Store and retrieve repository context with automatic freshness verification and citations. Developers use this to maintain accurate, time-bounded memory of codebases without stale information polluting AI conversations.
io.github.cognitivemyriad/verified-repo-memory
Local install
STDIO
No auth required
How models use it and what it is built for.
Store and retrieve repository context with automatic freshness verification and citations. Developers use this to maintain accurate, time-bounded memory of codebases without stale information polluting AI conversations.
Local install — runs as a subprocess.
Configuration this server reads at startup.
Default TTL in days (1-365).
Override data dir path.
Max file parsing size bytes.
Enable secret scan (on/off).
Where to find authoritative docs and source for Verified Repo Memory.
Paste any of these into Agent Studio after connecting Verified Repo Memory.
Common questions about connecting and running Verified Repo Memory.
What does 'just-in-time verification' mean in this MCP server?
The server validates stored repository data against the actual codebase when you retrieve it, ensuring citations remain accurate. If data has exceeded its TTL (set via VRM_TTL_DAYS), it flags or refreshes the information automatically.
How do I set up Verified Repo Memory locally?
Install via `npx @cognitivemyriad/vrm-local@0.1.2`. Configure VRM_TTL_DAYS (1–365 days), VRM_DATA_DIR for storage location, VRM_MAX_FILE_BYTES for file size limits, and VRM_SECRET_SCAN to enable secret detection.
Can this server prevent secrets from being stored in repository memory?
Yes. Set VRM_SECRET_SCAN to 'on' to enable secret scanning. This prevents API keys, tokens, and credentials from being cached in your repository memory.
What happens when stored repository data expires?
Data older than VRM_TTL_DAYS is marked stale. The server will flag it as unverified or prompt re-validation against the live repository on next retrieval, preventing outdated context from being used.
Is there a file size limit for repository parsing?
Yes. VRM_MAX_FILE_BYTES controls the maximum file size the server will parse. Adjust this if you're working with large codebases or want to exclude massive generated files from memory.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 60+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent StudioJudges Panel
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Addozhang Nexus
Query Sonatype Nexus Repository (OSS/Pro) for Maven, Python, and Docker artifacts
Cyanheads MCP Ts Template
TypeScript template for building MCP servers with declarative tooling, observability, and auth.
Chernistry Bernstein
Declarative agent orchestration for engineering teams