Moresq Corpus

The useful tool surface is small: search, retrieve, apply, report issue and learn from outcome. Everything else should support trust and governance, not flood the model with raw chunks.

A private MCP corpus is often the right internal first version. Moresq Corpus is the productized version when teams need walleting, receipts, quality labels, learning exports and cross-agent portability.

The corpus is tuned for implementation cards, runbooks, snippets and prior fixes rather than generic documents. That makes retrieval actionable inside terminal coding workflows.

From search to an auditable implementation

A pattern you verified is worth more sanitized and shared than sitting in one repo. Deposit through the console (corpus.deposit) — pay the scan fee, pass the automated admission scan, and it's retrievable by other agents immediately. You earn a share of every future retrieval fee.

Corpus is not a promise that every retrieved snippet is correct, a replacement for code review, or a silent training dump of private chats. It is a governed reuse layer: the process verifies provenance and review evidence, while the developer remains responsible for fit, testing and the final change.

MCP gives agents a standard tool surface. A serious code corpus also needs review queues, source metadata, receipts, revocation and learning from misses.

Moresq Corpus lets coding agents search reusable implementation cards, retrieve relevant snippets with proof receipts, and learn from misses, applies and corrections.

Does retrieval remove the need for code review?

No. Retrieval can reduce repeated work and expose provenance, but developers still need to check project fit, security implications and test results before shipping.

Why AI coding assistants lose context, repeat code and forget repo decisions — and how retrieval-first repo memory fixes the workflow.

Agent repo memory for Claude Code, Codex, Cursor and MCP clients: retrieve proven implementation patterns before regenerating code.

Verified code snippets with source metadata, review status, proof receipts and revocation for AI coding agents.

A retrieval-first coding workflow where agents search known patterns, retrieve compact context and generate only the project-specific adaptation.

Local Markdown/Obsidian knowledge substrate for MCP agents with governed memory and hybrid search.

Local-first long-term memory for coding agents — in-process embeddings (MLX/CPU), hybrid vector+BM25 search, markdown as source of truth. No cloud, no keys.

Local-first memory across sessions where Markdown files stay the source of truth and the search index is a rebuildable artifact.

Local-first MCP server for searching private Obsidian vaults with hybrid full-text, fuzzy, semantic, and wikilink graph retrieval.

Self-hosted MCP server for Obsidian: semantic + full-text search, wikilink graph, note CRUD, OAuth, and a self-describing vault guide.

Search your past OpenCode conversation history before starting new work, via a local read-only FTS5 index — no network calls.

Turn LinkedIn saved posts into a queryable knowledge base you can search, chat with, and connect to Claude or ChatGPT through MCP.

Persistent coding memory for AI assistants — MCP stdio + remote URL, hybrid search, knowledge graph, token-efficient context. Self-host on Cloudflare D1 or Postgres.

A local-first, generic memory layer for MCP agents, with multilingual hybrid search and reranking, versioned memories, provenance, temporal recall, relationships, feedback, and secure multi-agent spaces.