DevsHub.ai
Invite only Early access — request an invite to get started

Your terminal. Your IDE. Your browser.
One autonomous engineering team.

DevsHub is a developer-first AI engineering platform that puts autonomous agents in your terminal, IDE, and browser. Agents plan, write, test, debug, and operate real workflows with multi-agent orchestration, permission guardrails, and precise local codebase intelligence. Use your preferred models, external coding agents, infrastructure, and API keys — with no vendor lock-in or token markup.

Multi-agent orchestration, permission guardrails, and ephemeral VMs on AWS, GCP, Docker, or your own hardware.

30+
Built-in tools
4
AI providers
5
Permission levels
MCP
Native extensions
BYOK
Your keys, at cost
Why DevsHub

Built for teams who ship,
not teams who rent AI.

Most AI coding products lock you into one model, mark up your tokens, and run code on their infrastructure. DevsHub is the opposite.

The problem

Single-vendor agents. Opaque pricing. Production credentials on someone else's cloud. You pay a seat fee and a token markup.

The problem

IDE copilots autocomplete lines. They don't run your test suite, open a PR, or coordinate a multi-file migration across repos.

The problem

Autonomous agents without guardrails blow budgets and touch files you never approved. Teams need PLAN before CODE, not YOLO by default.

Autonomous workflows

Agents plan, edit, test, and iterate across your repos — not just suggest the next line. Pair on complex work or dispatch one-shot jobs that run to completion in a sandbox.

Any model. Your keys.

Route tasks across Anthropic, OpenAI, Google, and Ollama. Opus for architecture, Flash for batch refactors, local models for sensitive code. You pay providers directly — DevsHub charges for orchestration, not tokens.

Sandboxed execution

Sessions run in ephemeral Docker or cloud VMs. Credentials stay on your machine and inject on demand. Five permission levels from read-only PLAN to full CODE — you control what agents can touch.

Getting started

Three steps to your first agent

Invite-only for now. Once approved, you're running in under a minute.

1

Request access

Tell us about your team and use case. We send an invite to [email protected].

2

Connect your workspace

Quick setup links your project to the DevsHub control plane. Credentials stay local; sandboxes spin up on demand.

3

Run agents

Start an interactive session or fire a one-shot task. Agents edit files, run tests, and use tools inside your sandbox.

DevsHub — agent session
⬢ DevsHub · claude-opus-4 · CODE · ~/projects/api
 
Review the auth middleware for SQL injection risks
 
Reading src/middleware/auth.ts
Grepping for raw query patterns…
Found 2 issues — drafting fixes
 
/permissions /mode /resume · type / for commands
DevsHub — session history
Resume Session
1 session in api — search by title, model, or tag
 
1. Auth middleware hardening 2h ago · 18 msgs · claude-opus-4
  2. Migration batch #4 1d ago · 42 msgs · gpt-4o
 
Type to search · Enter resume · Esc cancel
Outcomes

What takes days
takes an afternoon.

PR review at scale

Agent reads the diff, checks against your style guide via skills, runs affected tests, and leaves structured review comments.

Before: 45 min per PR  →  After: 5 min human review

Framework migrations

Parallel agents refactor deprecated APIs, update configs, and fix broken imports across a monorepo — with PLAN mode first, CODE mode after approval.

Before: 6-week epic  →  After: days with agent assist

Test generation

Point an agent at uncovered modules. It writes unit and integration tests, runs them in a sandbox, and iterates until green.

Before: Backlog forever  →  After: coverage in one session

Incident response

One-shot mode: paste the stack trace, agent traces the failure, proposes a patch, runs regression tests, and opens a branch.

Before: 2am pager duty  →  After: agent drafts the fix

Platform

Everything in one stack

PLAN · CODE · ASK modes

Strict permission boundaries. Read-only analysis before write access. Interactive Q&A without touching files.

MCP + Skills

Connect any MCP server. Install community skills from the registry — Chrome DevTools, Cloudflare, databases, and more.

