Anyshift vs Doctor Droid (2026)

Integrations cover AWS, GCP, Azure, Cloudflare, GitHub, GitLab, Kubernetes, Datadog, Grafana, Splunk, PagerDuty, incident.io, Sentry, Jira, Confluence, Notion and Linear. Annie posts RCA results as PagerDuty notes and incident.io comments and opens pull requests through a separate agentic GitHub app. The integrations number 25+, and the graph also reads Terraform code and Terraform state.

SourceAnyshift, docs.anyshift.io Root Cause Analysis, Propose Fix and llms.txt indexread 2026-10-05

DrDroid offers 80+ integrations across AWS, GCP, Azure, GitHub, Datadog, Grafana, PagerDuty, Slack, Linear and Jira, runbook based remediation, and ArgoCD rollbacks, with write access granted only when rollbacks and permissions are configured.

The connectors cover observability tools such as Grafana with Loki and Mimir, Prometheus, CloudWatch, Azure Log Analytics, Google Cloud metrics and logs, New Relic, Datadog, Elasticsearch, OpenSearch, Sentry, SigNoz, Coralogix, VictoriaLogs and PostHog, Kubernetes on EKS, AKS, GKE or self managed clusters, and databases including BigQuery, ClickHouse, MongoDB Atlas and PostgreSQL.

Incident and work tools include Slack, Microsoft Teams, email, Opsgenie, PagerDuty, Jira, Confluence, Rootly and Zenduty, and code access runs through GitHub, GitHub Actions, Bitbucket and Jenkins. The agent can also run bash and remote server commands. Every plan includes unlimited integrations.

SourceDrDroid, drdroid.io, /pricing and docs.drdroid.io Common FAQs and llms.txt indexread 2026-10-05

Annie runs its own investigation across the graph, logs and traces and returns a timeline, root cause and remediation steps, coordinating specialized agents along the way. Customers tune it with instructions, personas and effort modes, and automation rules route Slack messages with fallbacks for each sender and a fixed default. There is no builder, branching or multi agent flow that customers control.

SourceAnyshift, docs.anyshift.io Root Cause Analysis and llms.txt indexread 2026-10-05

Teams build agents for alert tuning, deployment tracking, investigations, remediation, reporting and retrospectives on the open source PlayBooks runbook engine, and agents can be triggered 'from an alert, a conversation, another agent, or your own automation', with A2A delegation.

The named agent jobs run from alert middleware, the first response to every alert, through alert tuning that adjusts thresholds and files tech debt tickets, canary deployment tracking, end to end investigation and auto remediation, to observability gap analysis, cost and monitoring reports, long horizon infrastructure migration and retrospectives. Outside MCP servers a team connects become tools inside playbooks and custom actions. Investigations draw on credits, 99 a month on the $99 Startup plan with $1 top ups and volume credits on Business and Enterprise.

SourceDrDroid, drdroid.io, /pricing and docs.drdroid.io MCP Server integrationread 2026-10-05

RCA starts automatically when an incident is created in PagerDuty or arrives through a webhook from incident.io, and investigations also start on demand from Slack and the Remote MCP, from pull request analysis and from proactive detection. Saved reports can run on a schedule, and automation rules let Annie act on Slack messages by itself.

SourceAnyshift, docs.anyshift.io Root Cause Analysis and llms.txt indexread 2026-10-05

Investigations start on alerts, PagerDuty pages, alertmanager webhooks, cron jobs and API calls from CI/CD, as well as Slack and Microsoft Teams threads, and auto investigation rules fire on alert filters and severity. Automations on the Startup plan run from Slack only, Business adds Teams, Google Chat, PagerDuty, Opsgenie, Zenduty and custom sources, and Enterprise adds ServiceNow and Jira Service Management. Claude and Cursor can start work through the MCP server, and other agents can hand work to DrDroid over the A2A protocol.

SourceDrDroid, drdroid.io and /pricingread 2026-10-05

Annie and other agents query one versioned knowledge graph of infrastructure, applications, identity and team tools, with timestamped state changes and entity resolution that joins an EC2 instance, a Kubernetes pod, a GitHub repo, a Jira ticket and a Confluence page into single nodes. The graph links Terraform code, Terraform state and live infrastructure, and change history shows what changed and when before an incident.

