repo-memory-mcp
mcp-name: io.github.Umarjaum/repo-memory-mcp
Persistent memory for AI coding agents
AI coding agents are powerful, but they forget repository-specific corrections, conventions, and architectural decisions. repo-memory-mcp gives an MCP-compatible coding agent a persistent, local, repository-aware memory layer.
Teach your coding agent once. Let your repository remember.
Why it exists
MCP hosts decide when tools are called; MCP does not automatically intercept every conversation. This project therefore exposes explicit tools for startup context, searching, storing corrections and decisions, updating stale guidance, and archiving obsolete memories.
Features
- Repository-scoped SQLite storage in
.repo-memory/ - FastMCP tools for corrections, rules, decisions, search, and startup context
- Deterministic local relevance scoring; no pretend semantic search
- Local-first, API-key-free, cloud-free, telemetry-free operation
- Conservative secret detection for explicitly submitted content
- Import/export and audit-friendly archiving
- Python 3.10+, Pydantic v2, pytest, standard-library-first design
Install
For local development:
pip install -e .[dev]
repo-memory doctor
After publishing the package to PyPI:
pip install repo-memory-mcp-ai
uvx repo-memory-mcp-ai
The published-package commands should only be used once the package is publicly available.
Configure an MCP client
The examples in examples/ use the common stdio configuration shape. Clients can differ; follow the client’s documented MCP configuration format.
Tool workflow
- New session: call
get_startup_context(). - Developer correction: call
remember_correction(topic, lesson). - Relevant work: call
recall_memory(query). - Obsolete guidance: call
forget_memory(memory_id).
Your memories stay on your machine. The implementation does not require API keys, cloud accounts, remote databases, external embeddings, or telemetry. The claims apply to this codebase as shipped; your operating system, package manager, backups, or MCP host may have separate behavior.
Development
pytest
repo-memory init
repo-memory list
repo-memory search "pydantic models"
Roadmap
Future work may improve ranking, add confidence feedback, provide optional local embeddings, generate project context, and add a memory inspection UI. Team/shared memory remains explicitly opt-in.
License
MIT. See LICENSE.
1 maintainer
Metadata
1 maintainer
Release files for repo-memory-mcp-ai 0.2.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| repo_memory_mcp_ai-0.2.0.tar.gz | 16.0 kB | Without provenance | Details for repo_memory_mcp_ai-0.2.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| repo_memory_mcp_ai-0.2.0-py3-none-any.whl | Python 3 | none | any | Details for repo_memory_mcp_ai-0.2.0-py3-none-any.whl |
Total release size: 29.3 kB
Release files / repo_memory_mcp_ai-0.2.0.tar.gz
| Download URL | repo_memory_mcp_ai-0.2.0.tar.gz |
|---|---|
| Size | 16.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
b40af28d46b89f9c0ed2226d7ca1056c9ceb8c9f07d18d6e03b2038c921f5387
|
|
BLAKE2b-256 checksum How to use checksums |
55981906d433eef4164185ba9d953cdeb83770dca83030833b4285c9102a4708
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.12.1 {"installer":{"name":"uv","version":"0.12.1","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / repo_memory_mcp_ai-0.2.0-py3-none-any.whl
| Download URL | repo_memory_mcp_ai-0.2.0-py3-none-any.whl |
|---|---|
| Size | 13.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
db49aced7591e8932787e21d581fb31d2f2034e053290321b9cfe25e88e4d7ab
|
|
BLAKE2b-256 checksum How to use checksums |
26490aec157bf707253028fe48b74cb04ff930aad61c04346d922132628e04a3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.12.1 {"installer":{"name":"uv","version":"0.12.1","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Security for repo-memory-mcp-ai 0.2.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