Session resume & checkpoints

Pick up where you left off. Rewind conversation and workspace state to any checkpoint.

Multi-agent orchestration

Supervisor-worker patterns, parallel fan-out, and specialized sub-agents with their own models and tools.

Cost tracking

Per-session token usage and spend. Restrictive guards prevent agents from silently upgrading to expensive models.

Integrations via MCP

Extend agents with MCP wrappers for GitHub, Linear, Slack, and internal APIs — composable, not locked in.

Compare

How DevsHub stacks up

Honest comparison against autonomous agents and IDE copilots.

Capability DevsHub Devin-style agents IDE copilots
Multi-provider model routing ✓ Anthropic, OpenAI, Google, Ollama Single vendor Usually one
Bring your own API keys ✓ Pay providers at cost Seat + token markup Subscription
MCP + skills ecosystem ✓ MCP + skills registry Limited Plugins
Permission granularity ✓ 5 levels (PLAN/CODE/ASK…) Coarse N/A
Runs tests & tooling end-to-end ✓ 30+ built-in tools ✓ Sandboxed Autocomplete only
Long-running agent sessions ✓ Streaming, checkpoints Dashboard UI Chat panel
Native Slack / Linear Via MCP ✓ Built-in
Enterprise dashboard polish Control plane + agents ✓ Mature ✓ Mature
Security

Your credentials never leave your machine

DevsHub isolates execution in ephemeral sandboxes. The control plane orchestrates state — it does not store your source code.

  • Local credential injection: AWS profiles, GCP keys, and SSH credentials stay on your developer machine. Injected into sandboxes on demand.
  • Ephemeral VMs: Workspaces spin up on demand and tear down when done. Docker, AWS, GCP, or Kubernetes targets.
  • Execution policies: Command allow/deny lists and permission levels enforced before any tool runs.
  • BYOC & air-gap: Self-host the control plane for regulated environments.
Pricing philosophy

Every model. Zero token markup.

Route Opus for hard problems, Flash for batch work, Ollama for sensitive code. You pay your AI provider directly.

A
Anthropic
Opus · Sonnet · Haiku
O
OpenAI
GPT-4o · O-series
G
Google
Gemini Flash · Pro
L
Local
Ollama · DeepSeek

Other platforms charge $500–$2,000/seat/month and mark up tokens 30–300%. DevsHub charges for orchestration. You pay providers at cost.

DevsHub IDE

The agent IDE.
Same engine as the CLI.

DevsHub IDE is a standalone editor experience built on VS Code. Open your repo, run agents in the integrated terminal, review inline diffs, and keep full workspace context — without switching to a separate copilot product.

Under the hood it is the same CodeSync agent you use from the shell: PLAN/CODE/ASK modes, MCP tools, session resume, and your API keys. The IDE adds selection injection, diagnostics, and blocking diff review on top of that stack.

  • Inline diffs: agents propose edits; you accept or reject in the editor before anything lands on disk.
  • Live workspace bridge: selection, open files, and diagnostics flow into the agent each turn.
  • VS Code compatible: works in VS Code, Cursor, Windsurf, and Insiders — one install path.
Download DevsHub IDE
DevsHub IDE — diff review
⬢ DevsHub · claude-sonnet-4 · CODE · ~/projects/api
 
Harden the auth middleware against SQL injection
 
openDiff src/middleware/auth.ts (1 of 2)
Parameterized queries · removed string concat
waiting for FILE_SAVED or DIFF_REJECTED…
 
/ide status /mode · attached to VS Code

Request access first

DevsHub is invite-only during early access. Once approved, connect your workspace with a one-line setup command.

Request Early Access

After you're approved

curl -fsSL https://devshub.ai/cli/install.sh | bash

Linux x86_64 · uv provisions isolated runtime · macOS & Windows coming soon

Ready to automate engineering at scale?

Tell us about your team and what you want agents to own. [email protected]

Request Access