SourceAnyshift, anyshift.io and docs.anyshift.io llms.txt indexread 2026-10-05

'DrDroid maps every repo, dashboard, K8s pod and cloud resource into one live knowledge graph' that traces blast radius when an alert fires, alongside uploaded documents and runbooks the agent draws on. Cross tool correlation and a decision engine work over that graph. When it picks queries, the agent combines log patterns with the alert, the runbooks and debugging knowledge, and it tries further queries when the first ones fail. It forms its hypotheses from live context, the dashboards and integrations available and the documents it can reach.

SourceDrDroid, drdroid.io and docs.drdroid.io Common FAQsread 2026-10-05

After each investigation Annie reflects and curates learnings that inform later investigations, covering infrastructure patterns, normal baselines and error signatures, effective queries and dashboard locations, and which services power which features and who owns them. Users add custom knowledge Annie cannot learn on its own, such as team conventions, vendor specifics and escalation procedures. Anyshift does not say who the learnings apply to, how long they are kept or how to view or delete them.

SourceAnyshift, docs.anyshift.io Memory and Agentsread 2026-10-05

A named AI Memory 'holds your service graph, runbooks, docs, and every live signal, alerts, deploys, conversations, incidents' across investigations, and the service graph doubles as the product's knowledge graph. DrDroid does not say who can see the remembered conversations and incidents, how long they are kept or how to delete them. The memory builds patterns over time so an engineer starts an incident with context already in place. Source code sessions are the exception, since each one starts fresh with nothing carried over.

SourceDrDroid, drdroid.io and docs.drdroid.io Source Code Securityread 2026-10-05

Annie's only write action, a fix pull request, runs when a person clicks Propose Fix on a hypothesis or answer. Write access is isolated in a separate agentic app while investigation stays read only, and nothing reaches production until a person merges the pull request.

Sourcedocs.anyshift.io/pages/product/propose_fixread 2026-09-29

Remediation runs from runbooks with human approvals, so responders approve remediations without leaving the thread, and the agent does not have access to execute write commands by default, with write access granted only alongside rollbacks and permissions. Responders can ask questions, approve a remediation and close the investigation from the same Slack or Teams thread. When the coding agent proposes a fix, it opens a pull request on a feature branch, cannot change the default branch and respects the repository's protection rules.

SourceDrDroid, drdroid.io and docs.drdroid.io Common FAQs and Source Code Securityread 2026-10-05

Role based access control, multi factor authentication and single sign on are supported, with roles and permissions set out in their own documentation. Anyshift holds AICPA SOC 2 Type II, covering security, availability, processing integrity, confidentiality and privacy, and a trust portal is published at trust.anyshift.io. The platform runs on AWS with encrypted storage, data isolation and retention policies, and code is scanned continuously for secrets, vulnerabilities and risky dependencies.

SourceAnyshift, docs.anyshift.io compliance and llms.txt indexread 2026-10-05

Access controls include SSO and SAML, SSO and SCIM with an audit log on Business, and RBAC and access management with PII scrubbing. DrDroid reports SOC 2 Type II compliance, and the Enterprise plan lists both SOC 2 Type II and ISO 27001.

Integrations are read only by default, data is encrypted at rest and in transit, and the agent never holds API keys itself, since an execution engine stores the credentials. Enterprise also lists an IP allowlist.

Source code is analyzed inside short lived E2B micro VMs that are destroyed after each session, with no context carried between sessions and none of it used for training.

SourceDrDroid, drdroid.io, /pricing and docs.drdroid.io Common FAQs and Source Code Securityread 2026-10-05

Each RCA carries a timeline of events, root cause details with evidence from the customer's systems and affected resources, and fix PRs link back to the conversation, but there is no record of the steps, queries or tools Annie used in the run, and retention is not stated. Saved reports can be reused and scheduled, and change history shows what changed, when, and what came before an incident.

SourceAnyshift, docs.anyshift.io Root Cause Analysis and llms.txt indexread 2026-10-05

An audit export of task execution records, retrieved over the API, can be filtered to executions performed by the 'Drdroid agent' and shows who ran each task, when, and the activity. Investigations are shared across the team on every plan, and on PagerDuty the findings arrive already attached to the page. The audit log in the product starts on the Business plan.

SourceDrDroid, docs.drdroid.io Audit, drdroid.io and /pricingread 2026-10-05

The product is SaaS with a 30 minute setup, and there is no self hosting, VPC, region or residency option. The service runs on AWS.

