The callback accepts provider state without matching it against the session, which can allow account-linking mixups.
Cadrai is a seven-agent cloud engineering team — PM, Architect, Engineer, QA, UI/UX, Code & Docs Reviewers — that plans, builds, tests, and ships pull requests while you sleep, ski, or hang with friends. Brief the PM from MCP, Claude, OpenClaw, or a one-line curl. They'll take it from there.
Each task runs in its own DevBox, and each agent gets its own role, prompt, and worktree. They hand off through a broker — and every line of the transcript is yours.
Brief the PM. The team plans, builds, tests, and ships — and only pings you when there's a real decision to make.
auth_providers table. Store refresh tokens encrypted. 3 new routes.task/417 → main. 14 commits, +612 −48. Passing checks. Ready for your review.For high-stakes changes, Cadrai can replace the single Code Reviewer with a Review Board. Three independent review agents, each with their own configured provider and model. Let them debate, then get one persisted verdict with blockers, dissent, and remediation attached.
The callback accepts provider state without matching it against the session, which can allow account-linking mixups.
The failure path logs the full token exchange response. Redact credentials before emitting broker diagnostics.
[Reviewer 1] final_vote block; issues: RB-1, RB-2 [Reviewer 2] final_vote approve; RB-1 accepted [Reviewer 3] final_vote block; issues: RB-1, RB-2 [Board] verdict=blocked tally=2/3 persisted=true
Validate tenant, project, and task context.
Inject real provider or GitHub credential server-side.
Return response without exposing the token boundary.
Each task runs in an isolated DevBox with its own task branch and worktrees. Agents receive placeholder credentials only. LLM and GitHub calls go through a credential proxy, where real secrets are injected server-side.
The PM routes work through the agentic team, and each agent can be tuned independently: provider, model, and thinking level. Put the Docs Reviewer on a fast model, Engineer on a model that scores high in coding, and the Code Reviewer on a model with high reasoning.
PM turns the request into assignments.
Architect defines approach and risks.
Engineer implements on the task branch.
QA checks behavior and regression risk.
Quality gate decision before handoff.
Watch every agent's terminal in real time. Click any file path to jump into your editor. Multi-project tabs — because you have more than one thing shipping.
Every task gets its own Firecracker microVM and its own git worktree on a task/<id> branch. No collisions, no polluted main, no "works on my machine."
Agents never see API keys. LLM + GitHub calls route through a credential proxy that injects secrets server-side. Six layers of tenant isolation, end to end.
WIP auto-commits push to the task branch constantly. If a DevBox dies, your work is already safely on the remote. Squash before merge, of course.
The PM escalates to email after ~30 minutes of waiting on a human decision. You're not glued to the dashboard — you're running a team.
Every operator-visible line of transcript is durably persisted per task. Come back a month later, scroll the conversation, know exactly why a decision was made.
Cadrai ships with an MCP server and a REST API. Point Claude, OpenClaw, Cursor, a Discord bot, or your in-house agent at it — submit tasks, check status, answer the PM, all from wherever you already work.
task_id you can poll.# submit a task from anywhere — your terminal, a cron, another agent. curl -X POST https://cadrai.dev/api/v1/tasks \ -H "Authorization: Bearer cdt_live_..." \ -H "Content-Type: application/json" \ -d '{ "project_id": "proj_7f3a", "title": "Add Google + GitHub OAuth to checkout", "brief": "Use OAuth2 with PKCE. Store refresh tokens in Vault.", "priority": "normal" }' # → { "task_id": "tsk_417", "status": "queued", "dashboard": "..." }
/data/worktrees/<taskId>/. WIP auto-commits push to the remote every 15 minutes. When the task is done, the DevBox is released.submit_task, check_messages, and reply_to_message tools, plus a REST API with the same powers. Point Claude, OpenClaw, your in-house agent, a Discord bot, or a cron job at it — your call.Private beta. We'll ping you when you're in. No newsletter spam, no LinkedIn thought pieces, no "10 prompts every founder should know."