langgraph-harnessThe engineering context platform for GitLab
Reviews merge requests, resolves issues autonomously, and chats with full project context — remembering what matters so every run builds on the last.
Skip to content
WebhookIssueManual · ScheduledInteractive
Workflows
Four ways to run
MR Review
Fires on webhook events — reads the diff, drafts comments, and publishes them, no polling or manual trigger.
Issue Resolution
Assign an issue and the agent implements the fix in a sandboxed checkout, opens a draft MR, and keeps responding to follow-up comments.
Task Resolution
The same sandboxed loop, started from a free-text instruction instead of a GitLab issue — on demand or on a recurring schedule.
Chat
A GitLab-aware assistant with full GitLab access, live web fetch, image uploads, and semantic search across past reviews and project history.
Trust
Kept honest
Guardrails & Self-Correction
A run that repeats a tool call, ends on an unfinished-looking question, or skips checking for new feedback gets caught and corrected mid-run, not after the fact.
Quality Control Before Publish
Every drafted comment is screened for low-value noise, and its diff position is verified before and after posting — GitLab's own publish response isn't trusted blindly.
Sub-agents
MR Review can spawn an isolated verifier for a single file's change, so its own investigation doesn't fill the parent run's context — findings come back reported, not just trusted.
Operations
Memory, analytics, and self-hosting
Durable Memory
The agent flags durable, project-specific facts as it works — conventions, recurring false positives, team decisions — seeding every future run of the same project.
Live Analytics
A React admin UI shows live runs, queue state, and per-project analytics — reliability, guardrail health, comment acceptance rate, and more.
Self-Hostable
A single Docker Compose stack. Bring your own GitLab instance, your own LLM backend (OpenRouter, Ollama, or sglang), and your own data.