Baz vs Greptile (2026)

Integrations cover GitHub, GitLab and Azure DevOps for source control; Jira, Linear, Monday, Shortcut, Azure DevOps Boards, YouTrack and Fibery for tickets; Figma for design; Notion and Google Docs for knowledge; Datadog and Sentry for the SRE agent; Slack for chat; and preview environments and a sandbox for running the app.

Sourcebaz.ai/docs/basics/integrationsread 2026-09-29

Reviews run on GitHub Cloud, GitLab.com, Bitbucket Cloud and Cursor Origin (beta) on every plan, with GitHub Enterprise Server, GitHub Enterprise Cloud with data residency, self managed GitLab, Bitbucket Data Center and Gitea on Enterprise and Perforce through P4 Code Review on premises. Context comes from Jira, Linear, Notion, Google Drive, Sentry and Datadog, and findings are delivered into Slack and the IDE.

Fix with your Agent sends a comment with file, line numbers and suggested fix straight to Claude Code, OpenAI Codex, Conductor, Cursor or Devin through a local bridge CLI, a Fix All control sends every issue at once, Greplooping lets an agent keep fixing until the review is clean, and comments are auto marked as addressed when a commit touches the flagged files.

A hosted MCP server, REST API, npm CLI and Zapier integration extend the reach, and the Partner Program adds maintained context for OpenAI, Vercel, Stripe, PostHog, Datadog, WorkOS, Mintlify and Braintrust.

Sourcegreptile.com/docs/integrations/code-providers, docs/integrations/fix-with-your-agent and greptile.com/independenceread 2026-10-28

Multiple agents divide the work on a change: SDLC agents (Fixer, Merger, SRE, Skill Maintainer) run independently in sandboxed environments alongside a set of individually scoped review agents, Merger decides after CI passes whether a pull request is safe to merge, and Planner produces an implementation plan that goes through approval before code is written.

Sourcebaz.ai/docs/agents/baz-agents and baz.ai/changelog 2026-07-01read 2026-09-29

The v5 review engine runs a swarm of narrowly scoped agents in parallel, each exploring one hypothesis for a potential bug, and aggregates their results into a single review. Greptile reports median review time falling from 5:04 to 2:25 and author addressed comments rising from 52 to 66 percent in production A/B tests.

The agent looks beyond the diff for similar logic, traces dependencies, reads git history and runs iterative passes that challenge their own hypotheses, with the maximum number of agentic turns configurable per review.

TREX runs as a companion agent that writes and executes tests, the security reviewer chains Opengrep pattern scanning, dependency analysis and AI exploit detection, and Greplooping hands findings to a coding agent repeatedly until the review comes back clean.

Sourcegreptile.com/blog/greptile-v5, greptile.com/changelog 2026-08-05 and greptile.com/independenceread 2026-10-28

Reviews run automatically when pull requests open across GitHub, GitLab and Azure DevOps, Merger runs after CI passes, and Skills Maintainer can scan on a schedule every three days, weekly or every two weeks. Comment commands, the CLI and the MCP server add runs on demand.

Sourcebaz.ai/changelog 2026-08-10 and docs/agents/baz-agentsread 2026-09-29

Reviews start automatically when a pull request opens in GitHub, GitLab, Bitbucket or Cursor Origin and run again on later commits under configured review triggers. TREX runs on every reviewed pull request or only on those matching branch, label, author or path rules, and skips changes with nothing to test. Reviews can also be started with @greptileai, a re trigger control, a reply in the thread, @greptileai trex, or the CLI on a local branch.

Sourcegreptile.com/docs/quickstart, docs/trex/overview and greptile.com/cliread 2026-10-28

Reviewers ground on the organization's repositories through API endpoints for file search, text grep and cross repository architecture search. They also take product intent from ticketing, Figma, Notion and Google Docs integrations, and the Spec Reviewer checks the code against it.

Sourcebaz.ai/docs/account/api-keys, docs/basics/integrations and docs/agents/baz-agents; baz.ai/docs/basics/integrationsread 2026-10-25

A graph index of the entire repository maps how functions, classes, files and directories connect and updates continuously, so reviews can reason about ripple effects beyond the diff, and a Knowledge Base generates and maintains documentation of how each part of the codebase works, how it connects and which past bugs and risks it carries, updated in real time as code changes, editable from the dashboard and served to coding agents over MCP.

Repo Clusters and a context.repos field give read only access to up to seven related repositories per review, with clusters suggested from shared contributors over the previous 90 days. A files.json file points reviews at existing schemas, API specs and architecture docs in the repository, and context also comes from Jira, Linear, Notion, Google Drive, Sentry and Datadog. The Partner Program supplies partner maintained documentation for supported third party APIs, and imported AI rules files, including CLAUDE.md and Cursor rules, become org wide context.

