Synara documentation

Synara is a free, open-source, local-first desktop workspace and control plane for coding agents. It brings provider sessions, tasks, terminals, browser work, diffs, Git worktrees, handoffs, automations, and pull-request delivery into one application.

What is Synara?

Synara is the workspace around coding-agent runtimes such as Claude Code, Codex, OpenCode, Cursor, Antigravity, Grok Build, Kilo Code, Pi, and Factory Droid. The provider still owns its account, models, tools, permissions, and service. Synara owns the durable task, working environment, transcript, review surfaces, and delivery workflow around that provider session.

What does Synara control?

• Projects and tasks: keep several repositories and durable conversations available without mixing their context.
• Provider runtimes: select supported coding agents, models, and provider-specific options from one interface.
• Development surfaces: use terminals, browser tabs, files, diffs, and Git tools beside the conversation.
• Git environments: work in the local checkout or isolate concurrent tasks in linked worktrees.
• Review and delivery: inspect changes, verify behavior, commit, push, and create pull requests.
• Orchestration: use provider handoffs, automations, Studio, Agent Gateway, and restricted External MCP access where appropriate.

Does Synara include model access?

No. Synara uses the provider runtimes, accounts, subscriptions, and API credentials already configured on your machine. Model availability and usage limits remain provider-owned.

Start with Installation and the Provider guides.

Does Synara upload code to its own cloud?

Synara stores its workspace data locally and does not require a Synara cloud account. The provider selected for a task still receives the prompts, file snippets, diffs, terminal output, or tool results needed for that provider session. Synara is the control surface; it is not a proxy for normal provider traffic.

See Privacy for the public data boundary.

How should I run my first task?

Use one clean Git repository, one provider you have already verified, and one bounded objective. Follow the transcript, inspect the complete diff, run the relevant checks independently, and commit only the changes you understand.

Use the Quickstart for the shortest path or Your first task for the complete walkthrough.

How do I run several agents safely?

Give each body of work one owner and use separate worktrees for concurrent writers. Keep objectives independently reviewable, preserve Git state before integration, and assign one integration owner.

Continue with Parallel agents and Worktrees.

Where do I go when something fails?

Start with the symptom-specific Troubleshooting hub. Preserve work before restarting or cleaning up, identify the failing layer, change one variable at a time, and collect the smallest useful diagnostic bundle.