Sprint 4 is closed.
The goal was to connect Meronq to GitHub as the first external engineering system — reading metadata, issues, and pull requests, then translating that data into CEM and local memory.
What Sprint 4 delivered
Every item on the roadmap is checked off:
- Repository metadata — stars, branch, description
- Issues and PRs — GitHub REST API
-
CEM translation —
issue:owner/repo#N,pull_request:owner/repo#N - Summaries — issue and PR text summaries
- Doc draft — markdown from git log + GitHub
Local MCP v1.13.0 — github_sync, github_status, github_summarize, github_doc_draft.
New package: @meronq/github
scanProject → CEM → fetchGitHubSnapshot → appendGithubToCem → SQLite memory
Auth: GITHUB_TOKEN (PAT). Cache: .meronq/local/github-snapshot.json.
CLI
meronq github sync
meronq github status
meronq github summarize issue 3
meronq github doc
Sprint 5 — MCP Server
Expose Meronq as a product MCP surface with handshake, memory search, and permissions.
Follow along
Read the full post on meronq.pages.dev · Source on GitHub
Top comments (0)