustedSigner allowlist; 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 Read as well as Edit, Write, MultiEdit and NotebookEdit, 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. Repository-wide coverage, symbol anchors, and an interactive record builder remain open: #32, #33.

  • Commit trailers travel with a clone; notes do not. Git does not fetch refs/notes/* by default, so a record in refs/notes/commitlore is absent from an ordinary clone until commitlore init configures 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.

Full security model →

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.

Installation and upgrades →

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.

Evidence → · Self-audit →

Documentation

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.

A
license - permissive license
Not graded
quality - not tested
A
maintenance

Maintenance

Maintainers
2hResponse time
1dRelease cycle
22Releases (12mo)
Commit activity
Issues opened vs closed

Related MCP Servers

  • A
    license
    A
    quality
    A
    maintenance
    Local-first memory layer for AI coding agents — captures issues, attempts, fixes, and decisions, and warns at git commit before you repeat a mistake.
    15
    665
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Git-native long-term memory for AI agents: your markdown files are the source of truth, the search index is a disposable projection rebuilt from git, and every memory the agent writes is a reviewable git commit. Served over one OAuth-secured MCP endpoint with hybrid lexical+semantic recall and a gated, git-first commit_note write tool.
    7
    8
    AGPL 3.0
  • A
    license
    A
    quality
    B
    maintenance
    Local-first project memory for AI coding agents. Records failed attempts, fragile files, and decisions per repo, and warns the agent via hooks before it repeats a recorded mistake.
    6
    89
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Self-hosted decision memory for AI coding agents. Captures decisions with the alternatives you rejected, and warns before an agent re-proposes a rejected approach.
    4
    81
    Apache 2.0

View all related MCP servers

Related MCP Connectors

  • Memory for coding agents: the decisions, the dead ends, and where the last session stopped.

  • Experience memory for coding agents: validated traps, fixes and dead-ends at decision time.

  • Give your AI agent a persistent map of your project's structure, dependencies, and bugs.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/MongLong0214/commitlore'

If you have feedback or need assistance with the MCP directory API, please join our Discord server