Sourcegreptile.com/knowledge-base, docs/code-review/cross-repo-context and greptile.com/pricing; greptile.com/docs/code-review/cross-repo-contextread 2026-10-28

Reviewer Memory stores a memory in a reviewer's own memory bank when similar feedback is given more than once, and updates that reviewer's prompt. Each memory can be switched on or off and shows its sources. An organization setting can hold new memories for admin approval before they go live, and admins control who may contribute. No lifetime, expiry or delete path is stated, so a disabled memory stays in the bank.

Sourcebaz.ai/docs/agents/working-with-agentsread 2026-10-25

Memory and Learning picks up team preferences from PR comments, replies to Greptile, reactions and whether comments were addressed between the first and last commit, suppresses comment types a team ignores, and turns repeated patterns into suggested rules. Its scope, lifetime and any way to review or delete what was learned are not stated.

Sourcegreptile.com/docs/how-greptile-works/memory-and-learningread 2026-10-28

Plans generated by Planner go through a dedicated approval workflow before implementation starts, and teammates can review plans together and track revisions, so a person approves before the agent's plan is built. Merger returns a merge, reject or escalate verdict after CI passes and labels the pull request; it approves only when a rule turns on auto approve, and merges only when configured to act autonomously, otherwise the verdict is left for a human reviewer to act on.

Sourcebaz.ai/docs/agents/baz-agents and baz.ai/changelog 2026-07-01 and 2026-09-24read 2026-10-28

Greptile posts its reviews and, where enabled, approves pull requests on its own after a clean five out of five review at or below a risk cap the customer sets, with exclusion filters by label, branch, file and author.

Authentication, secrets, billing, migrations, infrastructure, CI and public APIs form the critical risk tier, so they are held back only when the cap sits below critical or the paths are excluded; with no cap set the page says it can approve any clean review, and an option counts TREX results in the decision. Custom rules shape what it flags. These controls constrain the agent, but no step where a person approves the agent's action before it lands is described.

Sourcegreptile.com/docs/code-review/auto-approve-prs, docs/trex/overview and greptile.com/changelog 2026-06-26; greptile.com/docs/code-review/first-pr-reviewread 2026-10-28

Baz states that it is SOC 2 certified, Enterprise adds SSO, centralized controls and VPC deployment, and API keys are limited to a whitelist of endpoints under the creator's permissions.

Sourcebaz.ai/docs/account/security-privacy-and-compliance, baz.ai/pricing and docs/account/api-keysread 2026-09-29

Greptile is SOC 2 Type II compliant, with the report, penetration test results and subprocessor list in its Trust Center at trust.greptile.com, and it holds zero data retention agreements with its LLM providers. Single sign on with SAML and role based access control come with Enterprise, along with audit logs.

Greptile Cloud runs on AWS with customer code cached on an encrypted filesystem until access is revoked, an admin can delete all customer data within 24 hours, and de identified data may be used to train Greptile's models unless an admin turns that off, which self hosted deployments never do. The whole service can also self host into a customer VPC or an air gapped environment with customer supplied LLM providers.

Sourcegreptile.com/security (updated 18 October 2026) and greptile.com/pricingread 2026-10-28

Session Logs let a team inspect how each run was triggered, where it executed, its status, the major stages it completed, its outcome and its cost, and the API records MCP session events.

Sourcebaz.ai/changelog 2026-06-01 and docs/account/api-keysread 2026-09-29

Each TREX flow keeps a step by step record of what the agent did and a captioned video of the run, posted to the pull request with live progress while it runs and retained for 30 days to anyone with read access to the repository. The analytics dashboard tracks reviews, addressed rate, bugs caught and merge times with export, and Enterprise adds audit logs. The review agent itself keeps outcomes rather than a step trace.

Sourcegreptile.com/docs/trex/overview, docs/trex/results and docs/analytics; greptile.com/docs/trex/resultsread 2026-10-28

Private Mode, on Pro and Enterprise, keeps source code stored only in the customer's own VPC through a file system service pod on AWS EKS, with analysis on Baz infrastructure reading it transiently. Enterprise adds self hosted deployment in the customer's own cloud, and private application review can run the sandbox inside the customer's Kubernetes as a limited preview.

Sourcebaz.ai/docs/account/private-mode and baz.ai/pricingread 2026-10-25

The entire service can be self hosted, including in air gapped environments, using Docker Compose on a single Linux VM for up to 100 developers or Kubernetes with Helm for 100 or more with horizontal scaling and high availability. Sizing requirements are published, and parallel deployments give a migration path between the two. An AWS Terraform module provisions VPC, EC2, RDS PostgreSQL and ElastiCache Redis and bootstraps the application, and manual setup covers GCP, Azure and on premises.

Self hosted customers bring their own LLM provider by base URL and keys, choosing among OpenAI, Anthropic, AWS Bedrock, Azure OpenAI and GCP Vertex AI, so inference stays on customer infrastructure; the deployment repository is public at github.com/greptileai/akupara and self hosting requires a license. Greptile Cloud runs on AWS, and Enterprise adds GitHub Enterprise Cloud with data residency and Perforce for on premises deployments.

