SAM — Run Coding Agents in Parallel on Your Infrastructure
Get Started
Open Source & Self-Hosted
The open-source platform formulti-agent workflows
Every agent runs in its own isolated container on your cloud.<br>Run 5 or 500 in parallel — SAM handles provisioning, scheduling, and cleanup.
Get Started
View on GitHub
Supports Claude Code<br>+ OpenAI Codex
+ Gemini CLI
+ Mistral Vibe
+ OpenCode
+ Amp
AGPL-3.0 Licensed Self-Hosted BYOC
Chat-First DevelopmentDescribe what you want.<br>Watch it happen.<br>Talk to your agents like teammates. Pick the right model for the job, attach files, and watch them write code, run tests, and open PRs — all from a single chat.
Multiple agents, one interface<br>Switch between Claude Code, Codex, Gemini CLI, Amp, and more — each configured with their own API key or OAuth token. Choose the right agent for the task without leaving the chat.
Explore Chat-First Development<br>Agent profiles listed at the bottom of the chat — click to switch<br>Real-time visibility into agent work<br>Tool calls, file edits, and shell commands are streamed to your browser as they happen. You can read every step the agent takes and cancel at any time.
Explore Chat-First Development<br>Every MCP tool call, shell command, and file edit — streamed live with the ability to cancel
Full Visibility & ControlSee everything.<br>Stay in control.<br>A dashboard for all your agent work. Track active tasks across projects, monitor node health, and get notified when agents need your attention.
Multi-project dashboard<br>See active tasks with their status, project, and timing. Below that, a project grid shows workspace counts, session counts, and last activity for each repo.
Explore Full Visibility & Control<br>Active tasks at the top, all projects below — click any card to jump in<br>Infrastructure you can see<br>Each node card shows its provider, spec, pricing, CPU/memory/disk usage, and the workspaces running on it. Create new nodes or add workspaces from the same page.
Explore Full Visibility & Control<br>Node specs, real-time resource usage, and workspace allocation<br>Never miss a decision point<br>Notifications are categorized by type — task completions, errors, progress updates, sessions ended, PRs created, and moments where agents need human input. Filter to focus on what matters.
Explore Full Visibility & Control<br>Filter by type — Task Complete, Needs Input, Error, Progress, and more
Agents That LearnAgents that remember<br>your preferences.<br>Build a project knowledge base that agents receive as context. Set policies that are injected into every session. Review a full log of agent activity.
Persistent project memory<br>Store observations about your architecture, conventions, and preferences. Each entry has a confidence score, a source (explicit or inferred), and a confirmation date so you can see what the knowledge base contains.
Explore Agents That Learn<br>Each observation shows confidence, source, and when it was last confirmed<br>Project policies<br>Define project-level instructions like "use portals for modals" or "CLI packages must meet QA standards." Policies are tagged as preferences or rules and injected into every agent session as context.
Explore Agents That Learn<br>Policies are instruction-only — injected into agent context, not programmatically enforced<br>Activity log<br>A timestamped feed of every task submission, execution step, session start/stop, and agent completion event. Filter to find specific activity across the project.
Explore Agents That Learn<br>Every event type — task completions, execution steps, session lifecycle changes
Idea to ExecutionFrom idea to<br>agent-ready task.<br>Capture ideas with a problem statement and plan. Schedule recurring tasks on a weekly or daily cadence. When you are ready, dispatch an agent with one click.
Structured idea capture<br>Write down the problem, sketch a plan, and link related chat conversations for context. When you are ready, hit Execute to dispatch an agent that picks up the idea as a task.
Explore Idea to Execution<br>Each idea has a problem statement, plan, and a button to dispatch an agent<br>Recurring triggers<br>Schedule agents to run dependency updates, spot checks, audits, or other recurring work on a daily or weekly cadence. Pause, resume, or run manually any time.
Explore Idea to Execution<br>Each trigger shows its schedule, last run, next run, and status — with manual run and pause controls
Your Project, Your WayFully configurable.<br>Open source.<br>Upload reference docs, choose your VM size, and pick a default agent — each project has its own settings for infrastructure and agent configuration.
Project library<br>Upload architecture docs, research, and reference material. Files are organized with folders and tags. Agents can access library files as additional context during their work.
Explore Your Project, Your Way<br>Folders, tags, and upload — agents can pull files from the library as context<br>Built-in document viewer<br>Markdown files render with full formatting, including Mermaid diagrams. Toggle between the...