Does RunTrim upload my source code?
No. Source code stays local by default. Cloud sync stores run metadata only.
RunTrim gives coding agents scope, memory, finish checks and restore points, which often reduces repeated context loading and shortens recovery loops.
Without a control layer, one prompt can become twelve files, wasted tokens, broken state and no clear way back.One prompt can become twelve files, wasted tokens and broken state.
Small requests drift into unrelated files.
files_touched: 12 / 3Bad runs spend context before they solve anything.
usage: +38% vs scopedCheckout, auth or config can change without warning.
risk: hiddenRunTrim rewinds the AI run, not your whole branch.
restore: localRunTrim checks scope, diff and forbidden writes.
finish: verifiedRunTrim carries project memory forward.
memory: loadedRunTrim turns a task into scope, memory and rules before edits begin. Finish checks the diff, sensitive files and proof gaps.Task, scope, memory, rules. Then finish checks the diff.
Creates memory, rules and MCP snippets.
Checks if your agent is RunTrim-ready.
Creates a scoped handoff. MCP agents can create it directly.
Checks scope, changed files and proof gaps.
Blocks risky AI-generated PRs before merge.
Preview and rewind a broken AI run locally.
Creates memory, rules and MCP snippets.
Checks if your agent is RunTrim-ready.
Creates a scoped handoff. MCP agents can create it directly.
Checks scope, changed files and proof gaps.
Blocks risky AI-generated PRs before merge.
Preview and rewind a broken AI run locally.
Early internal benchmark across repeated guarded vs unguarded tasks. Public benchmark report coming soon.
See the task, contract, changed files, risk, finish verdict, continuation state, and run history in one place.
Every guarded task records the agent, scope, changed files, and outcome.
See scope, forbidden files, tests, diff size, and the finish verdict in one place.
Next session starts from what actually happened, not from memory loss.
Shared state, approvals, and audit logs as your team workflow grows.
Scoped context keeps tasks focused and reduces repeated context loading.
Allowed paths and stop rules keep agents inside the contract boundaries.
If it can read a prompt or repo instructions, it can run through RunTrim. No SDK, no model lock-in, no rewiring.
The CLI is free forever. Upgrade when you need cloud history, synced memory, recovery metadata and team governance.
The CLI, local memory and recovery for individual AI coding runs.
Personal agent control with synced memory, cloud history and recovery metadata.
Advanced guardrails for founders shipping production code with AI agents daily.
Shared control for teams using AI coding agents.
Compare limits, cloud sync, memory, and team controls.
View all plansFAQ
No. Source code stays local by default. Cloud sync stores run metadata only.
No. Restore is local recovery. You can recover without spending another agent run.
BLOCKED means needs review. The run is recorded as evidence, but is not trusted yet.
No. MCP is optional. Copy mode works with any agent UI.
Free is local-first for one project. Pro adds cloud sync and history. Builder adds unlimited projects and CI Gate.
No. Git remains your version history. RunTrim adds control, verification and recovery for agent runs.
One command installs the protocol. Every run after that is scoped, memorable, and on the record.