Sourcegreptile.com/docs/deployment-options, greptile.com/security and docs/integrations/code-providersread 2026-10-28

Baz ships named built in agents with their own jobs, among them Fixer, Spec Reviewer and an AI SRE agent. Five core review agents (Code Correctness, Code Quality, Basic Security Patterns, Advanced Security and AI Coding Guidelines) replaced eleven narrower reviewers in October 2026, and teams can build customized agents on top.

Sourcebaz.ai/docs/agents/baz-agents and baz.ai/changelogread 2026-10-25

The Partner Program supplies vendor curated review context for third party APIs, so a pull request that touches a supported partner API, SDK, config or integration is reviewed against partner maintained documentation, implementation rules and common failure patterns, with comments marked by partner logo and linked to the relevant docs.

It is on by default for all users, with featured partners including OpenAI, Vercel, Stripe, PostHog, Datadog, WorkOS, Mintlify and Braintrust. Greptile also ships two named agents, the code reviewer and TREX, and imports existing AI rules files, including CLAUDE.md, AGENTS.md and Cursor rules, as org wide context. There is no browsable catalog, marketplace or gallery of installable agents or templates.

Sourcegreptile.com/partners and greptile.com/pricingread 2026-10-28

Baz's agentic reviewers run on OpenAI's GPT-5-Codex with Anthropic Sonnet 4.5 reflections, and Baz chooses the models, with no customer model selection, bring your own key or local model option offered.

Sourcebaz.ai/changelog 2025-10-16read 2026-09-29

Review settings let the customer choose which AI model powers reviews and set the maximum number of agentic turns per review, balancing speed, depth and cost.

Model Inversion, marked experimental, detects from commit trails, branch prefixes and PR titles when a coding agent wrote a pull request and routes the review to a different model, so Claude authored code is reviewed by GPT and GPT authored code by Claude.

The cloud service combines frontier models from OpenAI and Anthropic, and self hosted deployments bring their own provider by base URL and keys, with OpenAI, Anthropic, AWS Bedrock, Azure OpenAI and GCP Vertex AI supported, so models run entirely on customer infrastructure.

Sourcegreptile.com/changelog entries of 2025-09-26 and 2026-07-22, greptile.com/independence and docs/deployment-optionsread 2026-10-28

API keys call the Baz REST API (v2, under /api/v2/ with an x-api-key header) and the Baz MCP server for scripts, CI and unattended agents, with twelve endpoints covering reviewer configuration, review discussions, repository search, plan creation and versioning, plan comments and linking pull requests to plans.

Sourcebaz.ai/docs/account/api-keysread 2026-09-29

A REST API exposes Index Repository, Query Repos, Search Repos and Get Repository Info, alongside webhooks, with API keys issued from app.greptile.com/settings/api.

A hosted MCP server at api.greptile.com/mcp, configured by bearer token in Claude Code, Claude Desktop, Cursor and VS Code, lets assistants trigger and re run reviews, inspect results, manage custom context and update repository rules, and the Knowledge Base MCP on Pro serves the maintained codebase documentation to coding agents.

An npm CLI runs reviews locally, with --json for machine readable output and --agent for agent workflows and scripts, and greptile onboard sets up an organization from the terminal. A Greptile plugin ships in Anthropic's official Claude Code marketplace, and a Zapier integration is published.

Sourcegreptile.com/docs/mcp/setup, greptile.com/knowledge-base, greptile.com/pricing and greptile.com/changelogread 2026-10-28

Prompt Playground lets a team test a review agent's behavior on real change requests before rollout and tune its tone, scope and strictness without pushing untested agents to production, and Evaluations report reviewer performance with usage metrics and comment tracking.

Sourcebaz.ai/changelog 2025-05-22 and 2025-07-29read 2026-09-29

Every pull request is reviewed for logic, security and cross file bugs, with confidence scores and P0 to P2 severity. TREX, in beta, works out which user flows a change affects, starts the app in a sandbox built from an environment the customer configures, exercises those flows like a user and runs targeted tests, posting what it tested and what broke with logs, traces and a video, so the tests act as a quality gate before release and can feed the auto approval decision.

Sourcegreptile.com/trex, docs/trex/overview, docs/trex/environments and greptile.com/changelog 2026-06-15read 2026-10-28

Spec Reviewer clones the repository, restores dependencies, runs the setup and start commands, waits for the application to become healthy and opens it in a browser to check the built experience against the specification.

Sourcebaz.ai/changelog 2026-07-29read 2026-09-29

TREX, in beta, starts the customer's app in a sandbox built from a configured environment and uses it the way a person would, clicking, typing and observing what is on the screen, on every reviewed pull request or on those matching rules. It records a video of every flow it runs. Each TREX run costs 3 credits on top of the review, charged only when a flow reaches a pass or fail.

Sourcegreptile.com/docs/trex/overviewread 2026-10-28