01
Code and history
Ask how retries are implemented and Memtro finds the file, reads it and points at the commit that changed it.
GitHub + Memtro
Issues, pull requests, code and commits, searchable by anyone who can ask a question.
Search issues and pull requests, read an issue, search code, read a file, list repositories and commits. Issues and PRs are anchored into memory linked to repositories and authors.
What you can do with GitHub in Memtro
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right GitHub tool, reads what it needs, and answers with the source cited.
02
Issues and pull requests
Which PRs touching billing are open, who reviews them, and what the linked issue says.
- Search issues and pull requests across your repositories
- Read an issue or PR with its comments
- Search code and read files at a ref
- List repositories and recent commits
- Hourly sync of recent issues, PRs and repositories
Ask it like this
Questions people ask once GitHub is connected. In agent mode each one also checks the other systems that know about the same people, companies or identifiers.
- ›Which PRs touched billing since September?
- ›Summarise open issues labelled P1 in acme/api
- ›Who last changed the retry policy and why?
Where it fits
Teams that get the most from GitHub in Memtro, with the rest of their stack attached.
- EngineeringKeep decisions from evaporatingDecisions, owners and deadlines are extracted from conversations and tool results into a typed, time-aware memory. Corrections supersede old facts instead of piling up next to them.
- ProductHear what customers actually ask forFeature requests are scattered across tickets, call notes, Slack threads and issues. Memtro reads them where they live, links them to the customers who raised them, and remembers which decision closed each one.
- Agent buildersMemory and tools for the agents you buildPoint your own agent at Memtro over the OpenAI-compatible API or MCP and it gets long-term memory, read-only connectors and model routing without you building any of it.
Better together
A record in GitHub is rarely the whole story. Connect the systems that hold the rest and the agent cross-references them by default, then remembers what it learned so the next question starts further along.
Also in Engineering and operations
Using something else for the same job, or both? Each connector has its own tools; connect as many as you like.
How to connect
- 01Create a fine-grained personal access token with read access to the repositories you want
- 02Paste it on Dashboard → Connections → GitHub, or use Sign in with GitHub where configured
Also works from
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The GitHub tools are the same everywhere.
Clients and agents →Questions
- Can Memtro change anything in GitHub?
- No. The GitHub connector is read-only: every tool reads, searches or lists. Nothing is created, sent, updated or deleted, and the credentials you give it should be read-only too.
- Who can use a GitHub connection?
- A personal connection serves only your own requests. A shared connection serves the organisation: everyone, or only the teams an admin chooses. Admins can always add shared connections; other members need the permission.
- Does Memtro store my GitHub data?
- Credentials are encrypted at rest. Tool results are cached briefly so agent loops do not repeat identical calls, and the facts the model extracts are saved to your organisation's memory with provenance (system, record and link) so they can be checked and superseded. An hourly sync anchors recently changed GitHub records into memory as entities.
- How do I connect GitHub?
- Token or OAuth. Create a fine-grained personal access token with read access to the repositories you want.
Connect GitHub in a few minutes
Seven-day free trial, then one monthly price per organisation. Connectors, jobs and memory are never metered.