SourceAnyshift, docs.anyshift.io complianceread 2026-10-05

DrDroid is cloud hosted, or self hosted in the customer's VPC by Helm or Docker Compose with air gapped support. Business offers self hosting, and Enterprise self hosts in the customer's VPC with zero outbound traffic to DrDroid. Business runs from $999 a month in DrDroid's cloud or from $2,999 a month self hosted, and Enterprise adds custom data residency. The $99 Startup plan is cloud only, with one click setup.

SourceDrDroid, drdroid.io and /pricingread 2026-10-05

There is one agent, Annie, with product capabilities (RCA, reports, proactive detection, propose fix) and Graph API use cases (alert noise, configuration churn, pull request blast radius). Those are features of one product, not separate agents or templates a customer adopts. Saved reports can be reused across the team.

SourceAnyshift, docs.anyshift.io llms.txt indexread 2026-10-05

Teams build their agents for listed jobs on the PlayBooks engine. The open source projects (PlayBooks, droidctx, Status Page Aggregator, Kenobi, VPC Agent) are tools, and no catalog of prebuilt agents or playbook templates is published. Nine agent jobs are listed, among them Alert Middleware, the Investigation Agent, the Deployment Tracking Agent, the Infrastructure Migration Agent and the Retrospective Agent.

SourceDrDroid, drdroid.ioread 2026-10-05

Anyshift lists its model providers among its external providers, and customers cannot choose the model. An effort mode trades speed against depth of reasoning, and personas set tone, depth and assumptions, but neither changes the model.

SourceAnyshift, docs.anyshift.io compliance and llms.txt indexread 2026-10-05

On the Business plan the customer can bring its own LLM or use DrDroid's, while Startup includes a managed LLM. The coding agent that analyzes source code is built on Claude Code. The models behind investigations on the managed option are not named.

SourceDrDroid, drdroid.io/pricing and docs.drdroid.io Source Code Securityread 2026-10-05

There is a read only Graph API over HTTP with a TypeScript SDK (@anyshift/graph-sdk), a CLI, a Graph MCP server and a published OpenAPI specification, plus Annie Remote MCP for triggering RCA from an IDE. The Graph API serves code, CI pipelines, internal platforms and other AI agents, and the CLI works from the terminal, scripts and CI.

SourceAnyshift, docs.anyshift.io Graph API and llms.txt indexread 2026-10-05

The DrDroid MCP server at aiops.drdroid.io/mcp/ uses bearer API keys and offers tools that update the service catalog, create and edit runbooks, and manage alert definitions and auto investigation rules, beside a published OpenAPI specification and API triggers.

DrDroid also works as an MCP client, connecting to a team's own MCP servers with bearer tokens, API keys or basic auth so their tools appear in playbooks and custom actions.

The open source projects include the PlayBooks engine, droidctx, a Status Page Aggregator, Kenobi and a VPC Agent, and the docs include a guide to building your own AI debugging agent.

SourceDrDroid, docs.drdroid.io DrDroid MCP Server, MCP Server integration and llms.txt indexread 2026-10-05

Pull request blast radius and drift detection check the customer's infrastructure changes before they ship, which tests the change, not the agent. There is no way to test Annie's own answers. Drift detection shows the gap between what Terraform declares and what is actually running.

SourceAnyshift, docs.anyshift.io llms.txt indexread 2026-10-05

DrDroid says 'Every alert, deploy, and incident strengthens the graph', and gives no more detail on how the agent improves. Alert tuning adjusts the customer's alerts, and DrDroid publishes no way to test or score the agent. The Retrospective Agent looks back over past incidents for long term improvements, and the Observability Agent reviews metric cardinality, logs and telemetry gaps in the customer's own monitoring.

SourceDrDroid, drdroid.ioread 2026-10-05

Annie works through integrations, read only live queries, Slack, pull requests, an API and MCP, and does not control a browser, desktop or computer. The only write access sits in a separate agentic GitHub app that opens fix pull requests.

SourceAnyshift, docs.anyshift.io Root Cause Analysis and Propose Fixread 2026-10-05

DrDroid acts through integrations, runbooks, commands and APIs and does not control a browser, desktop or computer. Commands on servers run through the bash and remote server command integrations, not a screen.

SourceDrDroid, drdroid.io and docs.drdroid.io llms.txt indexread 2026-10-05