See which features your team is building, what’s been completed, and where coding session time is spent. Carry decisions, findings, and next steps across developers and coding agents, so each new session builds on what your team already knows.
Works with every coding agent your org runs
Reads Claude Code, Cursor, Codex, Copilot, Amp, Gemini CLI and more.So every machine has every thread, whoever opened it and whichever agent they run.
See what’s in progress and what’s been tried, and carry what your agents learn across sessions and threads.
See the task and the latest recorded activity across developers and agents, not just a list of open sessions.
Fix duplicate payments
CTOFix flaky deploy pipeline
DevOpsDebug feature store staleness
MLFollow attempted fixes, recorded results, and open questions, not just the final diff.
Disabled the pay button after the first click (FE)
CTODidn’t work: a slow connection let people click it again.
Checked for a duplicate charge before saving (BE)
CTODidn’t work: two requests still landed at the exact same instant.
Gave the deploy more time to start up
DevOpsDidn’t work: it still failed under heavy traffic.
Ran the data refresh again
MLStill unverified: the numbers came back just as out of date.
Carry decisions, failed approaches, and next steps across sessions and threads, even when the developer or agent changes.
Decision
Proceed with a shared idempotency key. The fix still needs verification.
Already tried
An in-memory lock failed across multiple workers.
Next step
Run the concurrent-retry test against the fix.
Sources preserved with the context
Explore recorded session time by task, with the underlying sessions available for context.
Every agent meets your codebase as a stranger. It rereads the repo, rederives the decision and retries the approach that was already thrown out, because the reasoning from last Tuesday ended with the session that produced it. Multiply that by every developer, every tool and every machine, and an organization relearns the same thing dozens of times a week. Loopmason listens, groups and serves it back.
A read only collector reads the session logs each coding agent already writes to disk and normalises them into one vendor neutral schema. No source code is read and nothing is executed.
Sessions are correlated by repo, code region and time window, so work on the same feature arrives as one thread instead of three private transcripts nobody can see across.
The thread becomes context the next agent can read, whoever opens it, whichever tool they use. Scoped to the code they are touching, not pasted into every session.
The load balancer was closing connections faster than the app expected.
Ruled out already: DB connection pool size, downstream retries.
Understand what your agents are building, and give the next session the decisions, findings, and next steps it needs to keep going.
Install the collector once on each developer’s machine. No separate setup is required for individual coding agents. The collector is read only and never runs commands or writes to your repositories.
One background process reads every agent on the machine.
Reuse decisions, attempted solutions, experiment results, and next steps recorded in coding sessions. This can include architecture choices, bugs investigated, fixes tested, performance improvements, ML algorithms evaluated, accuracy achieved, and insights about datasets, along with why an approach was chosen or ruled out.
Your coding agent can retrieve relevant context through the Loopmason client. You can also copy context from a thread into another agent. Links to the original sessions let you check the details behind each finding.
Loopmason is in early access. We are running pilots on one repo at a time, with the collector read only and the data wherever you want it. Tell us what your team runs and we will show you your own sessions.
